1
Maintenance Prediction of Bridges using Entity Embedding Neural Networks Business process Subjective assessment by trained inspectors (can vary) Difficult to follow, justify and replicate past decisions Limited to no access to similar cases of the past Inspection to Maintenance Advice process of bridge management system Motivation Architecture Interpretability Results Conclusions References A standard three-layers feed-forward neural network was used for all the classification tasks. We utilise entity embedding layer to learn representations from categorical features. Weighted categorical cross-entropy was also applied to handle class imbalance problem. Typical inspection process of civil structures (bridges) To provide support in subjective assessment of bridges maintenance planning by developing predictive models using historical data Little attension towards improving subjective assessment process of inspection Predictive tasks and data representation Action Based on Advice Details of Inspected Components Inferring Damage Details Assessment of Damage Level Desk Study for Risk Assessment Condition State? Level of Risk? Analysis of Risk After Principal Inspection Subjective Judgement Service Level Agreements Qualitative Standards Quantitaive Standards Legend Maintenance Advice? Input Processing Decision Visual insights Principal inspection data collected from 2007 to 2017 Bridges asset register Inspection data Damages detais Risk details Feature engineering process was guided by experts Number of features were reduced from 69 to 23 only! Input Embedding Input Embedding Input Dense Input Dense Dense Dropout Dense Dropout Output Concatenate Categorical Features Numeric Features Input Embedding Input Embedding Input Dense Input Dense Output Concatenate Categorical Features Numeric Features Dense Dropout Dense Dropout Output Output Condition State Risk Level Maintenance Advice Shared Layers Dense Dropout Dense Dropout Dense Dropout Dense Dropout Condition state classification with SRS Risk level classification with SRS Maintenance advice classification with SRS Explanation of NN-EE (cw) model for all three predictive tasks Utilise data from in-use business process Aid decision-makers in maintenance related tasks classiifcation with 80% accuracy Provide interpretability of the results Multi-task learning for future similar tasks Generic modeling apporach Evolving data Data quality Black-box models Allah Bukhsh, Z., Stipanovic, I., Saeed, A., & Doree, A. G. Maintenance prediction of bridges using entity embedding neural networks.Under review in Automation in Construction Caruana, R. Multitask learning. Machine learning 1997, 28, 41–75 . Guo, C.; Berkhahn, F. Entity embeddings of categorical variables. arXiv preprint arXiv:1604.06737 2016 Ribeiro, M.T.; Singh, S.; Guestrin, C. Why should i trust you?: Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD 2016 Dataset Zaharah Allah Bukhsh [email protected] University of Twente Enschede, The Netherlands Irina Stipanovic [email protected] University of Twente Enschede, The Netherlands Aaqib Saaed [email protected] Eindhoven University of Techology, Eindhoven Andre G. Doree [email protected] University of Twente Enschede, Netherlands To leverage task-relatedness, we use multi- task learning to learn unified models for solving condition state, risk level, and maintenance advice prediction tasks. The hard-parameter sharing is used in the initial layers of the network, which are shared across all the tasks, whereas the final layers are problem specific. Architecture of Neural Network with Entity Embeddings Multi-task neural networks with entity embedding and two shared layers

Maintenance Prediction of Bridges using Entity Embedding ... · Irina Stipanovic [email protected] University of Twente Enschede, The Netherlands Aaqib Saaed [email protected]

  • Upload
    others

  • View
    3

  • Download
    0

Embed Size (px)

Citation preview

Page 1: Maintenance Prediction of Bridges using Entity Embedding ... · Irina Stipanovic i.stipanovic@utwente.nl University of Twente Enschede, The Netherlands Aaqib Saaed a.saeed@tue.nl

Maintenance Prediction of Bridges using Entity Embedding Neural Networks

Business process

Subjective assessment by trained inspectors (can vary)Difficult to follow, justify and replicate past decisionsLimited to no access to similar cases of the past

Inspection to Maintenance Advice process of bridge management system

Motivation Architecture

Interpretability

Results

Conclusions

References

A standard three-layers feed-forwardneural network was used for all the classification tasks. We utilise entityembedding layer to learn representationsfrom categorical features. Weighted categorical cross-entropy was also applied tohandle class imbalance problem.

Typical inspection process of civil structures (bridges)

To provide support in subjective assessmentof bridges maintenance planning by developing

predictive models using historical data

Little attension towards improving subjective assessment process of inspection

Predictive tasks and data representation

Action Basedon Advice

Details of Inspected Components

Inferring Damage Details

Assessment of Damage Level

Desk Study forRisk Assessment

Condition State?

Level of Risk?

Analysis of Risk

After Principal Inspection

SubjectiveJudgement

Service LevelAgreements

Qualitative Standards

Quantitaive Standards

Legend

MaintenanceAdvice?

Input Processing Decision

Visual insights

Principal inspection data collected from 2007 to 2017

Bridges asset register Inspection dataDamages detais Risk details

Feature engineering process was guided by expertsNumber of features were reduced from 69 to 23 only!

Input

Embedding

Input

Embedding

Input

Dense

Input

Dense

Dense

Dropout

Dense

Dropout

Output

Concatenate

Categorical FeaturesNumeric Features

Input

Embedding

Input

Embedding

Input

Dense

Input

Dense

Output

Concatenate

Categorical FeaturesNumeric Features

Dense

Dropout

Dense

Dropout

OutputOutput

Condition StateRisk LevelMaintenance Advice

Shared Layers

Dense

Dropout

Dense

Dropout

Dense

Dropout

Dense

Dropout

Condition state classification with SRS

Risk level classification with SRS

Maintenance advice classification with SRS

Explanation of NN-EE (cw) model for all three predictive tasks

Utilise data from in-use business process

Aid decision-makers in maintenance related tasks classiifcation with 80% accuracy

Provide interpretability of the resultsMulti-task learning for future similar tasksGeneric modeling apporachEvolving dataData quality Black-box models

Allah Bukhsh, Z., Stipanovic, I., Saeed, A., & Doree, A. G. Maintenance prediction of bridges using entity embedding neural networks.Under review in Automation in Construction

Caruana, R. Multitask learning. Machine learning 1997, 28, 41–75.Guo, C.; Berkhahn, F. Entity embeddings of categorical variables. arXiv preprint arXiv:1604.06737 2016

Ribeiro, M.T.; Singh, S.; Guestrin, C. Why should i trust you?: Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD 2016

Dataset

Zaharah Allah Bukhsh

[email protected]

University of TwenteEnschede, The Netherlands

Irina Stipanovic

[email protected]

University of TwenteEnschede, The Netherlands

Aaqib Saaed

[email protected]

Eindhoven University of Techology, Eindhoven

Andre G. Doree

[email protected]

University of TwenteEnschede, Netherlands

To leverage task-relatedness, we use multi-task learning to learn unified models for solving condition state, risk level, and maintenance advice prediction tasks. The hard-parameter sharing is used in the initial layers of the network, which are shared across all the tasks, whereas the final layers are problem specific.

Architecture of Neural Network with Entity Embeddings

Multi-task neural networks with entity embedding and two shared layers