Research ArticleResearch on Mathematical Model of Cost Budget in the EarlyStageofAssemblyConstructionProjectBasedonImprovedNeuralNetwork Algorithm

Xin Lin 1 and Yinan Lu 2

1School of Urban Construction Engineering Chongqing Radio amp TV University Chongqing China2School of Information Engineering Nanchang University Nanchang China

Correspondence should be addressed to Xin Lin lxcqrtvu_edu126com

Received 2 May 2020 Accepted 25 June 2020 Published 15 July 2020

Academic Editor Jia-Bao Liu

Copyright copy 2020 Xin Lin and Yinan Lu is is an open access article distributed under the Creative Commons AttributionLicense which permits unrestricted use distribution and reproduction in any medium provided the original work isproperly cited

In view of the poor performance of the original mathematical model of assembly construction project precost budget amathematical model of assembly construction project precost budget based on improved neural network algorithm is proposedis paper investigates the cost content of assembly construction project and analyzes its early cost It finds that the early cost ofassembly construction project includes component production cost transportation component cost and installation componentcost Based on the improved neural network algorithm to build an improved neural network model the improved neural networkmodel to mine the cost data in the early stage of assembly construction project is used In this paper the earned value variable isintroduced to transform the project duration and project cost in the early stage of the prefabricated construction project intoquantifiable cost data and the earned value analysis method is used to estimate the implementation cost of the prefabricatedconstruction project According to the result of cost estimation the mathematical model of precost budget of prefabricatedconstruction project is built based on the project parameters In order to prove that the cost budget performance of themathematical model based on the improved neural network algorithm in the early stage of assembly construction project is betterthe original mathematical model is compared with the mathematical model the experimental results show that the cost budgetperformance of the model is better than the original model and the cost budget performance is improved

1 Introduction

In traditional construction projects the pouring of concretemainly adopts manual scaffolding formwork supportingand binding of steel bars at site However such kind of cast-in-place can cause a variety of problems including makingconstruction site in a mess generating lots of constructionwaste and polluting the surrounding environment [1]Meanwhile with the progress of population aging and theincrease of labor costs in China this extensive constructionmodel is no longer suitable for the green energy-saving andenvironmentally friendly concepts Under this circumstancethe prefabricated construction project emerged at the rightmoment and eased this dilemma As a new building con-struction technology prefabricated construction project

means to process and produce the prefabricated componentsin factory move them to the construction site after main-tenance and then assemble the building components ac-cordingly through machinery equipment to achieve thebuilding functional requirements [2] Compared with thecast-in-place construction method the prefabricated con-struction project can save about 20 of materials and 80 ofwater resources in manufacturing and processing buildingcomponents At the same time in prefabricated constructionproject protective nets and scaffolding are not used duringconstruction which reduced construction waste and low-ered the pollution and harm to the environment [3]

Under the trend of urbanization people have put for-ward higher requirements for environmental protection andenergy-saving performance of buildings erefore

HindawiMathematical Problems in EngineeringVolume 2020 Article ID 3674929 7 pageshttpsdoiorg10115520203674929

prefabricated buildings are getting popular have achievedrapid development in China and promoted the improve-ment of the installation quality and component precision ofprefabricated components [4] However based on thecurrent construction market the overall production scale ofprefabricated buildings is restricted so that it is unable toreduce the construction cost budget through expanding thescale which limited the development of prefabricatedbuildings in China and affected the industrialization processof construction field At its initial stage of developmentprefabricated buildings in China are still facing manyshortcomings in technology experience and cost control[5] In order to accelerate the development of prefabricatedbuildings an innovative research on the mathematicalmodel of cost budget in early stage of prefabricated con-struction is carried out On this basis a mathematical modelof cost budget in the early stage of prefabricated constructionproject based on improved neural network algorithm isproposed [6]

2 Design of Mathematical Model of CostBudget in the Early Stage of PrefabricatedConstruction Project Based on ImprovedNeural Network Algorithm

21 Analysis of Cost in the Early Stage of PrefabricatedConstruction Project As found in the cost analysis in earlystage of the prefabricated construction project the pre-liminary cost of prefabricated construction project includescomponent production cost component transportationcost and component installation cost Among them sta-tistics found that component production cost contains laborcost material cost mold cost amortization expense cost ofsetting the embedded parts and pipelines management andstorage cost and water and electricity charges e specificcontents are shown in Table 1 [7]

Component transportation cost covers the cost oftransporting components from the factory to the con-struction site which is directly related to the size and weightof the components as well as the distance between thefactory and the construction site [8]

Component installation costs involves the cost of verticalcomponent transportation labor cost of component in-stallation machinery cost of component installation ma-terial cost of component installation cast-in-place cost andamortization cost as shown in Table 2 [9]

22 Data Mining of Cost in the Early Stage of PrefabricatedConstruction Project As shown in the analysis of costbudget in early stage of prefabricated construction projectan improved neural network model is built based on theimproved neural network algorithm so as to conduct datamining on the cost budget in early stage of prefabricatedconstruction project [10] e specific steps are as follows

(1) First the improved neural network is initialized(X Y) is adopted to represent the input and outputsequence of the improved neural network Based on

this sequence the specific number of nodes corre-sponding to the output layer hidden layer and inputlayer of the improved neural network is clarifiedwhich is m l and n nodes respectively Next thethreshold and the connection weight are initializede neuron connection weight between the hiddenlayer and the input layer is set to ωij the neuronconnection weight between the output layer and thehidden layer is set to ωjk the thresholds of the outputlayer and hidden layer is b and a respectively Fi-nally the learning rate of the improved neuralnetwork is set to η and the excitation neuronfunction is set to f(x) [11]

(2) e specific output of the hidden layer is computedthe specific output of the hidden layer is obtainedbased on the specific input variable X of the im-proved neural network the threshold value a of thehidden layer and the neuron connection weight ωij

between the hidden layer and the input layer edetails are as follows

Hj f 1113944n

i1ωijxi minus aj

⎛⎝ ⎞⎠ j 1 2 3 l⎧⎨

⎩ (1)

In formula 1 Hj represents the specific output of thehidden layer xi represents the ith input value aj

represents the threshold of the jth hidden layer and l

represents the specific number of nodes of thehidden layer [12]

(3) e specific output of the input layer is computedthe specific output of the input layer is obtainedaccording to the specific output Hj of the hiddenlayer the threshold value b of the output layer andthe neuron connection weight ωjk between theoutput layer and the hidden layer

Ok 1113944l

i1Hjωjk minus bk k 1 2 3 m

⎧⎨

⎩ (2)

In forrmula 2 Ok represents the specific output ofthe input layer and bk represents the threshold of thekth output layer [13]

(4) Error calculation the specific error of the improvedneural network is predicted based on the specificoutput of the input layer and the specific expectedoutput Y of the improved neural network

(5) e neuron connection weight ωij between thehidden layer and the input layer and the neuronconnection weight ωjk between the output layer andthe hidden layer are updated according to the specificpredicted error of the improved neural network

(6) reshold updating the thresholds b and a of theoutput layer and hidden layer are updated accordingto the specific predicted error of the improved neuralnetwork

(7) e construction of improved neural network modelis realized and the data mining on the cost in early

2 Mathematical Problems in Engineering

stage of prefabricated construction project is per-formed on this basis [14]

23 Cost Budget in Early Stage of Prefabricated ConstructionProject Based on the data mining of cost in early stage ofprefabricated construction project a variable called earnedvalue is introduced to convert the project duration andproject cost in early stage of prefabricated construction intoquantifiable cost data Meanwhile the cost in early stage ofprefabricated construction project is estimated through theearned value analysis so as to carry out the cost budget ofprefabricated construction project [15] e calculationformula of earned value is as follows

EV A times B (3)

In formula 3 EV represents earned value A representsthe project actual workload and B represents the cost budgetof the completed project

For the analysis by using the earned value the differencevariables of two analyzes must be obtained at first includingschedule deviation and cost deviation eir calculationformulas are separately as follows

SV B minus BSWS (4)

In formula 4 SV represents the schedule deviation andBSWS represents the cost budget of planned project volume

CV B minus ACWP (5)

In formula 5 CV represents cost deviation and ACWP

represents the specific cost of the completed project volume[16]

Along with two variable indexes including performanceprogress index and performance cost index the calculationformulas are as follows

SPI B

BCWS (6)

In formula 6 SPI represents the performance progressindex

CPI B

ACWP (7)

In formula 7 CPI represents the performance costindex

e data of the cost budget of completed project volumethe specific cost of completed project volume and the costbudget of planned project volume are added separately [17]in analysis so that 3 corresponding cumulative series areobtained By inputting data of cost budget of completedproject volume the specific cost of completed project vol-ume and the cost budget of planned project volume into atwo-dimensional coordinate axis of time and cost and 3analysis curves are obtained and applied to analyze theperiod and cost in early stage of prefabricated constructionproject Among them when the cost deviation is greaterthan 0 it indicates that the early stage of prefabricatedconstruction project is in a cost-saving state when the costdeviation is less than 0 it indicates that the early stage ofprefabricated construction project is in the over-cost statewhen the progress deviation is greater than 0 it indicatesthat the early stage of prefabricated construction project is ina state of advanced progress when the progress deviation isless than 0 it indicates that the early stage of prefabricatedconstruction project is in a state of delayed progresse cost

Table 1 Component production cost

No Name of cost Content of cost1 Labor cost of component production Higher salaries shall be paid to professional workers2 Material cost of component production Basically the same materials as required by the traditional construction method

3 Mold cost of component production Cost of table molding binding steel bar mold concrete pouring mold maintenance moldand finished component mold

4 Amortization expense Amortization fee based on specific types of components and specific quantities of molds

5 Cost of setting the embedded parts andpipelines

Costs incurred in arranging the embedded parts and pipelines in the installationcomponents mainly the pipeline costs

