www.ima-zlw-ifu.rwth-aachen.de
The Internet of Things in Production Technology:
Heterogeneous Agent Systems for Dezentralized Production Paradigms
6. Expertenforum „Agenten im Umfeld von Industrie 4.0“ Munich, Germany, May 07th, 2014
Univ.-Prof. Dr. rer. nat. Sabina Jeschke
IMA/ZLW & IfU Faculty of Mechanical Engineering RWTH Aachen University
2
07.05.2014
S. Jeschke
Outline
I. Cyber-Physical Systems alias the Internet of Things The term, its predecessors, its definition and its “relatives”...
… leading to the 4th industrial (r)evolution...
… towards a networked world
II. Heterogeneous Agents - Stabilization by Local Autonomy The rise of agent systems …
… its visions and views, …
… its scientific challenges
III. Towards an Autopoietic Production: 1. Decentralized production planning
2. Virtual Production Intelligence
3. Self-optimizing in socio-technical assembly systems
4. MAS in (Intra-)Logistics
3
07.05.2014
S. Jeschke
“When wireless is perfectly applied the whole earth will be converted into a huge brain, which in fact it is, […] and the instruments through which we shall be able to do this will be amazingly simple compared with our present telephone. A man will be able to carry one in his vest pocket.”
The term and its predecessors… Teleautomation…
1926 Nikola Tesla “Teleautomation”
Nikola Tesla, „Teleautomation“, USA
Wardenclyffe Tower (built for broadcast
energy experiments)
remote-controlled unmanned aerial vehicle (unmanned boat) by Tesla, 1898
4
07.05.2014
S. Jeschke
Google Trends (October 2012): Cyber-physical systems
“Cyber-physical systems are physical, biological, and engineered systems whose operations are integrated, monitored, and/or controlled by a computational core. Components are networked at every scale. Computing is deeply embedded into every physical component, possibly even into materials. The computational core is an embedded system, usually demands real-time response, and is most often distributed. ”
Helen Gill, NSF, USA
The term and its predecessors… … and other steps towards cyber-physical systems
1926 Nikola Tesla “Teleautomation”
1948 Norbert Wiener “Cybernetics”
1961 Charles Stark Draper “Apollo Guidance Computer” one of the first embedded systems
2006 Helen Gill “Cyber-physical systems”
1999 Kevin Ashton “Internet of Things”
1988 Mark Weiser “Ubiquitous computing”
5
07.05.2014
S. Jeschke
… its definition and its “relatives”... Internet of Things & Industry 4.0
Cyber-Physical Systems OR Internet of things ?
• large-scale distributed computing systems of systems
• computation and “intelligence” is not decoupled from environment
• internet as large-scale network • embedded systems
(= intelligent components)
Shared
Vision
Core Technology
• Internet of Things driven from computer sciences, Internet technologies driven by EC
• Cyber-Physical System driven from engineering aspects driven by the NSF
• Internet of Things focusing on openness and on the network - virtuality
• Cyber-Physical System focusing on the physical process behind, often a closed-loop system
Distinct
Scientific Community
Philosophy, focus
• Today: more or less synonym • Industry 4.0 as a special field of application For all practical purposes:
6
07.05.2014
S. Jeschke
… leading to the 4th industrial (r)evolution... The Drivers….
