Arzen Computer Software Structures Integrating AI/KBS Systems in Process Control

1. Auflage 2014
ISBN: 978-1-4832-9761-3
Verlag: Elsevier Science & Techn.
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 232 Seiten, Web PDF

Reihe: IFAC Postprint Volume

The past few years have seen rapid developments in computer technology, giving rise to a range of system control options which can be applied in the process industries. These include; open systems, expert systems, neural networks, fuzzy systems and object-oriented systems, all of which are covered in this key volume, which provides an invaluable summary of the latest international research in this area.

Autoren/Hrsg.

Arzen, K. -E.

Inhaltsverzeichnis

1;Front Cover;1
2;Computer Software Structures Integrating AI/Kbs Systems in Process Control;2
3;Copyright Page;3
4;Table of Contents;6
5;Chapter 1. Towards Integrated Process Supervision: Current Status and Future Directions;10
5.1;1 . INTRODUCTION;10
5.2;2 . PROBLEM SOLVING PARADIGMS IN PROCESS SUPERVISION;11
5.3;3. INTEGRATED PROCESS SUPERVISION: CHALLENGES AND THE ROLE OF AI;12
5.4;4. CURRENT STATUS OF AUTOMATION IN PROCESS SUPERVISION: A BRIEF REVIEW;14
5.5;5. BRINGING IT ALL TOGETHER: FUTURE DIRECTIONS IN INTEGRATED PROCESS SUPERVISION;18
5.6;6 . CONCLUSIONS;21
5.7;7 . REFERENCES;21
6;Chapter 2. Software Integration of Real-Time Expert Systems;24
6.1;1. Introduction;24
6.2;2. Objectives;24
6.3;3. Approach;25
6.4;4. Implementation;27
6.5;5. Related Work;28
6.6;6. Summary and Future Directions;29
6.7;7. References;29
7;Chapter 3. DATA FLOW ARCHITECTURE FOR ADVANCED PROCESS CONTROL;30
7.1;1. INTRODUCTION;30
7.2;2. DATAFLOW;30
7.3;3. INTEGRATION;31
7.4;4. CONTROL SYSTEM;32
7.5;5. DATA FLOW GRAPHS;33
7.6;6. SUMMARY;34
7.7;7. DEFICIENCIES;34
7.8;8. PROTOTYPE;34
7.9;9. APPLICATION;35
7.10;10. CONCLUSIONS;35
7.11;REFERENCES;35
7.12;ACKNOWLEDGEMENTS;35
8;Chapter 4. CONTROLLER VERIFICATION USING QUALITATIVE REASONING;36
8.1;INTRODUCTION;36
8.2;CSTR PROCESS;37
8.3;RESULTS;37
8.4;CONCLUSIONS;38
8.5;REFERENCES;39
9;Chapter 5. TIME-DEPENDENT SYSTEM KNOWLEDGE REPRESENTATION BASED ON DYNAMIC MPLD;42
9.1;1. INTRODUCTION;42
9.2;2. TIME-DEPENDENT BEHAVIOR OF PHYSICAL SYSTEMS;43
9.3;3. DYNAMIC MPLD;44
9.4;4. EXAMPLES OF DMPLD REPRESENTATION;45
9.5;5. REFERENCE;48
10;Chapter 6. Combining Multilevel Flow Modeling and Hybrid Phenomena Theory for efficient design of engineering systems;50
10.1;1. INTRODUCTION;50
10.2;2. A KNOWLEDGE-BASED SUPPORT SYSTEM FOR FUNCTION-BASED DESIGN;51
10.3;3. MULTILEVEL FLOW MODELING AND ITS EXTENSION FOR DESIGN PROBLEMS;51
10.4;4. IMPLEMENTATION OF THE HYBRID PHENOMENA THEORY;52
10.5;5. EXAMPLE DESIGN PROBLEMS;53
10.6;6. CONCLUSIONS;54
10.7;7. ACKNOWLEDGEMENT;55
10.8;8. REFERENCES;55
11;Chapter 7. A SIMULATION ENVIRONMENT FOR EVALUATION OF KNOWLEDGE BASED FAULT DIAGNOSIS SYSTEMS;56