6 Management and storage cost Additional management and storage costs after maintenance of component productions7 Water and electricity charges Electricity and water charges incurred by factory component production

Table 2 Component installation cost

No Name of cost Content of cost

1 Cost of vertical componenttransportation Cost of vertically hoisting components

2 Labor cost of componentinstallation

Higher labor salaries shall be paid because the vertical hoisting of components requires higherprofessionalism and proficiency

3 Machinery cost of componentinstallation e cost generated by using machinery equipment during component installation

4 Material cost of componentinstallation Costs incurred by filling materials and connectors

5 Cast-in-place cost Cast-in-place cost for assembly6 Amortization cost Amortization cost of tools

Mathematical Problems in Engineering 3

of prefabricated buildings can be estimated by inputting theconstruction period and cost analysis results of early stage ofthe prefabricated construction project as well as the actualstatus of the early stage of project into the project man-agement software

24 Mathematical Model of Cost Budget in Early Stage ofPrefabricated Construction Project According to the esti-mated cost in the early stage of prefabricated constructionproject the mathematical model of cost budget in early stageof prefabricated construction project is constructed based onproject parameters e items of material budget in earlystage of prefabricated construction project are shown inTable 3

e project parameters are described according to thetype of project in which the parameter of productionprogress in the early stage of prefabricated constructionproject is set to rg the parameter of production calculationperiod is set to T the parameter of periodic component

production batch is set to N labor demand cost is set toL(P) machinery demand cost is set to L(c) other expensessuch as management fee are set to K demand machineryvalue is set to FL site cost is set to AC equipment rental costis set to F(c) the upper limit of transportation cost is set toP(c) and the assembly cost is set to Asum

e production process in early stage of prefabricatedconstruction project can be summarized as follows the firstif component production followed by component assemblyand transportation In this way the cost in early stage ofprefabricated construction project includes constructionproduction cost component assembly and transportationfee [19] erefore by setting parameters of productionprogress in early stage of prefabricated construction projectas independent variables and the minimum budget cost asthe model objective function then the mathematical modelof cost budge in the early stage of prefabricated constructionprojects is established as follows [20]

rg T

N

MinCost A(c) 1113946T

0L(p)dt + L(c) 1113946

T

0Adt + F(L) 1113946

T

0F(c)dt + K middot P(c) middot Asum

⎧⎪⎪⎪⎪⎪⎨

⎪⎪⎪⎪⎪⎩

(8)

In formula 8 MinCost represents the minimum costbudget in the early stage

3 Experimental Research and Result Analysis

31 Experiment Design e experiment of cost budget inearly stage of prefabricated construction project is carriedout by using the mathematical model of cost budget in earlystage of prefabricated construction project designed basedon improved neural network algorithm With a total area of920 square meters the prefabricated construction project inthis experiment contains 14 floors in prefabricated struc-tures of assembled shear wall e prefabricated componentnodes are manufactured by secondary cast-in-place eouter wall of the building is made of prefabricated thermalinsulation Sandwich panel the floor is made of concreteprestressed composite slab the load-bearing wall is made ofshear prefabricated wall panel the staircase is prefabricatedthe inner partition wall is made of lightweight wall panele prefabricated parts involved in this prefabricated con-struction project are listed as follows prefabricated parts forstair prefabricated parts for laminated panel prefabricatedparts for partition wall shear wall etc Considering that it isa prefabricated construction project all the prefabricatedparts are produced at the prefabricated production base andthen transported to the construction site after maintenanceMeanwhile the transportation and production of pre-fabricated parts for different places and floors are arrangedseparately according to the specific project progress

e specific building parameters of this prefabricatedbuilding project are shown in Table 6

In this prefabricated construction project all the floorsare standard and the early stage is set to a six-day con-struction period per floor According to the buildingstructure and engineering quantity the construction se-quence is arranged reasonably and the whole project isdivided into three phases e specific arrangements for theconstruction of each floor are as follows hoisting 60 pieces ofwall in the first construction phase hoisting 60 pieces of wallin the second construction phase grouting sleeve in the firstconstruction phase grouting sleeve in the second con-struction phase hoisting 30 pieces of wall in the thirdconstruction phase grouting sleeves in the third construc-tion phase binging steel bars with postcasting belts rein-forcing formwork with postcasting belts erecting supportiveframes hoisting composite beams hoisting stairs hoistingof 60 pieces of composite slabs hoisting 57 pieces ofcomposite slabs preburying hydropower and other pipe-lines binding the upper stair reinforcement supportingformwork joints and pouring concrete e cost budget inearly stage of this prefabricated building construction isestimated through the mathematical model In order toensure the effectiveness and contrast of this experiment theoriginal mathematical model of cost budget in the early stageof prefabricated construction project is compared to themathematical model of cost budget in the early stage ofprefabricated construction project designed based on theimproved neural network algorithm in this paper Among

4 Mathematical Problems in Engineering

Table 3 Items of material budget in early stage of prefabricated construction project

No Items of material budget Unit1 Prefabricated PC wall components Cubic meter2 Prefabricated PC floor (laminated) components Cubic meter3 Prefabricated PC stair components Cubic meter4 Prefabricated PC balcony components Cubic meter5 Prefabricated PC air conditioning panel components Cubic meter6 Prefabricated PC beam components Cubic meter7 Rebar B300HR(Dlt 25) Ton8 Screw-thread steel B225HR(Dlt 12) Ton9 Concrete C30 (premixed) Cubic meter10 Concrete C35 (premixed) Cubic meter11 Fine stone concrete C20 (premixed) Cubic meter12 Aerated light sand autoclaved block concrete Cubic meter13 Specialized component grouting Ton14 Remaining self-purchased materials (estimated value) mdashe items of labor cost budget in early stage of prefabricated construction project are shown in Table 4 [18]

Table 4 Items of labor cost budget in early stage of prefabricated construction project

No Items of labor cost Unit1 Manual cleaning of foundation pit Cubic meter2 Manual lashing of cast-in-place and steel bar making Ton3 Manual assembly and wooden template making Cubic meter4 Manual maintenance of cast-in-place and concrete pouring Cubic meter5 Manual installation of prefabricated PC components Cubic meter6 Tower crane driver surveyor and bell man Cubic meter7 Manual masonry Cubic meter8 Manual water resistance Cubic meter9 Manual fitment Cubic metere items of machinery budget in early stage of prefabricated construction project are shown in Table 5

Table 5 Items of machinery budget in early stage of prefabricated construction project

No Name Unit Type1 (Tower) crane Set ST50202 Car crane Set 26T3 Material hoist Set SES160

Table 6 Specific building parameters of this prefabricated building project

No Name of building parameters Specific parameters1 Height 40m2 Floors 143 Structure type Prefabricated structure of assembled shear wall

4 Specific floor height 36M at 1st floor28M from 2nd to 14th floor

5 Covered area 920m2

6 Seismic grade 40 magnitude7 Seismic intensity Scale 68 Specific flame resistance Level 29 Specific waterproof rating Level 2

11 Specific type of prefabricated part

Shear wallPartition wallComposite slab

Platforms ladder beams stairs12 Building nature Residence13 Plan view size 15times 4014 Waterproof condition (roofing) Composite SBS waterproof15 Production materials such as windows and doors High quality aluminum alloye specific contracting situation of this prefabricated construction project is shown in Table 7

Mathematical Problems in Engineering 5

them the original mathematical model of cost budget inearly stage of prefabricated construction project includes themathematical model of cost budget in early stage of pre-fabricated construction project based on cost control ran-dom function and system dynamics As learned fromcomparing the performance of different mathematicalmodels of cost budget in early stage of prefabricated con-struction project that is from analyzing the cost budgetaccuracy of the experimental model the higher the costbudget accuracy the more reasonable the cost budget resultof the prefabricated construction project and the better costbudget performance [21]

32 Analysis Results e result of comparative experimenton cost budget performance between the original mathe-matical model of cost budget in early stage of prefabricatedconstruction project and the mathematical model of costbudget in early stage of prefabricated construction projectdesigned based on the improved neural network algorithm isshown in Figure 1

According to the result of comparative experiment oncost budget performance between two different mathe-matical models the mathematical model of cost budget in

early stage of prefabricated construction project designedbased on the improved neural network algorithm is better incost budget accuracy at means the cost budget perfor-mance of the mathematical model of cost budget in earlystage of prefabricated construction project based on theimproved neural network algorithm is superior to that of theoriginal mathematical model of cost budget in early stage ofprefabricated construction project

4 Conclusions

e cost budget performance of the mathematical model ofcost budget in the early stage of prefabricated constructionproject based on the improved neural network algorithm canrealize the improvement of cost budget performance in theearly stage of prefabricated construction project which is ofgreat reference significance to accurate cost budget of theoverall prefabricated construction project

Data Availability

Simulation data and our model and related hyperparametersused are provided within the article

Conflicts of Interest

e authors declare that they have no conflicts of interest

Acknowledgments

is work was supported by the Chongqing MunicipalEducation Commission Science and Technology ResearchProject (KJQN201904003) and research project ofChongqing Technology and Business Institute (ZD2016-04)

References

[1] G E Gurcanli S Bilir and M Sevim ldquoActivity based riskassessment and safety cost estimation for residential buildingconstruction projectsrdquo Safety Science vol 80 pp 1ndash12 2015

[2] Y T Chae R Horesh Y Hwang and Y M Lee ldquoArtificialneural network model for forecasting sub-hourly electricityusage in commercial buildingsrdquo Energy and Buildingsvol 111 pp 184ndash194 2016

[3] M-Y Cheng H-C Tsai and E Sudjono ldquoConceptual costestimates using evolutionary fuzzy hybrid neural network for

Table 7 Specific contracting situation of this prefabricated construction project