Power revolution Centralized electric power infrastructure; mass production by division of labor
1st industrial revolution Mechanical production systematically using the power of water and steam
today
Digital revolution Digital computing and communication technology, enhancing systems’ intelligence
Information revolution Everybody and everything is networked – networked information as a “huge brain”
Communication technology bandwidth and computational power
Embedded systems miniaturization
Semantic technologies information integration
around 1750 around 1900 around 1970
Towards intelligent and (partly-) autonomous systems AND systems of systems
Watson 2011
Google Car 2012
7
07.05.2014
S. Jeschke
… leading to the 4th industrial (r)evolution... Towards complex and networked social-technical systems
… let’s have a look Communication Consumer Energy Infrastructure Health Care Manufacturing Military Robotics Transportation
[CAR2CAR, 2011] and [ConnectSafe, 2011]
8
07.05.2014
S. Jeschke
… towards a networked world Not restricted to industry: cyber physical systems in all areas
Back to: The earth converted into a huge “brain”… (Tesla 1926) Integrating complex information from multiple heterogenous sources opens multiple possibilities of optimization: e.g. energy consumption, security services, rescue services as well as increasing the quality of life
… and more
Building automation
Smart grid
Room automation
Smart environment
Smart metering
9
07.05.2014
S. Jeschke
IOT CPS
… towards a networked world Two worlds coming together
Physical world
Internet Manufacturing process Material behavior Service-oriented
Things Semantics
Unique Identifier
Embedded Systems
Simulation Automation
Cyber-physical Digital world
“Closed” System controllable and partly predictable by simulation
“Open” System difficult to control or to predict system behavior
10
07.05.2014
S. Jeschke
IOT CPS
… towards a networked world Two worlds coming together
“Closed” System controllable and partly predictable by simulation
“Open” System difficult to control or to predict system behavior
! Timed communication and information exchange
! Well-known and controlled interaction between participants
! Time delayed communication
! Interaction between unknown participants
! “Dynamic” (continuously changing) ! “Static”
(changes are controlled)
Beyond traditional technical systems: Systems of distributed intelligence
VS
Change of perspective: from system to individual, from top-down to bottom-up
11
07.05.2014
S. Jeschke
Outline
I. Cyber-Physical Systems alias the Internet of Things The term, its predecessors, its definition and its “relatives”...
… leading to the 4th industrial (r)evolution...
… towards a networked world
II. Heterogeneous Agents - Stabilization by Local Autonomy The rise of Agent Systems …
… its visions and views, …
… its scientific challenges
III. Towards an Autopoietic Production: 1. Decentralized production planning
2. Virtual Production Intelligence
3. Self-optimizing in socio-technical assembly systems
4. MAS in (Intra-)Logistics
12
07.05.2014
S. Jeschke
The rise of agent systems … Its origins
B.F. Skinner (1953)
John B. Watson (1928)
Hadley Cantril (1940)
Charles Darwin (1838)
Peter Corning (1971)
Psychological and philosophical foundations
Classical behaviorism S-R model
Functionalism S-O-R model
Refle
xive
Co
nditi
oned
Classical conditioning US + NS = CS CR
Operant conditioning S-O-R-K-C model
Iwan Pawlow (1926)
H. Putnam (1960)
Social and biological foundation
Syst
em
theo
ry
com
mun
i-ca
tion
evol
utio
n
©The Daily Telegraph
med
ia
Shannon/Weaver (1949)
Inspired by social systems and biological models …
The idea of agent-based modeling was developed as a relatively simple concept in the late 1940s. Since it requires computation-intensive procedures, it did not become widespread until the 1990s.