11.1;1. INTRODUCTION;56
11.2;2. CONCEPT OF THE SIMULATION ENVIRONMENT;57
11.3;3. THE MFM APPROACH TO FAULT DETECTION AND DIAGNOSIS;58
11.4;4. A CASE STUDY: A SIMULATED LABORATORY PLANT UNDER CONTROL;58
11.5;5. DISCUSSION AND FURTHER ENHANCEMENTS;60
11.6;6. CONCLUSIONS;61
11.7;ACKNOWLEDGEMENT;61
11.8;REFERENCES;61
12;Chapter 8. MULTI-PARADIGM REASONING FOR MOLECULAR BEAM EPITAXY CONTROL;62
12.1;1. GOALS;62
12.2;2. TECHNICAL DESCRIPTION - GENERAL APPROACH;62
12.3;3. TECHNICAL DESCRIPTION - SPECIFIC CASE;64
12.4;4. CONCLUSION;67
12.5;5. REFERENCES;67
13;Chapter 9. CANCELLATION CONTROLLER BASED ON FUZZY RELATIONAL MATRIX AND COMPARISON WITH OTHER CONTROL ALGORITHMS;68
13.1;1. INTRODUCTION;68
13.2;2. THE FUZZY RELATIONAL MATRIX MODEL;68
13.3;3. CANCELLATION CONTROLLER BASED ON FUZZY RELATIONAL MATRIX MODEL;70
13.4;4. FUZZY CANCELLATION CONTROL OF NONLINEAR PLANT;71
13.5;5. CONCLUSION;72
13.6;REFERENCES;72
14;Chapter 10. ADAPTIVE TUNING OF FUZZY LOGIC CONTROLLERS;74
14.1;1. INTRODUCTION;74
14.2;2. LINGUISTIC SIMULATION;74
14.3;3. CONTROLLER TUNING;76
14.4;4. ADAPTIVE FUZZY CONTROLLERS;78
14.5;5. CONCLUSIONS;79
14.6;6. REFERENCES;79
15;Chapter 11. STEPS TOWARDS REAL-TIME CONTROL USING KNOWLEDGE BASED SIMULATION OF FLEXIBLE MANUFACTURING SYSTEMS;80
15.1;1. INTRODUCTION;80
15.2;2. DECISION MAKING IN SIMULATION OF FMS;80
15.3;3. EXPERIMENTAL KB SIMULATION SYSTEMS FOR FMS;81
15.4;5. CONCLUSIONS;83
15.5;6. REFERENCES;83
16;Chapter 12. INTELLIGENT ACTUATION AND MEASUREMENT SYSTEM-BASED MODELLING: THE PRIAM WAY OF WORKING;84
16.1;1. INTRODUCTION;84
16.2;2.IAT CONTEXT;85
16.3;3.IAM CONTEXT;85
16.4;4. - FUNCTIONAL REQUIREMENT DIAGRAMS OF IAM;86
16.5;5. FUNCTIONAL DIAGRAMS OF IAM;87
16.6;6. CONCLUSION;88
16.7;7· ACKNOWLEDGEMENTS;88
16.8;8. ACRONYMS;88
16.9;9. REFERENCES;88
17;Chapter 13. REAL-TIME INTELLIGENT PROCESS CONTROL USING CONTINUOUS FUZZY PETRI NETS;90
17.1;1 Introduction;90
17.2;2 Fuzzy Logic Overview;90
17.3;3 Petri Net Overview;91
17.4;4 CFPN;91
17.5;5 Example;94
17.6;6 Conclusions;94
17.7;References;94
18;Chapter 14. PARAMETERIZED HIGH-LEVEL GRAFCET FOR STRUCTURING REAL-TIME KBS APPLICATIONS;98
18.1;1. INTRODUCTION;98
18.2;2. GRAFCHART;99
18.3;3. AN INDUSTRIAL EXAMPLE;100
18.4;4. HIGH-LEVEL GRAFCHART;101
18.5;5. CONCLUSIONS;102
18.6;REFERENCES;103
19;Chapter 15. Knowledge-Based Madelling of a TV -Tube Manufacturing Process;104
19.1;1 INTRODUCTION;104
19.2;2 THE SUPERVISION GOBAL ARCHITECTURE;104
19.3;3 THE PROCESS SIMULATION SYSTEM;106
19.4;4 PROCESS SIMULATION;107
19.5;5 CONCLUDING REMARKS;110
19.6;ACKNOWLEDGMENTS;110
19.7;REFERENCES;110
20;Chapter 16. A PERSPECTIVE ON THE INTEGRAED ARTIFICIAL INTELLIGENCE/KNOWLEDGE BASED SYSTEMS IN THE PROCESS INDUSTRIES: CHALLENGES AND OPPORTUNITIES;112
20.1;1 INTRODUCTION;112
20.2;2 POSITION OF ARTIFICIAL INTELLIGENCE/KNOWLEDGE BASED SYSTEMS;113