No Items Specific situation1 Specific project name Project of Fuligang building 22 Construction company Haoqiang Real Estate co ltd3 Design contractor Yicai Architectural Design co ltd4 Supervision company Keli Supervision Construction co ltd5 Construction organization Risheng Engineering Cconstruction co ltd6 Quality supervision organization Yihe Engineering Quality Supervision co ltd7 Total project cost RMB 126 million8 Contracted form Contract for labor and material9 Contract scope Decoration main body foundation10 Planned schedule One year11 Overall quality goal Good in quality

Cost control modelSystem dynamics model

Random function model

Improverd neural networkalgorithm model

0

20

40

60

80

100

Cost

budg

et ac

cura

cy (

)

2 10 12 1464 80Time (month)

Figure 1 Result of comparative experiment on cost budgetperformance

6 Mathematical Problems in Engineering

projects in construction industryrdquo Expert Systems with Ap-plications vol 37 no 6 pp 4224ndash4231 2010

[4] K H Hyari A Al-Daraiseh and M El-Mashaleh ldquoCon-ceptual cost estimation model for engineering services inpublic construction projectsrdquo Journal of Management inEngineering vol 32 Article ID 04015021 2016

[5] B Pal A Mhashilkar A Pandey B Nagphase andV Chandanshive ldquoCost estimation model (CEM) of buildingsby ANN (artificial neural networks)ndashA reviewrdquo NeuralNetworks vol 5 pp 1ndash15 2018

[6] J Liu X Li D Wu and J Dong ldquoCost estimation of buildingindividual cooperative housing with crowdfunding modelcase of Beijing Chinardquo Journal of Intelligent Manufacturingvol 28 no 3 pp 749ndash757 2017

[7] H Piili A Happonen T Vaisto V VenkataramananJ Partanen and A Salminen ldquoCost estimation of laser ad-ditive manufacturing of stainless steelrdquo Physics Procediavol 78 pp 388ndash396 2015

[8] O Tatari and M Kucukvar ldquoCost premium prediction ofcertified green buildings a neural network approachrdquoBuilding and Environment vol 46 no 5 pp 1081ndash1086 2011

[9] S C Lhee I Flood and R R Issa ldquoDevelopment of a two-stepneural network-based model to predict construction costcontingencyrdquo Journal of Information Technology in Con-struction (ITcon) vol 19 pp 399ndash411 2014

[10] V Chandanshive and A R Kambekar ldquoEstimation ofbuilding construction cost using artificial neural networksrdquoJournal of Soft Computing in Civil Engineering vol 3pp 91ndash107 2019

[11] J A Rodger ldquoA fuzzy nearest neighbor neural networkstatistical model for predicting demand for natural gas andenergy cost savings in public buildingsrdquo Expert Systems withApplications vol 41 no 4 pp 1813ndash1829 2014

[12] G Ngowtanasuwan ldquoMathematical model for optimization ofconstruction contracting in housing development projectrdquoProcedia-Social and Behavioral Sciences vol 105 pp 94ndash1052013

[13] D-K Bui T Nguyen J-S Chou H Nguyen-Xuan andT D Ngo ldquoA modified firefly algorithm-artificial neuralnetwork expert system for predicting compressive and tensilestrength of high-performance concreterdquo Construction andBuilding Materials vol 180 pp 320ndash333 2018

[14] E Asadi M G d Silva C H Antunes L Dias andL Glicksman ldquoMulti-objective optimization for buildingretrofit a model using genetic algorithm and artificial neuralnetwork and an applicationrdquo Energy and Buildings vol 81pp 444ndash456 2014

[15] M Ceylan M H Arslan R Ceylan M Y Kaltakci andY Ozbay ldquoA new application area of ANN and ANFISdetermination of earthquake load reduction factor of pre-fabricated industrial buildingsrdquo Civil Engineering and Envi-ronmental Systems vol 27 no 1 pp 53ndash69 2010

[16] A Nasirian M Arashpour B Abbasi and A AkbarnezhadldquoOptimal work assignment to multiskilled resources in pre-fabricated constructionrdquo Journal of Construction Engineeringand Management vol 145 pp 4019ndash4034 2019

[17] H Quan D Srinivasan and A Khosravi ldquoParticle swarmoptimization for construction of neural network-based pre-diction intervalsrdquo Neurocomputing vol 127 pp 172ndash1802014

[18] H-L Yip H Fan and Y-H Chiang ldquoPredicting the main-tenance cost of construction equipment comparison betweengeneral regression neural network and Box-Jenkins time

series modelsrdquo Automation in Construction vol 38 pp 30ndash38 2014

[19] J Sobhani M Najimi A R Pourkhorshidi and T ParhizkarldquoPrediction of the compressive strength of no-slump concretea comparative study of regression neural network and ANFISmodelsrdquo Construction and Building Materials vol 24 no 5pp 709ndash718 2010

[20] R Sonmez ldquoRange estimation of construction costs usingneural networks with bootstrap prediction intervalsrdquo ExpertSystems with Applications vol 38 no 8 pp 9913ndash9917 2011

[21] A O Elfaki S Alatawi and E Abushandi ldquoUsing intelligenttechniques in construction project cost estimation 10-yearsurveyrdquo Advances in Civil Engineering vol 2014 pp 1023ndash1031 2014

Mathematical Problems in Engineering 7

stage of prefabricated construction project is per-formed on this basis [14]

23 Cost Budget in Early Stage of Prefabricated ConstructionProject Based on the data mining of cost in early stage ofprefabricated construction project a variable called earnedvalue is introduced to convert the project duration andproject cost in early stage of prefabricated construction intoquantifiable cost data Meanwhile the cost in early stage ofprefabricated construction project is estimated through theearned value analysis so as to carry out the cost budget ofprefabricated construction project [15] e calculationformula of earned value is as follows

EV A times B (3)

In formula 3 EV represents earned value A representsthe project actual workload and B represents the cost budgetof the completed project

For the analysis by using the earned value the differencevariables of two analyzes must be obtained at first includingschedule deviation and cost deviation eir calculationformulas are separately as follows

SV B minus BSWS (4)

In formula 4 SV represents the schedule deviation andBSWS represents the cost budget of planned project volume

CV B minus ACWP (5)

In formula 5 CV represents cost deviation and ACWP

represents the specific cost of the completed project volume[16]

Along with two variable indexes including performanceprogress index and performance cost index the calculationformulas are as follows

SPI B

BCWS (6)

In formula 6 SPI represents the performance progressindex

CPI B

ACWP (7)

In formula 7 CPI represents the performance costindex

e data of the cost budget of completed project volumethe specific cost of completed project volume and the costbudget of planned project volume are added separately [17]in analysis so that 3 corresponding cumulative series areobtained By inputting data of cost budget of completedproject volume the specific cost of completed project vol-ume and the cost budget of planned project volume into atwo-dimensional coordinate axis of time and cost and 3analysis curves are obtained and applied to analyze theperiod and cost in early stage of prefabricated constructionproject Among them when the cost deviation is greaterthan 0 it indicates that the early stage of prefabricatedconstruction project is in a cost-saving state when the costdeviation is less than 0 it indicates that the early stage ofprefabricated construction project is in the over-cost statewhen the progress deviation is greater than 0 it indicatesthat the early stage of prefabricated construction project is ina state of advanced progress when the progress deviation isless than 0 it indicates that the early stage of prefabricatedconstruction project is in a state of delayed progresse cost

Table 1 Component production cost

No Name of cost Content of cost1 Labor cost of component production Higher salaries shall be paid to professional workers2 Material cost of component production Basically the same materials as required by the traditional construction method

3 Mold cost of component production Cost of table molding binding steel bar mold concrete pouring mold maintenance moldand finished component mold

4 Amortization expense Amortization fee based on specific types of components and specific quantities of molds

5 Cost of setting the embedded parts andpipelines

Costs incurred in arranging the embedded parts and pipelines in the installationcomponents mainly the pipeline costs

6 Management and storage cost Additional management and storage costs after maintenance of component productions7 Water and electricity charges Electricity and water charges incurred by factory component production

Table 2 Component installation cost

No Name of cost Content of cost

1 Cost of vertical componenttransportation Cost of vertically hoisting components

2 Labor cost of componentinstallation

Higher labor salaries shall be paid because the vertical hoisting of components requires higherprofessionalism and proficiency

3 Machinery cost of componentinstallation e cost generated by using machinery equipment during component installation

4 Material cost of componentinstallation Costs incurred by filling materials and connectors

5 Cast-in-place cost Cast-in-place cost for assembly6 Amortization cost Amortization cost of tools

Mathematical Problems in Engineering 3

of prefabricated buildings can be estimated by inputting theconstruction period and cost analysis results of early stage ofthe prefabricated construction project as well as the actualstatus of the early stage of project into the project man-agement software

24 Mathematical Model of Cost Budget in Early Stage ofPrefabricated Construction Project According to the esti-mated cost in the early stage of prefabricated constructionproject the mathematical model of cost budget in early stageof prefabricated construction project is constructed based onproject parameters e items of material budget in earlystage of prefabricated construction project are shown inTable 3

e project parameters are described according to thetype of project in which the parameter of productionprogress in the early stage of prefabricated constructionproject is set to rg the parameter of production calculationperiod is set to T the parameter of periodic component

production batch is set to N labor demand cost is set toL(P) machinery demand cost is set to L(c) other expensessuch as management fee are set to K demand machineryvalue is set to FL site cost is set to AC equipment rental costis set to F(c) the upper limit of transportation cost is set toP(c) and the assembly cost is set to Asum

e production process in early stage of prefabricatedconstruction project can be summarized as follows the firstif component production followed by component assemblyand transportation In this way the cost in early stage ofprefabricated construction project includes constructionproduction cost component assembly and transportationfee [19] erefore by setting parameters of productionprogress in early stage of prefabricated construction projectas independent variables and the minimum budget cost asthe model objective function then the mathematical modelof cost budge in the early stage of prefabricated constructionprojects is established as follows [20]

rg T

N

MinCost A(c) 1113946T

0L(p)dt + L(c) 1113946

T

0Adt + F(L) 1113946

T

0F(c)dt + K middot P(c) middot Asum

⎧⎪⎪⎪⎪⎪⎨

⎪⎪⎪⎪⎪⎩

(8)