13
07.05.2014
S. Jeschke
Division of labor
Macro-scale Automation
Micro-scale Multi-Core Ha
rdw
are
Soft
war
e
Service oriented
Agent- based
The rise of agent systems … Beyond traditional technical systems: organic computing
Specializations
Learning and reasoning
Adaptive behavior
Motivation
Multimodal communication modes
Touc
h
Faci
al
Emot
ion
Affective Computing ©Michael S. Ryoo, CalTech
©Fraunhofer IOSB
Spee
ch
©sciencedirect.com
Following social systems and biological models … ! Large heterogeneous systems = societies
14
07.05.2014
S. Jeschke
Evolution
The rise of agent systems … Beyond traditional technical systems: organic computing
… inspired by social systems and biological models …
SOFTWARE - Algorithms HARDWARE - Robotics
Genetic Algorithms
Neural networks [Gar3t, 2010] and [Robbins, 2010]
Awareness
Self-replication [Bongard, 2006; Lipson, 2007]
Zykov V., Mytilinaios E., Adams B., Lipson H. (2005) "Self-reproducing machines", Nature Vol. 435 No. 7038, pp. 163-164 Bongard J., et al., Resilient Machines Through Continuous Self-Modeling, Science 314, 2006 Lipson H. (2005) "Evolutionary Design and Evolutionary Robotics", Biomimetics, CRC Press (Bar Cohen, Ed.) pp. 129-155
15
07.05.2014
S. Jeschke
… its visions and views … Conservative system design
[Sztipanovits, Vanderbilt, 1997]
Use of domain-specific modeling languages
Models are computer-readable
Check of correctness against pre-specified design rules
! Requires deep understanding of system‘s behavior
! Modeling of complex systems often: time consuming, difficult
Top-Down: Model-Integrated Computing
Janos Sztipanovits E. Bronson Ingram Chair in Engineering Professor of Electrical and Computer Engineering Director of the Institute for Software Integrated Systems
Vanderbilt University
16
07.05.2014
S. Jeschke
… its visions and views An agent based approach of system design
[Lin, 2010 (on CPS)]
Bottom-up: Agent-based modeling
Dynamically interacting rule-based agents
Model using autonomous agents
Open Agent Based Modeling Consortium (www.openabm.org) Swarm Development Group (www.swarm.org) More information www.agent-based-models.com
! Established method to simulate large distributed systems
! Good at predicting appearance of complex phenomena
! Good at modeling of dynamically changing participants
17
07.05.2014
S. Jeschke
… its visions and views Visions towards multi agent systems
A key air-traffic control system at the main airport of Ruritania suddenly fails, leaving flights in the vicinity of the airport with no air-traffic control support. Fortunately, autonomous air-traffic control systems in nearby air-ports recognize the failure of their peer, and cooperate to track and deal with all affected flights. [Wooldridge 199%2009]
… ideas how things might be …
“By mid-21st century, a team of fully autonomous humanoid robot soccer players shall win the soccer game, comply with the official rule of the FIFA, against the winner of the most recent World Cup. ….” [Kitano/Assada 2000]
Interplanetary space flights …: “[The control system] must be capable of reacting autonomously … Goals may be implanted in the [system] prior to flight, but rigid seeking of those goals may result in total mission failure; those implanted goals may have to be expanded, contracted, or superseded in the light of unanticipated circumstances.” [Bond 1978]
18
07.05.2014
S. Jeschke
MAS: integrating a variety of heterogeneous fields
… its visions and views MAS: “distributed diversity” in all perspectives
Self-interested computation
Ubiquitous Computing
Autonomic computing
The semantic Web
Distributed Artificial Intelligence
Cyber-Physical Systems
Internet of Things
Concurrent systems
Game Theory
“Diversity”: Heterogeneous Agents for complex systems
John Ashbys Law of “requisite variety”: complex system demand for bottom-up-design with autonomous units
Bottom-up design hopes for an emergent interplay among its autonomous units
Heterogenous agents: interdisciplinarity promotes emergent potential by the ability to be different
19
07.05.2014
S. Jeschke
… its scientific challenges The agent in its society
How to build agents that are capable of autonomous action in order to successfully carry out the tasks that we delegate to them?
microscopic agent design
Proactiveness Generation of goal-directed behavior and attempts to achieve goals.
Agent communication Ability to communicate agent plans and world information and to provide coordination services.
Coordination Dynamic election of coordinator/ mediator to assign tasks/ moderate negotiation processes
MAS Group
Mediator
Human Machine Interaction
Transparency Transparent decision making, predictability (“traceability”) , creating confidence.
Cooperation Task decomposition and goal-directed interaction as a team to achieve a shared goal.
Service Provider Awareness of abilities which are provided to a central planning or coordinating unit.
Negotiation Reaching agreements on matters of common interest. Involves offer and counter-offer.
Intentional systems Behaviors show the intention of agents for a smooth human machine cooperation.