20.3;3 EXPERIENCEIN OTHER INDUSTRIES;114
20.4;4 ANALYSIS OF THE EVIDENCE;114
20.5;5 HOW COULD THE PROCESS INDUSTRIES CHANGE;115
20.6;6 CONCLUSIONS;116
20.7;REFERENCES;116
20.8;ACKNOWLEDGEMENT;116
21;Chapter 17. Improvement of Mold-Level Control using Fuzzy-Logic;118
21.1;1. Introduction;118
21.2;2. Model of the Mold-level Control Circuit;118
21.3;3. Fuzzy PI-Control of the Mold-level Circuit;120
21.4;4. Simulation results;122
21.5;5. Conclusion;123
21.6;REFERENCES;123
22;Chapter 18. RIP CONTROL IN KNOWLEDGE-BASED SYSTEMS;124
22.1;1. INTRODUCTION;124
22.2;2. RIP CONTROL;124
22.3;3. RIP DESIGN SHELL;127
22.4;4. HYBRID RULE BASE;128
22.5;5. RESULTS;129
22.6;6. CONCLUSION;129
22.7;7. REFERENCES;129
23;Chapter 19. PROCESS CONTROL USING RECURRENT NEURAL NETWORKS;130
23.1;1. INTRODUCTION;130
23.2;2. NEURAL NETWORKS ARCHITECTURES;130
23.3;3. NEURAL NETWORK BASED CONTROL ARCHITECTURES;131
23.4;4. SIMULATION STUDIES OF RECURRENT NEURAL CONTROLLERS;133
23.5;5. CONCLUSIONS;135
23.6;6. ACKNOWLEDGEMENTS;135
23.7;7. REFERENCES;135
24;Chapter 20. FUZZY ANTI-RESET WINDUP FOR HEATER CONTROL;136
24.1;1. INTRODUCTION;136
24.2;2. CONTROL PROBLEM;136
24.3;3. ANALYSIS;137
24.4;4. ANTI WINDUP SCHEME;139
24.5;5. SIMULATIONS;140
24.6;6. CONCLUSIONS;141
24.7;7. REFERENCES;141
25;Chapter 21. ACTION PLANS DYNAMIC APPLICATION IN THE ALEXIP KNOWLEDGE-BASED SYSTEM;142
25.1;1. INTRODUCTION;142
25.2;2. SITUATION GRAPHS;142
25.3;3. SELECTION OF PLANS OFACTION;146
25.4;4. CONCLUSIONS;147
25.5;5. ACKNOWLEDGMENTS;147
25.6;6. REFERENCES;147
26;Chapter 22. COMPUTERISED SUPPORT IN THE PREPARATION, IMPLEMENTATION AND MAINTENANCE OF OPERATING PROCEDURES;148
26.1;1. INTRODUCTION;148
26.2;2. PROCEDURE PREPARATION;149
26.3;3. PROCEDURE IMPLEMENTATION;150
26.4;4. DISCUSSION;151
26.5;5. CONCLUSIONS;153
26.6;REFERENCES;153
27;Chapter 23. COAST - COMPUTERISED ALARM SYSTEM TOOLBOX;154
27.1;1. INTRODUCTION;154
27.2;2. FUNCTIONALITY OF COAST;155
27.3;3. STRUCTURE AND INTERFACES;157
27.4;4. CONCLUSION;158
27.5;5. REFERENCES;159
28;Chapter 24. APPLICATION OF THE EXPERT CONTROL IN A SUGAR FACTORY;160
28.1;1. INTRODUCTION;160
28.2;2. EXPERT CONTROL;160
28.3;3. EXTRACTION CONTROL;161
28.4;4. CO-ORDINATION CONTROL;163
28.5;5. CRYSTALLISATION CONTROL IN A VACUUM PAN;164
28.6;6. PRACTICAL IMPLEMENTATION AND RESULTS;165
28.7;8. REFERENCES;165
29;Chapter 25. AREAL-TIME KNOWLEDGE-BASED BLAST FURNACE SUPERVISION SYSTEM;166
29.1;1. INTRODUCTION;166
29.2;2. THE STRUCTURE OF THE SYSTEM;167
29.3;3. THE APPLICATION;168
29.4;4. CONCLUDING REMARKS;170
29.5;5. REFERENCES;170
30;Chapter 26. REAL TIME SUPERVISION OF WASTEWATER TREATMENT PLANTS: A DISTRIBUTED AI APPROACH;172
30.1;1 INTRODUCTION;172
30.2;2. DISTRIBUTED AI AND REAL TIME PROCESS CONTROL;173
30.3;3. DESIGN OF THE DISTRIBUTED SUPERVISORY SYSTEM'S ARCHITECTURE;174
30.4;4. THE SUPERVISORY CYCLE;175