In formula 8 MinCost represents the minimum costbudget in the early stage

3 Experimental Research and Result Analysis

31 Experiment Design e experiment of cost budget inearly stage of prefabricated construction project is carriedout by using the mathematical model of cost budget in earlystage of prefabricated construction project designed basedon improved neural network algorithm With a total area of920 square meters the prefabricated construction project inthis experiment contains 14 floors in prefabricated struc-tures of assembled shear wall e prefabricated componentnodes are manufactured by secondary cast-in-place eouter wall of the building is made of prefabricated thermalinsulation Sandwich panel the floor is made of concreteprestressed composite slab the load-bearing wall is made ofshear prefabricated wall panel the staircase is prefabricatedthe inner partition wall is made of lightweight wall panele prefabricated parts involved in this prefabricated con-struction project are listed as follows prefabricated parts forstair prefabricated parts for laminated panel prefabricatedparts for partition wall shear wall etc Considering that it isa prefabricated construction project all the prefabricatedparts are produced at the prefabricated production base andthen transported to the construction site after maintenanceMeanwhile the transportation and production of pre-fabricated parts for different places and floors are arrangedseparately according to the specific project progress

e specific building parameters of this prefabricatedbuilding project are shown in Table 6

In this prefabricated construction project all the floorsare standard and the early stage is set to a six-day con-struction period per floor According to the buildingstructure and engineering quantity the construction se-quence is arranged reasonably and the whole project isdivided into three phases e specific arrangements for theconstruction of each floor are as follows hoisting 60 pieces ofwall in the first construction phase hoisting 60 pieces of wallin the second construction phase grouting sleeve in the firstconstruction phase grouting sleeve in the second con-struction phase hoisting 30 pieces of wall in the thirdconstruction phase grouting sleeves in the third construc-tion phase binging steel bars with postcasting belts rein-forcing formwork with postcasting belts erecting supportiveframes hoisting composite beams hoisting stairs hoistingof 60 pieces of composite slabs hoisting 57 pieces ofcomposite slabs preburying hydropower and other pipe-lines binding the upper stair reinforcement supportingformwork joints and pouring concrete e cost budget inearly stage of this prefabricated building construction isestimated through the mathematical model In order toensure the effectiveness and contrast of this experiment theoriginal mathematical model of cost budget in the early stageof prefabricated construction project is compared to themathematical model of cost budget in the early stage ofprefabricated construction project designed based on theimproved neural network algorithm in this paper Among

4 Mathematical Problems in Engineering

Table 3 Items of material budget in early stage of prefabricated construction project

No Items of material budget Unit1 Prefabricated PC wall components Cubic meter2 Prefabricated PC floor (laminated) components Cubic meter3 Prefabricated PC stair components Cubic meter4 Prefabricated PC balcony components Cubic meter5 Prefabricated PC air conditioning panel components Cubic meter6 Prefabricated PC beam components Cubic meter7 Rebar B300HR(Dlt 25) Ton8 Screw-thread steel B225HR(Dlt 12) Ton9 Concrete C30 (premixed) Cubic meter10 Concrete C35 (premixed) Cubic meter11 Fine stone concrete C20 (premixed) Cubic meter12 Aerated light sand autoclaved block concrete Cubic meter13 Specialized component grouting Ton14 Remaining self-purchased materials (estimated value) mdashe items of labor cost budget in early stage of prefabricated construction project are shown in Table 4 [18]

Table 4 Items of labor cost budget in early stage of prefabricated construction project

No Items of labor cost Unit1 Manual cleaning of foundation pit Cubic meter2 Manual lashing of cast-in-place and steel bar making Ton3 Manual assembly and wooden template making Cubic meter4 Manual maintenance of cast-in-place and concrete pouring Cubic meter5 Manual installation of prefabricated PC components Cubic meter6 Tower crane driver surveyor and bell man Cubic meter7 Manual masonry Cubic meter8 Manual water resistance Cubic meter9 Manual fitment Cubic metere items of machinery budget in early stage of prefabricated construction project are shown in Table 5

Table 5 Items of machinery budget in early stage of prefabricated construction project

No Name Unit Type1 (Tower) crane Set ST50202 Car crane Set 26T3 Material hoist Set SES160

Table 6 Specific building parameters of this prefabricated building project

No Name of building parameters Specific parameters1 Height 40m2 Floors 143 Structure type Prefabricated structure of assembled shear wall

4 Specific floor height 36M at 1st floor28M from 2nd to 14th floor

5 Covered area 920m2

6 Seismic grade 40 magnitude7 Seismic intensity Scale 68 Specific flame resistance Level 29 Specific waterproof rating Level 2

11 Specific type of prefabricated part

Shear wallPartition wallComposite slab

Platforms ladder beams stairs12 Building nature Residence13 Plan view size 15times 4014 Waterproof condition (roofing) Composite SBS waterproof15 Production materials such as windows and doors High quality aluminum alloye specific contracting situation of this prefabricated construction project is shown in Table 7

Mathematical Problems in Engineering 5

them the original mathematical model of cost budget inearly stage of prefabricated construction project includes themathematical model of cost budget in early stage of pre-fabricated construction project based on cost control ran-dom function and system dynamics As learned fromcomparing the performance of different mathematicalmodels of cost budget in early stage of prefabricated con-struction project that is from analyzing the cost budgetaccuracy of the experimental model the higher the costbudget accuracy the more reasonable the cost budget resultof the prefabricated construction project and the better costbudget performance [21]

32 Analysis Results e result of comparative experimenton cost budget performance between the original mathe-matical model of cost budget in early stage of prefabricatedconstruction project and the mathematical model of costbudget in early stage of prefabricated construction projectdesigned based on the improved neural network algorithm isshown in Figure 1

According to the result of comparative experiment oncost budget performance between two different mathe-matical models the mathematical model of cost budget in

early stage of prefabricated construction project designedbased on the improved neural network algorithm is better incost budget accuracy at means the cost budget perfor-mance of the mathematical model of cost budget in earlystage of prefabricated construction project based on theimproved neural network algorithm is superior to that of theoriginal mathematical model of cost budget in early stage ofprefabricated construction project

4 Conclusions

e cost budget performance of the mathematical model ofcost budget in the early stage of prefabricated constructionproject based on the improved neural network algorithm canrealize the improvement of cost budget performance in theearly stage of prefabricated construction project which is ofgreat reference significance to accurate cost budget of theoverall prefabricated construction project

Data Availability

Simulation data and our model and related hyperparametersused are provided within the article

Conflicts of Interest

e authors declare that they have no conflicts of interest

Acknowledgments

is work was supported by the Chongqing MunicipalEducation Commission Science and Technology ResearchProject (KJQN201904003) and research project ofChongqing Technology and Business Institute (ZD2016-04)

References

[1] G E Gurcanli S Bilir and M Sevim ldquoActivity based riskassessment and safety cost estimation for residential buildingconstruction projectsrdquo Safety Science vol 80 pp 1ndash12 2015

[2] Y T Chae R Horesh Y Hwang and Y M Lee ldquoArtificialneural network model for forecasting sub-hourly electricityusage in commercial buildingsrdquo Energy and Buildingsvol 111 pp 184ndash194 2016

[3] M-Y Cheng H-C Tsai and E Sudjono ldquoConceptual costestimates using evolutionary fuzzy hybrid neural network for

Table 7 Specific contracting situation of this prefabricated construction project

No Items Specific situation1 Specific project name Project of Fuligang building 22 Construction company Haoqiang Real Estate co ltd3 Design contractor Yicai Architectural Design co ltd4 Supervision company Keli Supervision Construction co ltd5 Construction organization Risheng Engineering Cconstruction co ltd6 Quality supervision organization Yihe Engineering Quality Supervision co ltd7 Total project cost RMB 126 million8 Contracted form Contract for labor and material9 Contract scope Decoration main body foundation10 Planned schedule One year11 Overall quality goal Good in quality

Cost control modelSystem dynamics model

Random function model

Improverd neural networkalgorithm model

0

20

40

60

80

100

Cost

budg

et ac

cura

cy (

)

2 10 12 1464 80Time (month)

Figure 1 Result of comparative experiment on cost budgetperformance

6 Mathematical Problems in Engineering

projects in construction industryrdquo Expert Systems with Ap-plications vol 37 no 6 pp 4224ndash4231 2010

[4] K H Hyari A Al-Daraiseh and M El-Mashaleh ldquoCon-ceptual cost estimation model for engineering services inpublic construction projectsrdquo Journal of Management inEngineering vol 32 Article ID 04015021 2016

[5] B Pal A Mhashilkar A Pandey B Nagphase andV Chandanshive ldquoCost estimation model (CEM) of buildingsby ANN (artificial neural networks)ndashA reviewrdquo NeuralNetworks vol 5 pp 1ndash15 2018

[6] J Liu X Li D Wu and J Dong ldquoCost estimation of buildingindividual cooperative housing with crowdfunding modelcase of Beijing Chinardquo Journal of Intelligent Manufacturingvol 28 no 3 pp 749ndash757 2017

[7] H Piili A Happonen T Vaisto V VenkataramananJ Partanen and A Salminen ldquoCost estimation of laser ad-ditive manufacturing of stainless steelrdquo Physics Procediavol 78 pp 388ndash396 2015

[8] O Tatari and M Kucukvar ldquoCost premium prediction ofcertified green buildings a neural network approachrdquoBuilding and Environment vol 46 no 5 pp 1081ndash1086 2011

[9] S C Lhee I Flood and R R Issa ldquoDevelopment of a two-stepneural network-based model to predict construction costcontingencyrdquo Journal of Information Technology in Con-struction (ITcon) vol 19 pp 399ndash411 2014