Matching of local optimization goals of agent and global optimization goals. Altruistic vs. egoistic behavior.
macroscopic society design
20
07.05.2014
S. Jeschke
Outline
I. Cyber-Physical Systems alias the Internet of Things The term, its predecessors, its definition and its “relatives”...
… leading to the 4th industrial (r)evolution...
… towards a networked world
II. Heterogeneous Agents - Stabilization by Local Autonomy The rise of Agent Systems …
… its Visions and Views, …
… its scientific challenges
III. Towards an Autopoietic Production: 1. Decentralized production planning
2. Virtual Production Intelligence
3. Self-optimizing in socio-technical assembly systems
4. MAS in (Intra-)Logistics
21
07.05.2014
S. Jeschke
How it all began...: the early ones Electronically coupled vehicle convoys
The KONVOI project (RWTH & partners)
automated / partly autonomous transportation e.g. by electronically coupling trucks to convoys
several successful tests have been conducted with trucks (KONVOI, SARTRE (EU), Energy-ITS (Japan))
expected improvements: reduction of fuel consumption; improved vehicle occupancy; gained road space; optimization of traffic flow; relief for professional drivers; increase in safety
!
advanced driver assistance system for trucks
short distances between vehicles of approx. 10m at a velocity of 80 km/h
Energy-ITS: 4m ! (2013)
22
07.05.2014
S. Jeschke
And how it went on…: Integrative Production Technology for High-Wage Countries
DFG Excellence Cluster (and DFG GradKolleg “RampUp”) IMA/ZLW & IfU in 1. Decentralized production planning 2. Self-optimizing socio-technical
assembly systems 3. Virtual Production Intelligence 4. MAS in (Intra-)Logistics
Speaker: Christian Brecher
23
07.05.2014
S. Jeschke
Decentralized production planning 1) Agent models for decentralized production planning…
Organization forms on demand – individualized by client - initialized by product
transport unit
production unit
virtual service provider
! Plans production steps and transportation steps Requests service from agents Negotiates with other products for agent-resources
Product agitates as super-agent Autopoiesis model & embodiment theory
fabr
icat
ion
outs
ide
wor
ld
24
07.05.2014
S. Jeschke
Decentralized production planning 1) Leading to “products acting as a super-agent”
transport unit
production unit
virtual service provider
production unit
provides services realizes product
features adds parts
communicates state
transportation unit
• specialized production unit
• often realized as mobile robot
virtual service provider
Provides Central Services knowledge base booking/accounting logging & monitoring re-scheduling
product
knows own goal configuration: desired parts desired
features requests
services from production units
negotiates with other products for resources
25
07.05.2014
S. Jeschke
Decentralized production planning 1) Everything is an agent, but: Who is in charge?
No central decision-making entity: Product manages its own creation
functionality emerges by interaction of independently agitating subsystems
Rivaling entities: Only local perspective, resource conflicts must be resolved by negotiation
Errors and perturbations can be handled locally
Central Control: Hierarchical agents
Central broker manages sub agents, coordinates interactions, plans main work flows
Omniscient entity: No resource conflicts, globally optimal solutions
Central control is error prone: Failure affects whole production, all changes in subsystems must be dealt with
centralization decentralization
transparency, optimality flexibility, fault tolerance
mar
kedn
ess
26
07.05.2014
S. Jeschke
Decentralized production planning 1) Flexible production chaining - “Factories of the Future”
Network of production entities forming an ad-hoc just-in-time process synthesis
flexible production stations
Symmetrical approach: everything/body is an agent!
