Hoffmann Smart Agents for the Industry 4.0

Enabling Machine Learning in Industrial Production
1. Auflage 2019
ISBN: 978-3-658-27742-0
Verlag: Springer
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 345 Seiten

Max Hoffmann describes the realization of a framework that enables autonomous decision-making in industrial manufacturing processes by means of multi-agent systems and the OPC UA meta-modeling standard. The integration of communication patterns and SOA with grown manufacturing systems enables an upgrade of legacy environments in terms of Industry 4.0 related technologies. The added value of the derived solutions are validated through an industrial use case and verified by the development of a demonstrator that includes elements of self-optimization through Machine Learning and communication with high-level planning systems such as ERP.About the Author: Dr.-Ing. Max Hoffmann is a scientific researcher at the Institute of Information Management in Mechanical Engineering, RWTH Aachen University, Germany, and leads the group 'Industrial Big Data'. His research emphasizes on production optimization by means of data integration through interoperability and communication standards for industrial manufacturing and integrated analysis by using Machine Learning and stream-based information processing.

Dr.-Ing. Max Hoffmann is a scientific researcher at the Institute of Information Management in Mechanical Engineering, RWTH Aachen University, Germany, and leads the group 'Industrial Big Data'. His research emphasizes on production optimization by means of data integration through interoperability and communication standards for industrial manufacturing and integrated analysis by using Machine Learning and stream-based information processing.

Autoren/Hrsg.