[10] V Chandanshive and A R Kambekar ldquoEstimation ofbuilding construction cost using artificial neural networksrdquoJournal of Soft Computing in Civil Engineering vol 3pp 91ndash107 2019

[11] J A Rodger ldquoA fuzzy nearest neighbor neural networkstatistical model for predicting demand for natural gas andenergy cost savings in public buildingsrdquo Expert Systems withApplications vol 41 no 4 pp 1813ndash1829 2014

[12] G Ngowtanasuwan ldquoMathematical model for optimization ofconstruction contracting in housing development projectrdquoProcedia-Social and Behavioral Sciences vol 105 pp 94ndash1052013

[13] D-K Bui T Nguyen J-S Chou H Nguyen-Xuan andT D Ngo ldquoA modified firefly algorithm-artificial neuralnetwork expert system for predicting compressive and tensilestrength of high-performance concreterdquo Construction andBuilding Materials vol 180 pp 320ndash333 2018

[14] E Asadi M G d Silva C H Antunes L Dias andL Glicksman ldquoMulti-objective optimization for buildingretrofit a model using genetic algorithm and artificial neuralnetwork and an applicationrdquo Energy and Buildings vol 81pp 444ndash456 2014

[15] M Ceylan M H Arslan R Ceylan M Y Kaltakci andY Ozbay ldquoA new application area of ANN and ANFISdetermination of earthquake load reduction factor of pre-fabricated industrial buildingsrdquo Civil Engineering and Envi-ronmental Systems vol 27 no 1 pp 53ndash69 2010

[16] A Nasirian M Arashpour B Abbasi and A AkbarnezhadldquoOptimal work assignment to multiskilled resources in pre-fabricated constructionrdquo Journal of Construction Engineeringand Management vol 145 pp 4019ndash4034 2019

[17] H Quan D Srinivasan and A Khosravi ldquoParticle swarmoptimization for construction of neural network-based pre-diction intervalsrdquo Neurocomputing vol 127 pp 172ndash1802014

[18] H-L Yip H Fan and Y-H Chiang ldquoPredicting the main-tenance cost of construction equipment comparison betweengeneral regression neural network and Box-Jenkins time

series modelsrdquo Automation in Construction vol 38 pp 30ndash38 2014

[19] J Sobhani M Najimi A R Pourkhorshidi and T ParhizkarldquoPrediction of the compressive strength of no-slump concretea comparative study of regression neural network and ANFISmodelsrdquo Construction and Building Materials vol 24 no 5pp 709ndash718 2010

[20] R Sonmez ldquoRange estimation of construction costs usingneural networks with bootstrap prediction intervalsrdquo ExpertSystems with Applications vol 38 no 8 pp 9913ndash9917 2011

[21] A O Elfaki S Alatawi and E Abushandi ldquoUsing intelligenttechniques in construction project cost estimation 10-yearsurveyrdquo Advances in Civil Engineering vol 2014 pp 1023ndash1031 2014

Mathematical Problems in Engineering 7

of prefabricated buildings can be estimated by inputting theconstruction period and cost analysis results of early stage ofthe prefabricated construction project as well as the actualstatus of the early stage of project into the project man-agement software

24 Mathematical Model of Cost Budget in Early Stage ofPrefabricated Construction Project According to the esti-mated cost in the early stage of prefabricated constructionproject the mathematical model of cost budget in early stageof prefabricated construction project is constructed based onproject parameters e items of material budget in earlystage of prefabricated construction project are shown inTable 3

e project parameters are described according to thetype of project in which the parameter of productionprogress in the early stage of prefabricated constructionproject is set to rg the parameter of production calculationperiod is set to T the parameter of periodic component

production batch is set to N labor demand cost is set toL(P) machinery demand cost is set to L(c) other expensessuch as management fee are set to K demand machineryvalue is set to FL site cost is set to AC equipment rental costis set to F(c) the upper limit of transportation cost is set toP(c) and the assembly cost is set to Asum

e production process in early stage of prefabricatedconstruction project can be summarized as follows the firstif component production followed by component assemblyand transportation In this way the cost in early stage ofprefabricated construction project includes constructionproduction cost component assembly and transportationfee [19] erefore by setting parameters of productionprogress in early stage of prefabricated construction projectas independent variables and the minimum budget cost asthe model objective function then the mathematical modelof cost budge in the early stage of prefabricated constructionprojects is established as follows [20]

rg T

N

MinCost A(c) 1113946T

0L(p)dt + L(c) 1113946

T

0Adt + F(L) 1113946

T

0F(c)dt + K middot P(c) middot Asum

⎧⎪⎪⎪⎪⎪⎨

⎪⎪⎪⎪⎪⎩

(8)

In formula 8 MinCost represents the minimum costbudget in the early stage

3 Experimental Research and Result Analysis

31 Experiment Design e experiment of cost budget inearly stage of prefabricated construction project is carriedout by using the mathematical model of cost budget in earlystage of prefabricated construction project designed basedon improved neural network algorithm With a total area of920 square meters the prefabricated construction project inthis experiment contains 14 floors in prefabricated struc-tures of assembled shear wall e prefabricated componentnodes are manufactured by secondary cast-in-place eouter wall of the building is made of prefabricated thermalinsulation Sandwich panel the floor is made of concreteprestressed composite slab the load-bearing wall is made ofshear prefabricated wall panel the staircase is prefabricatedthe inner partition wall is made of lightweight wall panele prefabricated parts involved in this prefabricated con-struction project are listed as follows prefabricated parts forstair prefabricated parts for laminated panel prefabricatedparts for partition wall shear wall etc Considering that it isa prefabricated construction project all the prefabricatedparts are produced at the prefabricated production base andthen transported to the construction site after maintenanceMeanwhile the transportation and production of pre-fabricated parts for different places and floors are arrangedseparately according to the specific project progress

e specific building parameters of this prefabricatedbuilding project are shown in Table 6

In this prefabricated construction project all the floorsare standard and the early stage is set to a six-day con-struction period per floor According to the buildingstructure and engineering quantity the construction se-quence is arranged reasonably and the whole project isdivided into three phases e specific arrangements for theconstruction of each floor are as follows hoisting 60 pieces ofwall in the first construction phase hoisting 60 pieces of wallin the second construction phase grouting sleeve in the firstconstruction phase grouting sleeve in the second con-struction phase hoisting 30 pieces of wall in the thirdconstruction phase grouting sleeves in the third construc-tion phase binging steel bars with postcasting belts rein-forcing formwork with postcasting belts erecting supportiveframes hoisting composite beams hoisting stairs hoistingof 60 pieces of composite slabs hoisting 57 pieces ofcomposite slabs preburying hydropower and other pipe-lines binding the upper stair reinforcement supportingformwork joints and pouring concrete e cost budget inearly stage of this prefabricated building construction isestimated through the mathematical model In order toensure the effectiveness and contrast of this experiment theoriginal mathematical model of cost budget in the early stageof prefabricated construction project is compared to themathematical model of cost budget in the early stage ofprefabricated construction project designed based on theimproved neural network algorithm in this paper Among

4 Mathematical Problems in Engineering

Table 3 Items of material budget in early stage of prefabricated construction project

No Items of material budget Unit1 Prefabricated PC wall components Cubic meter2 Prefabricated PC floor (laminated) components Cubic meter3 Prefabricated PC stair components Cubic meter4 Prefabricated PC balcony components Cubic meter5 Prefabricated PC air conditioning panel components Cubic meter6 Prefabricated PC beam components Cubic meter7 Rebar B300HR(Dlt 25) Ton8 Screw-thread steel B225HR(Dlt 12) Ton9 Concrete C30 (premixed) Cubic meter10 Concrete C35 (premixed) Cubic meter11 Fine stone concrete C20 (premixed) Cubic meter12 Aerated light sand autoclaved block concrete Cubic meter13 Specialized component grouting Ton14 Remaining self-purchased materials (estimated value) mdashe items of labor cost budget in early stage of prefabricated construction project are shown in Table 4 [18]

Table 4 Items of labor cost budget in early stage of prefabricated construction project

No Items of labor cost Unit1 Manual cleaning of foundation pit Cubic meter2 Manual lashing of cast-in-place and steel bar making Ton3 Manual assembly and wooden template making Cubic meter4 Manual maintenance of cast-in-place and concrete pouring Cubic meter5 Manual installation of prefabricated PC components Cubic meter6 Tower crane driver surveyor and bell man Cubic meter7 Manual masonry Cubic meter8 Manual water resistance Cubic meter9 Manual fitment Cubic metere items of machinery budget in early stage of prefabricated construction project are shown in Table 5

Table 5 Items of machinery budget in early stage of prefabricated construction project

No Name Unit Type1 (Tower) crane Set ST50202 Car crane Set 26T3 Material hoist Set SES160

Table 6 Specific building parameters of this prefabricated building project

No Name of building parameters Specific parameters1 Height 40m2 Floors 143 Structure type Prefabricated structure of assembled shear wall

4 Specific floor height 36M at 1st floor28M from 2nd to 14th floor

5 Covered area 920m2

6 Seismic grade 40 magnitude7 Seismic intensity Scale 68 Specific flame resistance Level 29 Specific waterproof rating Level 2

11 Specific type of prefabricated part

Shear wallPartition wallComposite slab

Platforms ladder beams stairs12 Building nature Residence13 Plan view size 15times 4014 Waterproof condition (roofing) Composite SBS waterproof15 Production materials such as windows and doors High quality aluminum alloye specific contracting situation of this prefabricated construction project is shown in Table 7

Mathematical Problems in Engineering 5

them the original mathematical model of cost budget inearly stage of prefabricated construction project includes themathematical model of cost budget in early stage of pre-fabricated construction project based on cost control ran-dom function and system dynamics As learned fromcomparing the performance of different mathematicalmodels of cost budget in early stage of prefabricated con-struction project that is from analyzing the cost budgetaccuracy of the experimental model the higher the costbudget accuracy the more reasonable the cost budget resultof the prefabricated construction project and the better costbudget performance [21]