27
07.05.2014
S. Jeschke
Application-layer
Simulation A Simulation C Simulation B
Integration-layer
Integration- server
Database- server
Service- provider
Middleware
Service- provider
Integration Bus
Analysis-layer Presentation-layer
Data-integration
Data-exploration • Data-similarity • User-centered Pattern-recognition
Data Mining • Classification • Clustering
Data-extraction Data-exploration • Interaction • User adaptive
Dashboard • Cockpit / Scoreboard • Solution analysis • Failure analysis
Visualization • CAVE • Immersion
Visualization
Data-analysis
Process-supervision
Coupling
Analysis
Cybernetics in production technology 2) Virtual Production Intelligence (VPI)
28
07.05.2014
S. Jeschke
Grand Unified Theory (GUT) for CPS
Cybernetics in production technology 2) Facing heterogeneity: towards a universal language
“GUT… is about developing a modeling language and conceptual framework into which heterogeneous modeling languages and frameworks can be translated.” [www.icyphy.org, 2013]
Global Ontology
Concrete data of arbitarily domain
Semantic annotation
Translation
A “top-down approach”
! Introduction of Semantic Web standards by Tim-Berners Lee, about 2005
! W3C (World Wide Web Consortium) standards provide web-scale semantic data exchange and federation
First steps towards “semantic interoperability”
www.icyphy.org
29
07.05.2014
S. Jeschke
Cybernetics in production technology 2) Facing heterogeneity: … or the universal translator
A “bottom-up approach” “Computational linguistics is an interdisciplinary field dealing with the statistical or rule-based modeling of natural language from a computational perspective.” [Wikipedia, 2013]
Computational Linguistics (CL) – NPL (Natural Language Processing)
! Today: CL as a subfield of AI
! Until shortly: interesting results but mostly restricted to specific subfields and restricted scenarios
Development of CL /NLP
! Lately: several “breakthroughs” in more comprehensive application areas
http://withfriendship.com
30
07.05.2014
S. Jeschke
Cybernetics in production technology 2) Facing heterogeneity: … or something-in-between
Abstract domain semantics for translation
Domain Ontology
Concrete data (product design)
Semantic annotation
Concrete data (resource planning) Transformation
Interface Ontology
Translation
Domain Ontology
“Abstract semantics … is about developing interfaces between heterogeneous modeling languages that are sufficient for interoperation…” [www.icyphy.org, 2013]
Semantic annotation
Our approach: The “something-in-between approach”
! Besides others: S. Jeschke, D. Schilberg, T. Meisen, RWTH Aachen
31
07.05.2014
S. Jeschke
human safety Objects are scanned by various sensors and fused into 3D point-cloud
Socio-technical assembly systems 3) Human machine interaction and cooperative robotics
Robots are no longer locked in work-cells but cooperate with eachother and/or with humans
past scenario: fenced working cell
hybrid planning integrates several robots and/or human and robot in assembly task („assembly by disassembly“), splitted into „online-offline“ for real-time capabilities
hybrid teams Elected leader starts assembly and delegates jobs
HM communication Human is informed about assembly job by virtual reality
32
07.05.2014
S. Jeschke
Socio-technical assembly systems 3) Human machine interaction and cooperative robotics
Robots are no longer locked in work-cells but cooperate with each other and/or with humans
hybrid teams Elected leader starts assembly and delegates jobs
Human-Machine Interaction in the X-Cell
Machine-Machine Cooperation
33
07.05.2014
S. Jeschke
Socio-technical assembly systems 3) Human machine interaction and cooperative robotics
Robots are no longer locked in work-cells but cooperate with each other and/or with humans
Direct interaction – object transfer
Working against visual occlusions of the object resulting from the robot body / the hands of the human Evaluating possible grasping points Offering good grasping options for the human co-worker
34
07.05.2014
S. Jeschke
MAS in (Intra-)Logistics 4) Adaptive logistics: autonomous transportation vehicles
!