Hoffmann, Max

Inhaltsverzeichnis

1;Foreword from Academia;5
2;Acknowledgement;7
3;Contents;9
4;List of Figures;15
5;List of Tables;19
6;Abbreviations;20
7;Glossary;27
8;Abstract;29
9;Zusammenfassung;31
10;1 Introduction;33
10.1;1.1 Motivation;33
10.1.1;1.1.1 Changing Reality – A Global Perspective;34
10.1.2;1.1.2 Trends and Visions of Modern Production;35
10.1.3;1.1.3 Digitalization and the Introduction of Cyber-Physical Systems;36
10.1.4;1.1.4 Challenges of the Digitalization and the Industrial (R)evolution;38
10.2;1.2 Research Goals;40
10.3;1.3 Structure of the Work;44
11;2 Problem Description and Fundamental Concepts;47
11.1;2.1 Strategical decision-making in a factory of the future;47
11.2;2.2 Fundamental Concepts of Industrial Manufacturing;54
11.3;2.3 Emerged Manufacturing Systems in Industrial Production;56
11.3.1;2.3.1 Static Control Systems in Current Factories;56
11.3.2;2.3.2 The Automation Pyramid and Hierarchical Production Organization;57
11.3.3;2.3.3 Tight Coupling in terms of Conventional Automation Infrastructures;62
11.4;2.4 The Duality of Loosely and Tightly-Coupled Systems;63
12;3 State of the Art;65
12.1;3.1 Global Strategies towards Future Manufacturing;67
12.1.1;3.1.1 Reference Architectures for an Industry 4.0;67
12.1.2;3.1.2 Important Research Programs targeting the Global Challenges;67
12.2;3.2 Current Approaches for Production Optimization;69
12.2.1;3.2.1 Organizational Optimization of the Production Process;69
12.2.2;3.2.2 Long-term Optimization of Production Goals using Low-Level Data;72
12.2.3;3.2.3 Autonomous Optimization Strategies in terms of Self-Optimization;73
12.3;3.3 Interoperability Approaches for Manufacturing Systems;74
12.4;3.4 Technical Solutions for Automated Production Control;77
12.4.1;3.4.1 Fieldbus Protocols;78
12.4.2;3.4.2 Industrial Ethernet;79
12.4.3;3.4.3 Publish-Subscribe within Industrial Applications;82
12.4.4;3.4.4 TSN and Real-Time Ethernet in Industrial Applications;85
12.5;3.5 Web Services and Service-Oriented Architectures;87
12.6;3.6 Intelligent Production Automation by Means of Multi-Agent Systems;89
12.6.1;3.6.1 Fundamental Concepts of Multi-Agent Systems;89
12.6.2;3.6.2 Communication Protocols and Standards for Multi-Agent Systems;96
12.6.3;3.6.3 Agent-based Approaches in Production;99
12.6.4;3.6.4 Agent-Based Solutions for Intelligent Manufacturing;101
12.6.5;3.6.5 Holonic Manufacturing Systems;103
12.6.6;3.6.6 Comparison of Traditional and HMS Inspired Control Solutions;105
12.7;3.7 Machine Learning in Distributed Environments;106
12.7.1;3.7.1 Basic Characteristics of Machine Learning;107
12.7.2;3.7.2 Applications of Machine Learning in Manufacturing;108
12.8;3.8 Information Modeling for Intelligent Automation;110
12.9;3.9 Advanced Interoperability Standards for Manufacturing;112
12.9.1;3.9.1 OPC – The Interface Standard for Generic Shop Floor Interoperability;115
12.9.2;3.9.2 OPC UA – The Interface Standard for Integrated Communication and Information Modeling;119
12.9.3;3.9.3 OPC UA System Architecture and Basic Services;124
12.9.4;3.9.4 AddressSpace Model and OPC UA based Information Modeling;125
12.9.5;3.9.5 Security Aspects of OPC UA for Reliable Information Exchange;129
12.9.6;3.9.6 Service-Oriented and Event-Driven Approaches through OPC UA;130
12.9.7;3.9.7 Interoperability with Tightly Coupled Systems by Means of OPC UA and Time-Sensitive Networking;132
12.9.8;3.9.8 Companion Standards and Domain-Specific Models for OPC UA;136
12.9.9;3.9.9 Realization of Agent-based and Decentralized Intelligence Approaches through OPC UA;139
13;4 Architecture of a Framework For Real-Time Interoperable Factories;145
13.1;4.1 Requirement Analysis for Legacy Systems in Automated Production Sites;146
13.1.1;4.1.1 Management Perspective of Automation Systems;146
13.1.2;4.1.2 Engineering Perspective for the Requirements of Flexible Automation Systems;148
13.1.3;4.1.3 Requirements from an Information Technological Perspective;150
13.2;4.2 MAS Architecture Enabling Interoperability with Existing Automation Solutions;152
13.2.1;4.2.1 Basic Architecture;153
13.2.2;4.2.2 Internal Agent Architecture;156
13.2.3;4.2.3 HMS Reference Architecture;160
13.2.4;4.2.4 Cross-Domain Architecture;163
13.3;4.3 Overall MAS Architecture for Cooperating Agents in a Smart Factory Environment;166
13.3.1;4.3.1 Multi-Agent System Architecture;167
13.3.2;4.3.2 Internal Agent Behavior and Hardware Component Interaction;171
13.4;4.4 Smart Automation of a Flexible Production by means of Evolving Software Agents;172
13.5;4.5 Limitations of the Architecture – Communication and Evolutionary Capabilities;174