32 Analysis Results e result of comparative experimenton cost budget performance between the original mathe-matical model of cost budget in early stage of prefabricatedconstruction project and the mathematical model of costbudget in early stage of prefabricated construction projectdesigned based on the improved neural network algorithm isshown in Figure 1

According to the result of comparative experiment oncost budget performance between two different mathe-matical models the mathematical model of cost budget in

early stage of prefabricated construction project designedbased on the improved neural network algorithm is better incost budget accuracy at means the cost budget perfor-mance of the mathematical model of cost budget in earlystage of prefabricated construction project based on theimproved neural network algorithm is superior to that of theoriginal mathematical model of cost budget in early stage ofprefabricated construction project

4 Conclusions

e cost budget performance of the mathematical model ofcost budget in the early stage of prefabricated constructionproject based on the improved neural network algorithm canrealize the improvement of cost budget performance in theearly stage of prefabricated construction project which is ofgreat reference significance to accurate cost budget of theoverall prefabricated construction project

Data Availability

Simulation data and our model and related hyperparametersused are provided within the article

Conflicts of Interest

e authors declare that they have no conflicts of interest

Acknowledgments

is work was supported by the Chongqing MunicipalEducation Commission Science and Technology ResearchProject (KJQN201904003) and research project ofChongqing Technology and Business Institute (ZD2016-04)

References

[1] G E Gurcanli S Bilir and M Sevim ldquoActivity based riskassessment and safety cost estimation for residential buildingconstruction projectsrdquo Safety Science vol 80 pp 1ndash12 2015

[2] Y T Chae R Horesh Y Hwang and Y M Lee ldquoArtificialneural network model for forecasting sub-hourly electricityusage in commercial buildingsrdquo Energy and Buildingsvol 111 pp 184ndash194 2016

[3] M-Y Cheng H-C Tsai and E Sudjono ldquoConceptual costestimates using evolutionary fuzzy hybrid neural network for

Table 7 Specific contracting situation of this prefabricated construction project

No Items Specific situation1 Specific project name Project of Fuligang building 22 Construction company Haoqiang Real Estate co ltd3 Design contractor Yicai Architectural Design co ltd4 Supervision company Keli Supervision Construction co ltd5 Construction organization Risheng Engineering Cconstruction co ltd6 Quality supervision organization Yihe Engineering Quality Supervision co ltd7 Total project cost RMB 126 million8 Contracted form Contract for labor and material9 Contract scope Decoration main body foundation10 Planned schedule One year11 Overall quality goal Good in quality

Cost control modelSystem dynamics model

Random function model

Improverd neural networkalgorithm model

0

20

40

60

80

100

Cost

budg

et ac

cura

cy (

)

2 10 12 1464 80Time (month)

Figure 1 Result of comparative experiment on cost budgetperformance

6 Mathematical Problems in Engineering

projects in construction industryrdquo Expert Systems with Ap-plications vol 37 no 6 pp 4224ndash4231 2010

[4] K H Hyari A Al-Daraiseh and M El-Mashaleh ldquoCon-ceptual cost estimation model for engineering services inpublic construction projectsrdquo Journal of Management inEngineering vol 32 Article ID 04015021 2016

[5] B Pal A Mhashilkar A Pandey B Nagphase andV Chandanshive ldquoCost estimation model (CEM) of buildingsby ANN (artificial neural networks)ndashA reviewrdquo NeuralNetworks vol 5 pp 1ndash15 2018

[6] J Liu X Li D Wu and J Dong ldquoCost estimation of buildingindividual cooperative housing with crowdfunding modelcase of Beijing Chinardquo Journal of Intelligent Manufacturingvol 28 no 3 pp 749ndash757 2017

[7] H Piili A Happonen T Vaisto V VenkataramananJ Partanen and A Salminen ldquoCost estimation of laser ad-ditive manufacturing of stainless steelrdquo Physics Procediavol 78 pp 388ndash396 2015

[8] O Tatari and M Kucukvar ldquoCost premium prediction ofcertified green buildings a neural network approachrdquoBuilding and Environment vol 46 no 5 pp 1081ndash1086 2011

[9] S C Lhee I Flood and R R Issa ldquoDevelopment of a two-stepneural network-based model to predict construction costcontingencyrdquo Journal of Information Technology in Con-struction (ITcon) vol 19 pp 399ndash411 2014

[10] V Chandanshive and A R Kambekar ldquoEstimation ofbuilding construction cost using artificial neural networksrdquoJournal of Soft Computing in Civil Engineering vol 3pp 91ndash107 2019

[11] J A Rodger ldquoA fuzzy nearest neighbor neural networkstatistical model for predicting demand for natural gas andenergy cost savings in public buildingsrdquo Expert Systems withApplications vol 41 no 4 pp 1813ndash1829 2014

[12] G Ngowtanasuwan ldquoMathematical model for optimization ofconstruction contracting in housing development projectrdquoProcedia-Social and Behavioral Sciences vol 105 pp 94ndash1052013

[13] D-K Bui T Nguyen J-S Chou H Nguyen-Xuan andT D Ngo ldquoA modified firefly algorithm-artificial neuralnetwork expert system for predicting compressive and tensilestrength of high-performance concreterdquo Construction andBuilding Materials vol 180 pp 320ndash333 2018

[14] E Asadi M G d Silva C H Antunes L Dias andL Glicksman ldquoMulti-objective optimization for buildingretrofit a model using genetic algorithm and artificial neuralnetwork and an applicationrdquo Energy and Buildings vol 81pp 444ndash456 2014

[15] M Ceylan M H Arslan R Ceylan M Y Kaltakci andY Ozbay ldquoA new application area of ANN and ANFISdetermination of earthquake load reduction factor of pre-fabricated industrial buildingsrdquo Civil Engineering and Envi-ronmental Systems vol 27 no 1 pp 53ndash69 2010

[16] A Nasirian M Arashpour B Abbasi and A AkbarnezhadldquoOptimal work assignment to multiskilled resources in pre-fabricated constructionrdquo Journal of Construction Engineeringand Management vol 145 pp 4019ndash4034 2019

[17] H Quan D Srinivasan and A Khosravi ldquoParticle swarmoptimization for construction of neural network-based pre-diction intervalsrdquo Neurocomputing vol 127 pp 172ndash1802014

[18] H-L Yip H Fan and Y-H Chiang ldquoPredicting the main-tenance cost of construction equipment comparison betweengeneral regression neural network and Box-Jenkins time

series modelsrdquo Automation in Construction vol 38 pp 30ndash38 2014

[19] J Sobhani M Najimi A R Pourkhorshidi and T ParhizkarldquoPrediction of the compressive strength of no-slump concretea comparative study of regression neural network and ANFISmodelsrdquo Construction and Building Materials vol 24 no 5pp 709ndash718 2010

[20] R Sonmez ldquoRange estimation of construction costs usingneural networks with bootstrap prediction intervalsrdquo ExpertSystems with Applications vol 38 no 8 pp 9913ndash9917 2011

[21] A O Elfaki S Alatawi and E Abushandi ldquoUsing intelligenttechniques in construction project cost estimation 10-yearsurveyrdquo Advances in Civil Engineering vol 2014 pp 1023ndash1031 2014

Mathematical Problems in Engineering 7

Table 3 Items of material budget in early stage of prefabricated construction project

No Items of material budget Unit1 Prefabricated PC wall components Cubic meter2 Prefabricated PC floor (laminated) components Cubic meter3 Prefabricated PC stair components Cubic meter4 Prefabricated PC balcony components Cubic meter5 Prefabricated PC air conditioning panel components Cubic meter6 Prefabricated PC beam components Cubic meter7 Rebar B300HR(Dlt 25) Ton8 Screw-thread steel B225HR(Dlt 12) Ton9 Concrete C30 (premixed) Cubic meter10 Concrete C35 (premixed) Cubic meter11 Fine stone concrete C20 (premixed) Cubic meter12 Aerated light sand autoclaved block concrete Cubic meter13 Specialized component grouting Ton14 Remaining self-purchased materials (estimated value) mdashe items of labor cost budget in early stage of prefabricated construction project are shown in Table 4 [18]

Table 4 Items of labor cost budget in early stage of prefabricated construction project

No Items of labor cost Unit1 Manual cleaning of foundation pit Cubic meter2 Manual lashing of cast-in-place and steel bar making Ton3 Manual assembly and wooden template making Cubic meter4 Manual maintenance of cast-in-place and concrete pouring Cubic meter5 Manual installation of prefabricated PC components Cubic meter6 Tower crane driver surveyor and bell man Cubic meter7 Manual masonry Cubic meter8 Manual water resistance Cubic meter9 Manual fitment Cubic metere items of machinery budget in early stage of prefabricated construction project are shown in Table 5

Table 5 Items of machinery budget in early stage of prefabricated construction project

No Name Unit Type1 (Tower) crane Set ST50202 Car crane Set 26T3 Material hoist Set SES160

Table 6 Specific building parameters of this prefabricated building project

No Name of building parameters Specific parameters1 Height 40m2 Floors 143 Structure type Prefabricated structure of assembled shear wall

4 Specific floor height 36M at 1st floor28M from 2nd to 14th floor

5 Covered area 920m2

6 Seismic grade 40 magnitude7 Seismic intensity Scale 68 Specific flame resistance Level 29 Specific waterproof rating Level 2

11 Specific type of prefabricated part

Shear wallPartition wallComposite slab

Platforms ladder beams stairs12 Building nature Residence13 Plan view size 15times 4014 Waterproof condition (roofing) Composite SBS waterproof15 Production materials such as windows and doors High quality aluminum alloye specific contracting situation of this prefabricated construction project is shown in Table 7