30.5;5. A CASE STUDY;176
30.6;6. CONCLUSIONS AND FUTURE WORK;176
30.7;ACKNOWLEDGEMENTS;177
30.8;REFERENCES;177
31;Chapter 27. NEURAL NETWORK MODEL FOR DISSOLVED OXYGEN CONTROL IN A BATCH FERMENTER;178
31.1;1. INTRODUCTION;178
31.2;2. NEURAL NETWORK MODEL;179
31.3;3. APPLICATION RESULTS;180
31.4;4. CONCLUSION;182
31.5;5. REFERENCES;182
32;Chapter 28. RULE BASED INTERPOLATING CONTROL FUZZY AND ITS ALTERNATIVES;184
32.1;1. INTRODUCTION;184
32.2;2. RULEBASED INTERPOLATING CONTROL;184
32.3;3. FUZZY SYSTEMS;185
32.4;4. LINEARIZATION;186
32.5;5. AND THE ALTERNATIVES;187
32.6;6. NONLINEAR MODELERS;188
32.7;7. CONCLUSIONS;189
32.8;8. REFERENCES;189
33;Chapter 29. AREAL-TIME EXPERT SYSTEM FOR PROCESS SUPERVISION AND ITS APPLICATION IN PULP INDUSTRY;190
33.1;1. BACKGROUND;190
33.2;2. WHYUSING KBS TECHNIQUES;190
33.3;3. OVERVIEW OF KE 2000;191
33.4;4. THE EXPERT SYSTEM;191
33.5;5. ARCHITECTURE OF THE PROTOTYPE;194
33.6;6. CURRENT STATUS;194
33.7;7. EFFORT;194
33.8;8. EVALUATION;195
33.9;9. ACKNOWLEDGEMENTS;195
33.10;REFERENCES;195
34;Chapter 30. Experiences from development and operation of an operator guidance system for the blast furnace process;196
34.1;1. INTRODUCTION;196
34.2;2. PROCESS CONTROL;197
34.3;3. INITIAL DECISION MODEL;197
34.4;4. MODIFIED DECISION MODEL;198
34.5;5. THE FUNCTION OF MASMESTER;199
34.6;6. RESULTS OF OPERATION;199
34.7;7. ACHIEVING ACCEPTANCE FROM THE ORGANIZATION;200
34.8;8. FURTHER R&D;201
34.9;9. CONCLUSIONS;201
34.10;10. REFERENCES;201
35;Chapter 31. Fuzzy Persistence in Process Protection;202
35.1;1. INTRODUCTION;202
35.2;2. IMPLEMENTATION OF FUZZY PERSISTENCE;204
35.3;3. CONCLUSION;205
35.4;4. ACKNOWLEDGMENT;205
36;Chapter 32. QUALITATIVE FAULT DETECTION BASED ON LOGICAL PROGRAMMING APPLIED TO A VARIABLE AIR VOLUME AIR HANDLING UNIT;208
36.1;1. INTRODUCTION;208
36.2;2. DESCRIPTION OF THE AIR-HANDLING SYSTEM;208
36.3;3. THE STEADY-STATE BEHAVIOUR OF THE SYSTEM;210
36.4;4. DESIGN OF QUALITATIVE FAULT DETECTORS OF THE CENTRAL AIR HANDLING PLANT;211
36.5;5. CONCLUSIONS AND OUTLOOK;216
36.6;6. ACKNOWLEDGEMEN;216
36.7;7. REFERENCES;216
37;Chapter 33. PROCESS DIAGNOSIS IMMUNE FROM SENSOR FAULT BY SELF-ORGANIZATION;220
37.1;1. INTRODUCTION;220
37.2;2. MUTUAL RECOGNITION NETWORK MODEL;220
37.3;3. MODIFICATIONS ON THE MUTUAL RECOGNITION MODEL;221
37.4;4. APPLICATION TO SENSOR SELF-DIAGNOSIS;222
37.5;5. PROCESS FAULT DETECTION BY HIERARCHICAL IMMUNE NETWORK;223
37.6;6. APPLICATION TO THE INDUSTRIAL PROCESS PLANT;224
37.7;7. CONCLUSIONS;225
37.8;8. REFERENCES;225
38;Chapter 34. AN INTELLIGENT ALARM HANDLING TOOL;226
38.1;1. INTRODUCTION;226
38.2;2. FIRST NAVIGATOR;226
38.3;3. KNOWLEDGE ACQUISITION;227
38.4;4. DATA-COLLECTION THROUGH EVENTS;228
38.5;5. PREDICTING CONSEQUENCES IN THE PROCESS;228
38.6;6. CONCLUSIONS;229
38.7;7. REFERENCES;230
39;AUTHOR INDEX;232