13.5.1;4.5.1 Critical Discussion in terms of Communication Flexibility;175
13.5.2;4.5.2 Scalability Limitations – Learning and Evolutionary Development;176
14;5 Agent OPC UA – Semantic Scalability and Interoperability Architecture for Multi-Agent Systems through OPC UA;177
14.1;5.1 Bridging the Gap to OPC Classic;180
14.2;5.2 Information Modeling and Infrastructure for CPPS;181
14.3;5.3 Implementation of OPC UA Enabled Multi-Agent Systems;183
14.3.1;5.3.1 Agent Requirements Specification;184
14.3.2;5.3.2 Multi-Agent System Requirements Specification;185
14.3.3;5.3.3 Required Functionalities of an OPC UA enabled MAS;186
14.3.4;5.3.4 Messaging System;186
14.3.5;5.3.5 Data Storage;196
14.3.6;5.3.6 Reading Values from Remote Devices;200
14.3.7;5.3.7 White Page Services;205
14.3.8;5.3.8 Yellow Page Service Realization;207
14.3.9;5.3.9 Discovery Process in MAS and Dynamic Networking;208
14.3.10;5.3.10 Incorporation of Traditional MAS through Gateway Agents;209
14.3.11;5.3.11 Interconnection of Multiple MAS by means of Mediation Agents;212
14.4;5.4 Representation of Intelligent Agents by means of OPC UA;214
14.4.1;5.4.1 OPC UA AddressSpace Representation for Smart Agents;215
14.4.2;5.4.2 OPC UA AgentType Model;217
14.5;5.5 Semantic Integration of Agent Communication and Interoperability;225
14.5.1;5.5.1 The MessageType Object Definition;225
14.5.2;5.5.2 Hierarchical Organization of Message Objects;228
14.5.3;5.5.3 Compatibility of OPC UA to Legacy ACL Messages;229
14.5.4;5.5.4 The ContentType Specification;230
14.5.5;5.5.5 The AbilityType Specification;231
14.5.6;5.5.6 SensorType Definitions;232
14.5.7;5.5.7 Overall Information Model for OPC UA Based MAS;232
15;6 Management System Integration of OPC UA based MAS;235
15.1;6.1 Architecture Extension for Decentralized Planning;235
15.1.1;6.1.1 General Capabilities/Requirements for Resource Planning;236
15.1.2;6.1.2 The ERP Agent as Gateway to High-Level Planning Systems;237
15.1.3;6.1.3 Planning and Scheduling Capabilities;240
15.1.4;6.1.4 Decentralized Organization Based on a Blackboard Approach;241
15.2;6.2 Incorporation of an ERP System Into OPC UA Based MAS;242
15.2.1;6.2.1 The ERP Information Model Specification;243
15.2.2;6.2.2 Incorporation of an Open Source ERP System;245
15.2.3;6.2.3 Cooperative Reactive Production Planning;246
16;7 Flexible Manufacturing based on Autonomous, Decentralized Systems;247
16.1;7.1 Learning Agents for Flexible Manufacturing;247
16.2;7.2 Machine Learning in Learning Agent Environments;249
16.3;7.3 Predictive Maintenance Manufacturing Scenarios;250
16.3.1;7.3.1 Prediction of the Remaining Useful Lifetime;251
16.3.2;7.3.2 Direct RUL Prediction with Neural Network Approaches;252
16.4;7.4 Application of ML Scenarios in MAS;253
16.4.1;7.4.1 Intelligent Negotiation Techniques in MAS;253
16.4.2;7.4.2 Quantitative Price Function for Negotiating Agents;255
16.4.3;7.4.3 Predictive Maintenance Costs through Machine Learning;257
16.4.4;7.4.4 Implementation of the RUL Prediction into Smart Agents;261
16.5;7.5 RUL Learning Agents in OPC UA Based MAS;262
17;8 Use-cases for Industrial Automation Processes;263
17.1;8.1 Domain Ontology for the “myJoghurt” Testbed;264
17.1.1;8.1.1 myJoghurt Demonstration Scenario and Work Flow;264
17.1.2;8.1.2 OPC UA Information Model for the Mapping of Agent Communication;268
17.1.3;8.1.3 Achievements and Limitations of the Use-Case Design Model;275
17.2;8.2 Manufacturing Use-Case;275
17.2.1;8.2.1 Process Description;276
17.2.2;8.2.2 Autonomous Organization of the Production Process;276
17.3;8.3 Demonstration Scenario – The Industry 4.0 Testbed;282
17.3.1;8.3.1 Technical Setup and Realization of the Demonstrator;282
17.3.2;8.3.2 Simulation of the Manufacturing Process;285
17.3.3;8.3.3 Learning and Evolution of the Software Agents;288
18;9 Future Research Topics;289
18.1;9.1 Semantic Scalability for Domain Specific Use-Cases;289
18.2;9.2 Generic Extensibility of Communication Concepts Based on Ontologies;290
19;Summary;292
20;Bibliography;294
21;Appendices;325
22;A Protocols for Production Automation;326
22.1;A.1 History and Background on Fieldbus Systems in Modern Manufacturing;326
22.2;A.2 Basics and Historical Background of Industrial Ethernet;332
23;B Architecture and Technical Realization of the MAS;337
23.1;B.1 Multi-Agent System Architecture;337
23.2;B.2 OPC UA Based MAS;338
23.2.1;B.2.1 GenericContentType Messages;338
23.2.2;B.2.2 ContentType Subtype Mapping;339
23.2.3;B.2.3 AbilityType Filtering Feature;340
23.2.4;B.2.4 ERP Model Extension;340
23.2.5;B.2.5 Technical Setup of the Demonstrator;342
24;C Machine Learning Results;344
24.1;C.1 Initial Prediction and Results of Genetic Algorithms;344