Competencies: localization & navigation computer vision adaptive planning multi agent strategies sensory & hardware
Mission: Team of mobile robots autonomously plans and realizes intralogistic tasks within a dynamic production scenario
Mobile transportation robots enable flexible routing “A new trend in automation is to deploy so-called cyber-physical systems (CPS) which combine computation with physical processes. The novel RoboCup Logistics League Sponsored by Festo (LLSF) aims at a such CPS logistic scenarios in an automation setting. A team of robots has to produce products from a number of semi-finished products …” [Niemueller et.al. 2013]
Mixed teams (mech./electrical engineering and informatics) of Master and PhD students
Goal: „Logistics League“ – Industry scenario of cooperative robotics
35
07.05.2014
S. Jeschke
MAS in (Intra-)Logistics 4) Adaptive logistics: The Carologistics agent
Deliberative-layer: Rule-based expert-system
!
Incremental task-level reasoning approach
Deterministic and thus transparent behavior
Reproducible by replay of recorded facts
Reactive-layer: Lua based behavior engine (roslua)
! Simple and known language Deterministic and thus
transparent behavior
Low level: Fawkes and ROS
CLIPS Agent Deliberative layer
(defrule s0-t23-s1 (state IDLE) (holding S0) ?g <- (goto (machines $?ms& ̃:(contains$ ?n ?ms )) (min-prio ?mp&:(<= ?mp (m-prio ?mt)))) => (modify ?g (machines (merge ?mp (m-prio ?mt) ?ms ?n)) (min-prio (m-prio ?mt))) )
Behavior Engine Reactive Behaviors
Components
A classical three-layered system architecture based on open source technology enables fast growing systems by crowd development
AI: Practical reasoning approach and role coordination among agents
Robotics: Model-building and use of established algorithms / SW libs
36
07.05.2014
S. Jeschke
MAS in (Intra-)Logistics 4) Next steps: Rio … we are coming!
Competitions
2012: 0 points in World Cup 2013: 4th in World Cup 2014: Winner of the GermanOpen
Critical factors for success: Totally decentralized No „brute force components“ Strong cooperation Re-planning during tasks
! Next Step - July 2014:
RoboCup - international Competition: Joáo Pessoa – Brasil 2014
! http://www.carologistics.org/
37
07.05.2014
S. Jeschke
Thank you!
Univ.-Prof. Dr. rer. nat. Sabina Jeschke Head of Institute Cluster IMA/ZLW & IfU phone: +49 241-80-91110 [email protected]
Co-authored by: Dipl.-Wirt.-Ing. Sebastian Reuter Institute Cluster IMA/ZLW & IfU phone: +49 241 / 80 91143 [email protected] Dr.-Ing. Tobias Meisen Institute Cluster IMA/ZLW & IfU phone: +49 241 / 80 91139 [email protected]
www.ima-zlw-ifu.rwth-aachen.de
38
07.05.2014
S. Jeschke
1968 Born in Kungälv/Schweden
1991 Birth of Son Björn-Marcel 1991 – 1997 Studies of Physics, Mathematics, Computer Sciences, TU Berlin 1994 NASA Ames Research Center, Moffett Field, CA/USA 10/1994 Fellowship „Studienstiftung des Deutschen Volkes“ 1997 Diploma Physics
1997 – 2000 Research Fellow , TU Berlin, Institute for Mathematics 2000 – 2001 Lecturer, Georgia Institute of Technology, GA/USA 2001 – 2004 Project leadership, TU Berlin, Institute for Mathematics 04/2004 Ph.D. (Dr. rer. nat.), TU Berlin, in the field of Computer Sciences from 2004 Set-up and leadership of the Multimedia-Center at the TU Berlin
2005 – 2007 Juniorprofessor „New Media in Mathematics & Sciences“ & Director of the Media-center MuLF, TU Berlin
2007 – 2009 Univ.-Professor, Institute for IT Service Technologies (IITS) & Director of the Computer Center (RUS), Department of Electrical Engineering, University of Stuttgart
since 06/2009 Univ.-Professor, Institute for Information Management in Mechanical Engineering (IMA) & Center for Learning and Knowledge Management (ZLW) & Institute for Management Cybernetics (IfU), RWTH Aachen University
since 10/2011 Vice dean of the department of Mechanical Engineering, RWTH Aachen University
since 03/2012 Chairwoman VDI Aachen
Prof. Dr. rer. nat. Sabina Jeschke
39
07.05.2014
S. Jeschke