Mathematical Problems in Engineering 5

them the original mathematical model of cost budget inearly stage of prefabricated construction project includes themathematical model of cost budget in early stage of pre-fabricated construction project based on cost control ran-dom function and system dynamics As learned fromcomparing the performance of different mathematicalmodels of cost budget in early stage of prefabricated con-struction project that is from analyzing the cost budgetaccuracy of the experimental model the higher the costbudget accuracy the more reasonable the cost budget resultof the prefabricated construction project and the better costbudget performance [21]

32 Analysis Results e result of comparative experimenton cost budget performance between the original mathe-matical model of cost budget in early stage of prefabricatedconstruction project and the mathematical model of costbudget in early stage of prefabricated construction projectdesigned based on the improved neural network algorithm isshown in Figure 1

According to the result of comparative experiment oncost budget performance between two different mathe-matical models the mathematical model of cost budget in

early stage of prefabricated construction project designedbased on the improved neural network algorithm is better incost budget accuracy at means the cost budget perfor-mance of the mathematical model of cost budget in earlystage of prefabricated construction project based on theimproved neural network algorithm is superior to that of theoriginal mathematical model of cost budget in early stage ofprefabricated construction project

4 Conclusions

e cost budget performance of the mathematical model ofcost budget in the early stage of prefabricated constructionproject based on the improved neural network algorithm canrealize the improvement of cost budget performance in theearly stage of prefabricated construction project which is ofgreat reference significance to accurate cost budget of theoverall prefabricated construction project

Data Availability

Simulation data and our model and related hyperparametersused are provided within the article

Conflicts of Interest

e authors declare that they have no conflicts of interest

Acknowledgments

is work was supported by the Chongqing MunicipalEducation Commission Science and Technology ResearchProject (KJQN201904003) and research project ofChongqing Technology and Business Institute (ZD2016-04)

References

[1] G E Gurcanli S Bilir and M Sevim ldquoActivity based riskassessment and safety cost estimation for residential buildingconstruction projectsrdquo Safety Science vol 80 pp 1ndash12 2015

[2] Y T Chae R Horesh Y Hwang and Y M Lee ldquoArtificialneural network model for forecasting sub-hourly electricityusage in commercial buildingsrdquo Energy and Buildingsvol 111 pp 184ndash194 2016

[3] M-Y Cheng H-C Tsai and E Sudjono ldquoConceptual costestimates using evolutionary fuzzy hybrid neural network for

Table 7 Specific contracting situation of this prefabricated construction project

No Items Specific situation1 Specific project name Project of Fuligang building 22 Construction company Haoqiang Real Estate co ltd3 Design contractor Yicai Architectural Design co ltd4 Supervision company Keli Supervision Construction co ltd5 Construction organization Risheng Engineering Cconstruction co ltd6 Quality supervision organization Yihe Engineering Quality Supervision co ltd7 Total project cost RMB 126 million8 Contracted form Contract for labor and material9 Contract scope Decoration main body foundation10 Planned schedule One year11 Overall quality goal Good in quality

Cost control modelSystem dynamics model

Random function model

Improverd neural networkalgorithm model

0

20

40

60

80

100

Cost

budg

et ac

cura

cy (

)

2 10 12 1464 80Time (month)

Figure 1 Result of comparative experiment on cost budgetperformance

6 Mathematical Problems in Engineering

projects in construction industryrdquo Expert Systems with Ap-plications vol 37 no 6 pp 4224ndash4231 2010

[4] K H Hyari A Al-Daraiseh and M El-Mashaleh ldquoCon-ceptual cost estimation model for engineering services inpublic construction projectsrdquo Journal of Management inEngineering vol 32 Article ID 04015021 2016

[5] B Pal A Mhashilkar A Pandey B Nagphase andV Chandanshive ldquoCost estimation model (CEM) of buildingsby ANN (artificial neural networks)ndashA reviewrdquo NeuralNetworks vol 5 pp 1ndash15 2018

[6] J Liu X Li D Wu and J Dong ldquoCost estimation of buildingindividual cooperative housing with crowdfunding modelcase of Beijing Chinardquo Journal of Intelligent Manufacturingvol 28 no 3 pp 749ndash757 2017

[7] H Piili A Happonen T Vaisto V VenkataramananJ Partanen and A Salminen ldquoCost estimation of laser ad-ditive manufacturing of stainless steelrdquo Physics Procediavol 78 pp 388ndash396 2015

[8] O Tatari and M Kucukvar ldquoCost premium prediction ofcertified green buildings a neural network approachrdquoBuilding and Environment vol 46 no 5 pp 1081ndash1086 2011

[9] S C Lhee I Flood and R R Issa ldquoDevelopment of a two-stepneural network-based model to predict construction costcontingencyrdquo Journal of Information Technology in Con-struction (ITcon) vol 19 pp 399ndash411 2014

[10] V Chandanshive and A R Kambekar ldquoEstimation ofbuilding construction cost using artificial neural networksrdquoJournal of Soft Computing in Civil Engineering vol 3pp 91ndash107 2019

[11] J A Rodger ldquoA fuzzy nearest neighbor neural networkstatistical model for predicting demand for natural gas andenergy cost savings in public buildingsrdquo Expert Systems withApplications vol 41 no 4 pp 1813ndash1829 2014

[12] G Ngowtanasuwan ldquoMathematical model for optimization ofconstruction contracting in housing development projectrdquoProcedia-Social and Behavioral Sciences vol 105 pp 94ndash1052013

[13] D-K Bui T Nguyen J-S Chou H Nguyen-Xuan andT D Ngo ldquoA modified firefly algorithm-artificial neuralnetwork expert system for predicting compressive and tensilestrength of high-performance concreterdquo Construction andBuilding Materials vol 180 pp 320ndash333 2018

[14] E Asadi M G d Silva C H Antunes L Dias andL Glicksman ldquoMulti-objective optimization for buildingretrofit a model using genetic algorithm and artificial neuralnetwork and an applicationrdquo Energy and Buildings vol 81pp 444ndash456 2014

[15] M Ceylan M H Arslan R Ceylan M Y Kaltakci andY Ozbay ldquoA new application area of ANN and ANFISdetermination of earthquake load reduction factor of pre-fabricated industrial buildingsrdquo Civil Engineering and Envi-ronmental Systems vol 27 no 1 pp 53ndash69 2010

[16] A Nasirian M Arashpour B Abbasi and A AkbarnezhadldquoOptimal work assignment to multiskilled resources in pre-fabricated constructionrdquo Journal of Construction Engineeringand Management vol 145 pp 4019ndash4034 2019

[17] H Quan D Srinivasan and A Khosravi ldquoParticle swarmoptimization for construction of neural network-based pre-diction intervalsrdquo Neurocomputing vol 127 pp 172ndash1802014

[18] H-L Yip H Fan and Y-H Chiang ldquoPredicting the main-tenance cost of construction equipment comparison betweengeneral regression neural network and Box-Jenkins time

series modelsrdquo Automation in Construction vol 38 pp 30ndash38 2014

[19] J Sobhani M Najimi A R Pourkhorshidi and T ParhizkarldquoPrediction of the compressive strength of no-slump concretea comparative study of regression neural network and ANFISmodelsrdquo Construction and Building Materials vol 24 no 5pp 709ndash718 2010

[20] R Sonmez ldquoRange estimation of construction costs usingneural networks with bootstrap prediction intervalsrdquo ExpertSystems with Applications vol 38 no 8 pp 9913ndash9917 2011

[21] A O Elfaki S Alatawi and E Abushandi ldquoUsing intelligenttechniques in construction project cost estimation 10-yearsurveyrdquo Advances in Civil Engineering vol 2014 pp 1023ndash1031 2014

Mathematical Problems in Engineering 7

them the original mathematical model of cost budget inearly stage of prefabricated construction project includes themathematical model of cost budget in early stage of pre-fabricated construction project based on cost control ran-dom function and system dynamics As learned fromcomparing the performance of different mathematicalmodels of cost budget in early stage of prefabricated con-struction project that is from analyzing the cost budgetaccuracy of the experimental model the higher the costbudget accuracy the more reasonable the cost budget resultof the prefabricated construction project and the better costbudget performance [21]

32 Analysis Results e result of comparative experimenton cost budget performance between the original mathe-matical model of cost budget in early stage of prefabricatedconstruction project and the mathematical model of costbudget in early stage of prefabricated construction projectdesigned based on the improved neural network algorithm isshown in Figure 1

According to the result of comparative experiment oncost budget performance between two different mathe-matical models the mathematical model of cost budget in

early stage of prefabricated construction project designedbased on the improved neural network algorithm is better incost budget accuracy at means the cost budget perfor-mance of the mathematical model of cost budget in earlystage of prefabricated construction project based on theimproved neural network algorithm is superior to that of theoriginal mathematical model of cost budget in early stage ofprefabricated construction project

4 Conclusions

e cost budget performance of the mathematical model ofcost budget in the early stage of prefabricated constructionproject based on the improved neural network algorithm canrealize the improvement of cost budget performance in theearly stage of prefabricated construction project which is ofgreat reference significance to accurate cost budget of theoverall prefabricated construction project

Data Availability

Simulation data and our model and related hyperparametersused are provided within the article

Conflicts of Interest

e authors declare that they have no conflicts of interest

Acknowledgments

is work was supported by the Chongqing MunicipalEducation Commission Science and Technology ResearchProject (KJQN201904003) and research project ofChongqing Technology and Business Institute (ZD2016-04)

References

[1] G E Gurcanli S Bilir and M Sevim ldquoActivity based riskassessment and safety cost estimation for residential buildingconstruction projectsrdquo Safety Science vol 80 pp 1ndash12 2015

[2] Y T Chae R Horesh Y Hwang and Y M Lee ldquoArtificialneural network model for forecasting sub-hourly electricityusage in commercial buildingsrdquo Energy and Buildingsvol 111 pp 184ndash194 2016