Literature [Shannon/Weaver 1949] – Shannon, C. E., & Weaver, W. (1949). The mathematical theory of communication. Urbana, Illinois: University of Illinois Press [Bond 1978] - Bond, A.: Project Daedalus: Final Report of the BIS Starship Study; Journal of the British Interplanetary Society (JBIS)Interstellar Studies; 1978. [Graves 1999] - Stephen C. Graves: Manufacturing Planning and Control; Massachusetts Institute of Technology (1999) [Mintzberg 1993] – Mintzberg, H.: Structure in fives: designing effective organizations; Prentice-Hall, 1983 - 312 Seiten [van Aart, 2000] – van Aart, C.: Organizational Principles for Multi-Agent Architectures; Birkhäuser Verlag, 2000 [Kitano,Assada 2000] – H. Kitano and M. Asada, “The RoboCup humanoid challenge as the millennium challenge for advanced robotics,” Adv. Robot., vol. 13, no. 8, pp. 723-737, 2000 [Wooldridge 2009] –M. J. Wooldridge: An Introduction to Multi Agent Systems (2. ed.). Wiley 2009 [Russel/Norvig 1995] – Russel, S, Norvig, P. : Artificial Intelligence: A modern approach; Prentice Hall (1995) [Weber 1994] – Weber, H.: Die Evolution von Produktionsparadigmen: Craft Production, Mass Production, Lean Production; Discussion papers at Universität Kaiserslautern - Fachgebiet Soziologie; FG Soziologie, Univ., 1994 [Maturana 1980] Maturana, H.R.: Autopoiesis and cognition: The realization of the living. No. 42. Springer, 1980. p. 80 [Maturana 1987] Maturana, H.R. : Everything is said by an observer; Gaia, a Way of Knowing, edited by W. Thompson, Lindisfarne Press, 1987, p. 71 [Probst 1987] Probst, G.J.B.: Selbstorganisation - Ordnungsprozesse in sozialen Systemen aus ganzheitlicher Sicht; Verlag Paul Parey, 1987 [Ewert, 2014] Ewert, D.: Adaptive Ablaufplanung für die Fertigung in der Factory of the Future; VDI Verlag GmbH, 2014 [Hartmann, 2002] Hartmann, E.: Arbeitssysteme und Arbeitsprozesse; Habilitation at RWTH Aachen; 2002
40
07.05.2014
S. Jeschke
Cybernetics in production technology Gaining Trust: “Zoom-in” by explorative information analysis
Virtual Production Intelligence Platform
summarizing view and information-distribution
Simulation Metal coating
Simulation Cutting the foils
Simulation winding
Simulation impregnation
factory layer
machine layer
material layer
Analysis
Assistance system for planning and decision support by integrative and explorative analysis
Integrated Views
! comprehensive consideration of “material, machine and factory”
Casual relationships
! online consolidation of “real-data” to gain knowledge about casual connections
Exploration
! user adaptive visualization for explorative data analysis
Vertical coupling of production layers
41
07.05.2014
S. Jeschke
The CloudLogistic Project (RWTH & partners)
› Using geographical information of origin and destination combined with a time-based approach to calculate needed distances
› Using heuristical approaches (e. g. genetic solvers) to handle the implied Constraint Satisfaction Problems (CSP)
› Using data mining techniques to improve the networks structure in a cybernetic way
…
› Innovative line-based logistics concept: combining Less Than Truckload (LTL) shipments of cooperating Logistic Service Provider (LSP)
› Pickups along the baseline realize direct transportation with no need for a centralized HUB-structure
Examples from the institute cluster … e.g., by increasing the efficiency of SME freight cooperation, …
42
07.05.2014
S. Jeschke
… its definition and its “relatives”... Cyber-physical systems
Cyber-physical systems OR Internet of things ? “The frontier between CPS and Internet-of-Things has not been clearly identified since both concepts have been driven in parallel from two independent communities, although they have always been closely related.” [Koubâa, 2009]
A quick glance into the web: “Cyber Physical System is the US version
of the ’internet of things’”
“The term ‘Internet of Things’, originally aiming at RFID technologies, is smoothly becoming synonymous for cyber-physical systems.”
Vision: Internet of Things, Data and Services e.g. Smart City
Vision: Cyber physical systems e.g. intelligent networked road junction
“Internet of Things & Services, M2M or cyber physical systems are much more than just buzzwords for the outlook of connecting 50 billions devices by 2015.”
43
07.05.2014
S. Jeschke
… leading to the 4th industrial (r)evolution... Industry 4.0 - Everybody and everything is networked
today
Information revolution Everybody and everything is networked – networked information as a “huge brain”
1st industrial revolution Mechanical production systematically using the power of water and steam
around 1750
Power revolution Centralized electric power infrastructure; mass production by division of labor
around 1900
Digital revolution Digital computing and communication technology, enhancing systems’ intelligence
around 1970
„local“ to „global“
„local“ to „global“
Weidmüller, Vission 2020 - Industrial Revolution 4.0 Intelligently networked, self-controlling manufacturing systems)
“The first three industrial revolutions came about as a result of mechanisation, electricity and IT. The introduction of the Internet of Things is ushering in a fourth industrial revolution. … Industry 4.0 will address and solve some of the challenges facing the world today such as resource and energy efficiency, urban production and demographic change. ” Henning Kagermann et.al., acatech, 2013
Vision of Wireless Next Generation System (WiNGS) Lab at the University of Texas at San Antonio, Dr. Kelley
44
07.05.2014
S. Jeschke
The crux of the matter Big Data induce “Intelligence”: From Big Data to Smart Data…
Acquistion/ Recording
Extraction/ Cleaning/
Annotation
Integration/ Aggregation/
Representation
Analysis/ Modeling Interpretation
The Big Data analysis pipeline…
! … transfers big data (many…) into smart data (meaningful data)
+
! … accumulates intelligence from information fragments
! … is a pipeline of aggregating (artificial) intelligence.
45
07.05.2014
S. Jeschke
DS
The way so far and beyond Two Worlds coming together
Distributed Systems
Big data - Volume
Distributed storage
Distributed Artificial Intelligence
DISTRIBUTED
Distributed computing
Distributed sources
Velocity
AI SMART
Artificial Intelligence
Smart data
Variety
Social media data
Natural language analysis
Real-time capability
Autonomy
Prediction
Veracity
46
07.05.2014
S. Jeschke
Challenge ‘Scale’ Data-parallel models - Fynn classification of distributed systems
Single Instruction Multiple Instruction
Single Data
Multiple Data
SISD
SIMD
MISD
MIMD
Do all CPUs have their one storage, or are they sharing it?
Do the CPUs apply the same instruction on all data oder different ones?
„regular“ desktop computer (one single CPU; not a distributed system!)
This is all about parallelization and distributed computation…
47
07.05.2014
S. Jeschke
Challenge ‘Scale’ MapReduce - first major data-processing paradigm
Doc 1 word1 word2 word2 word3
Doc 2 word2 word2 word1 word3
Input
Parallel handling of several documents
(word1, 2)
(word2, 4)
(word3, 2)
Reduce
Reduce
Reduce
Reduce Result
Summarizing all findings (by words)
Map
Map
(word1, 1) (word2, 1) (word2, 1) (word3, 1)
(word2, 1) (word2, 1) (word1, 1) (word3, 1)
Map
Word recognition
(word1, (1,1))
(word2, (1,1,1,1))
(word3, (1,1))
Summarize, Group, Share
Re-arrangement of results by words (before: by documents)
Result: word frequency of different words in the collection of documents
Example Extreme high degree of parallelization possible