[3] M-Y Cheng H-C Tsai and E Sudjono ldquoConceptual costestimates using evolutionary fuzzy hybrid neural network for

Table 7 Specific contracting situation of this prefabricated construction project

No Items Specific situation1 Specific project name Project of Fuligang building 22 Construction company Haoqiang Real Estate co ltd3 Design contractor Yicai Architectural Design co ltd4 Supervision company Keli Supervision Construction co ltd5 Construction organization Risheng Engineering Cconstruction co ltd6 Quality supervision organization Yihe Engineering Quality Supervision co ltd7 Total project cost RMB 126 million8 Contracted form Contract for labor and material9 Contract scope Decoration main body foundation10 Planned schedule One year11 Overall quality goal Good in quality

Cost control modelSystem dynamics model

Random function model

Improverd neural networkalgorithm model

0

20

40

60

80

100

Cost

budg

et ac

cura

cy (

)

2 10 12 1464 80Time (month)

Figure 1 Result of comparative experiment on cost budgetperformance

6 Mathematical Problems in Engineering

projects in construction industryrdquo Expert Systems with Ap-plications vol 37 no 6 pp 4224ndash4231 2010

[4] K H Hyari A Al-Daraiseh and M El-Mashaleh ldquoCon-ceptual cost estimation model for engineering services inpublic construction projectsrdquo Journal of Management inEngineering vol 32 Article ID 04015021 2016

[5] B Pal A Mhashilkar A Pandey B Nagphase andV Chandanshive ldquoCost estimation model (CEM) of buildingsby ANN (artificial neural networks)ndashA reviewrdquo NeuralNetworks vol 5 pp 1ndash15 2018

[6] J Liu X Li D Wu and J Dong ldquoCost estimation of buildingindividual cooperative housing with crowdfunding modelcase of Beijing Chinardquo Journal of Intelligent Manufacturingvol 28 no 3 pp 749ndash757 2017

[7] H Piili A Happonen T Vaisto V VenkataramananJ Partanen and A Salminen ldquoCost estimation of laser ad-ditive manufacturing of stainless steelrdquo Physics Procediavol 78 pp 388ndash396 2015

[8] O Tatari and M Kucukvar ldquoCost premium prediction ofcertified green buildings a neural network approachrdquoBuilding and Environment vol 46 no 5 pp 1081ndash1086 2011

[9] S C Lhee I Flood and R R Issa ldquoDevelopment of a two-stepneural network-based model to predict construction costcontingencyrdquo Journal of Information Technology in Con-struction (ITcon) vol 19 pp 399ndash411 2014

[10] V Chandanshive and A R Kambekar ldquoEstimation ofbuilding construction cost using artificial neural networksrdquoJournal of Soft Computing in Civil Engineering vol 3pp 91ndash107 2019

[11] J A Rodger ldquoA fuzzy nearest neighbor neural networkstatistical model for predicting demand for natural gas andenergy cost savings in public buildingsrdquo Expert Systems withApplications vol 41 no 4 pp 1813ndash1829 2014

[12] G Ngowtanasuwan ldquoMathematical model for optimization ofconstruction contracting in housing development projectrdquoProcedia-Social and Behavioral Sciences vol 105 pp 94ndash1052013

[13] D-K Bui T Nguyen J-S Chou H Nguyen-Xuan andT D Ngo ldquoA modified firefly algorithm-artificial neuralnetwork expert system for predicting compressive and tensilestrength of high-performance concreterdquo Construction andBuilding Materials vol 180 pp 320ndash333 2018

[14] E Asadi M G d Silva C H Antunes L Dias andL Glicksman ldquoMulti-objective optimization for buildingretrofit a model using genetic algorithm and artificial neuralnetwork and an applicationrdquo Energy and Buildings vol 81pp 444ndash456 2014

[15] M Ceylan M H Arslan R Ceylan M Y Kaltakci andY Ozbay ldquoA new application area of ANN and ANFISdetermination of earthquake load reduction factor of pre-fabricated industrial buildingsrdquo Civil Engineering and Envi-ronmental Systems vol 27 no 1 pp 53ndash69 2010

[16] A Nasirian M Arashpour B Abbasi and A AkbarnezhadldquoOptimal work assignment to multiskilled resources in pre-fabricated constructionrdquo Journal of Construction Engineeringand Management vol 145 pp 4019ndash4034 2019

[17] H Quan D Srinivasan and A Khosravi ldquoParticle swarmoptimization for construction of neural network-based pre-diction intervalsrdquo Neurocomputing vol 127 pp 172ndash1802014

[18] H-L Yip H Fan and Y-H Chiang ldquoPredicting the main-tenance cost of construction equipment comparison betweengeneral regression neural network and Box-Jenkins time

series modelsrdquo Automation in Construction vol 38 pp 30ndash38 2014

[19] J Sobhani M Najimi A R Pourkhorshidi and T ParhizkarldquoPrediction of the compressive strength of no-slump concretea comparative study of regression neural network and ANFISmodelsrdquo Construction and Building Materials vol 24 no 5pp 709ndash718 2010

[20] R Sonmez ldquoRange estimation of construction costs usingneural networks with bootstrap prediction intervalsrdquo ExpertSystems with Applications vol 38 no 8 pp 9913ndash9917 2011

[21] A O Elfaki S Alatawi and E Abushandi ldquoUsing intelligenttechniques in construction project cost estimation 10-yearsurveyrdquo Advances in Civil Engineering vol 2014 pp 1023ndash1031 2014

Mathematical Problems in Engineering 7

projects in construction industryrdquo Expert Systems with Ap-plications vol 37 no 6 pp 4224ndash4231 2010

[4] K H Hyari A Al-Daraiseh and M El-Mashaleh ldquoCon-ceptual cost estimation model for engineering services inpublic construction projectsrdquo Journal of Management inEngineering vol 32 Article ID 04015021 2016

[5] B Pal A Mhashilkar A Pandey B Nagphase andV Chandanshive ldquoCost estimation model (CEM) of buildingsby ANN (artificial neural networks)ndashA reviewrdquo NeuralNetworks vol 5 pp 1ndash15 2018

[6] J Liu X Li D Wu and J Dong ldquoCost estimation of buildingindividual cooperative housing with crowdfunding modelcase of Beijing Chinardquo Journal of Intelligent Manufacturingvol 28 no 3 pp 749ndash757 2017

[7] H Piili A Happonen T Vaisto V VenkataramananJ Partanen and A Salminen ldquoCost estimation of laser ad-ditive manufacturing of stainless steelrdquo Physics Procediavol 78 pp 388ndash396 2015

[8] O Tatari and M Kucukvar ldquoCost premium prediction ofcertified green buildings a neural network approachrdquoBuilding and Environment vol 46 no 5 pp 1081ndash1086 2011

[9] S C Lhee I Flood and R R Issa ldquoDevelopment of a two-stepneural network-based model to predict construction costcontingencyrdquo Journal of Information Technology in Con-struction (ITcon) vol 19 pp 399ndash411 2014

[10] V Chandanshive and A R Kambekar ldquoEstimation ofbuilding construction cost using artificial neural networksrdquoJournal of Soft Computing in Civil Engineering vol 3pp 91ndash107 2019

[11] J A Rodger ldquoA fuzzy nearest neighbor neural networkstatistical model for predicting demand for natural gas andenergy cost savings in public buildingsrdquo Expert Systems withApplications vol 41 no 4 pp 1813ndash1829 2014

[12] G Ngowtanasuwan ldquoMathematical model for optimization ofconstruction contracting in housing development projectrdquoProcedia-Social and Behavioral Sciences vol 105 pp 94ndash1052013

[13] D-K Bui T Nguyen J-S Chou H Nguyen-Xuan andT D Ngo ldquoA modified firefly algorithm-artificial neuralnetwork expert system for predicting compressive and tensilestrength of high-performance concreterdquo Construction andBuilding Materials vol 180 pp 320ndash333 2018

[14] E Asadi M G d Silva C H Antunes L Dias andL Glicksman ldquoMulti-objective optimization for buildingretrofit a model using genetic algorithm and artificial neuralnetwork and an applicationrdquo Energy and Buildings vol 81pp 444ndash456 2014

[15] M Ceylan M H Arslan R Ceylan M Y Kaltakci andY Ozbay ldquoA new application area of ANN and ANFISdetermination of earthquake load reduction factor of pre-fabricated industrial buildingsrdquo Civil Engineering and Envi-ronmental Systems vol 27 no 1 pp 53ndash69 2010

[16] A Nasirian M Arashpour B Abbasi and A AkbarnezhadldquoOptimal work assignment to multiskilled resources in pre-fabricated constructionrdquo Journal of Construction Engineeringand Management vol 145 pp 4019ndash4034 2019

[17] H Quan D Srinivasan and A Khosravi ldquoParticle swarmoptimization for construction of neural network-based pre-diction intervalsrdquo Neurocomputing vol 127 pp 172ndash1802014

[18] H-L Yip H Fan and Y-H Chiang ldquoPredicting the main-tenance cost of construction equipment comparison betweengeneral regression neural network and Box-Jenkins time

series modelsrdquo Automation in Construction vol 38 pp 30ndash38 2014

[19] J Sobhani M Najimi A R Pourkhorshidi and T ParhizkarldquoPrediction of the compressive strength of no-slump concretea comparative study of regression neural network and ANFISmodelsrdquo Construction and Building Materials vol 24 no 5pp 709ndash718 2010

[20] R Sonmez ldquoRange estimation of construction costs usingneural networks with bootstrap prediction intervalsrdquo ExpertSystems with Applications vol 38 no 8 pp 9913ndash9917 2011

[21] A O Elfaki S Alatawi and E Abushandi ldquoUsing intelligenttechniques in construction project cost estimation 10-yearsurveyrdquo Advances in Civil Engineering vol 2014 pp 1023ndash1031 2014

Mathematical Problems in Engineering 7