Crespo Artificial Intelligence in Real-Time Control 1994

1. Auflage 2014
ISBN: 978-1-4832-9693-7
Verlag: Elsevier Science & Techn.
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 390 Seiten, Web PDF

Reihe: IFAC Postprint Volume

Artificial Intelligence is one of the new technologies that has contributed to the successful development and implementation of powerful and friendly control systems. These systems are more attractive to end-users shortening the gap between control theory applications. The IFAC Symposia on Artificial Intelligence in Real Time Control provides the forum to exchange ideas and results among the leading researchers and practitioners in the field. This publication brings together the papers presented at the latest in the series and provides a key evaluation of present and future developments of Artificial Intelligence in Real Time Control system technologies.

Autoren/Hrsg.

Crespo, A.

Inhaltsverzeichnis

1;Front Cover;1
2;Artificial Intelligence in Real Time Control 1994 (AIRTC'94);2
3;Copyrigh Page;3
4;Table of Contents;6
5;IFAC SYMPOSIUM ON ARTIFICIAL INTELLIGENCE IN REAL TIME CONTROL 1994;4
6;FOREWORD;5
7;PART 1:
PLENARY PAPERS;10
7.1;Chapter 1. Integrating Real-Time AI Techniques in Adaptive Intelligent Agents;10
7.1.1;1. INTRODUCTION;10
7.1.2;2. REAL TIME TECHNIQUES IN THE AGENT ARCHITECTURE;11
7.1.3;3. REAL-TIME AI TECHNIQUES IN THE AGENT'S REASONING METHODS;13
7.1.4;4. REAL-TIME AI TECHNIQUES IN THE AGENT'S CONTROL STRATEGY;14
7.1.5;5. EMERGENT REAL-TIME PROPERTIES IN AN AGENT'S BEHAVIOR;17
7.1.6;6. CONCLUSIONS;18
7.1.7;7. REFERENCES;18
7.2;CHAPTER 2. NEURAL NETWORK BASED ADAPTIVE CONTROL;22
7.2.1;1. INTRODUCTION;22
7.2.2;2. NEURAL NETWORK BASED CONTROL;23
7.2.3;3. LEARNING AND ADAPTATION;25
7.2.4;4. NN BASED ADAPTIVE CONTROLLERS CLASSIFICATION;26
7.2.5;5. NN ADAPTIVE CONTROL WITH FAST ADAPTATION SPEED;28
7.2.6;6. STABILITY ANALYSIS;29
7.2.7;7. IMPLEMENTATIONS;30
7.2.8;8. CONCLUSIONS;31
7.2.9;ACKNOWLEDGEMENT;31
7.2.10;9. REFERENCES;31
7.3;CHAPTER 3. A COMPUTATIONAL INTELLIGENCE PERSPECTIVE ON PROCESS MONITORING AND OPTIMIZATION;34
7.3.1;1. INTRODUCTION;34
7.3.2;2. THE FUNCTIONAL-LINK NET: EFFICIENCY IN LEARNING A MODEL OF A PROCESS;35
7.3.3;3. OPTIMIZATION;36
7.3.4;4 ASSOCIATIVE MEMORIZATION AND RECALL;36
7.3.5;5 THE COMPUTATIONAL INTELLIGENCE PERSPECTIVE;37
7.3.6;6. EXAMPLES OF PROCESS MONITORING AND OPTIMIZATION TASKS;37
7.3.7;7. REFERENCES;38
7.4;CHAPTER 4. TRENDS IN ARTIFICIAL INTELLIGENCE APPLICATIONS FOR REAL-TIME CONTROL (A SPECULATIVE STUDY);40
7.4.1;1. INTRODUCTION;40
7.4.2;2. REAL-TIME SYSTEMS;40
7.4.3;3. AI METHODS AND TIME CONSTRAINTS;42
7.4.4;4. AI APPLICATIONS IN REAL-TIME;45
7.4.5;5. TRENDS IN REAL-TIME AI;46
7.4.6;6. CONCLUSIONS;47
7.4.7;ACKNOWLEDGEMENT;48
7.4.8;REFERENCES;48
8;PART 2:
FUZZY LOGIC AND NEURAL NETWORKS;52
8.1;CHAPTER 5. DYNAMIC ANALYSIS OF WEIGTHED-OUTPUT FUZZY CONTROL SYSTEMS;52
8.1.1;1. INTRODUCTION;52
8.1.2;2. STABILITY ANALYSIS;53
8.1.3;3. WEIGTHED OUTPUT FUZZY CONTROLLERS;53
8.1.4;4. CONCLUSIONS;56
8.1.5;5. ACKNOWLEDGEMENTS;56
8.1.6;6. REFERENCES;57
8.2;CHAPTER 6. IDENTIFICATION OF FUZZY RULES FROM LEARNING DATA;58
8.2.1;1. INTRODUCTION;58
8.2.2;2. THE SIMPLIFIED COS-FUZZY CONTROLLER;58
8.2.3;3. THE IDENTIFICATION ALGORITHM;59
8.2.4;4. EXAMPLES;60
8.2.5;5. CONCLUSIONS;62
8.2.6;REFERENCES;63
8.3;CHAPTER 7. ROBUST DESIGN OF FUZZY CONTROLLERS BASED ON SMALL GAIN CONDITIONS;64
8.3.1;1. INTRODUCTION;64
8.3.2;2. STABILITY ANALYSIS;65
8.3.3;3. ROBUST DESIGN;66
8.3.4;4. EXAMPLE;68
8.3.5;5. CONCLUSIONS;69
8.3.6;6. ACKNOWLEDGEMENT;69
8.3.7;7. REFERENCES;69
8.4;CHAPTER 8. A FUZZY CONTROLLER FOR ACTIVATED SLUDGE WASTE WATER PLANTS;70
8.4.1;1. INTRODUCTION;70
8.4.2;2. AN EXAMPLE PLANT;70
8.4.3;3. CONVENTIONAL CONTROL;71
8.4.4;4. THE FUZZY CONTROLLER PROPOSED;72
8.4.5;5. SIMULATION EXPERIMENTS AND RESULTS;72
8.4.6;6. CONCLUDING REMARKS;74
8.4.7;Acknowledgements;74
8.4.8;7. REFERENCES;75
8.5;CHAPTER 9. AN ADVANCED FUZZY CONTROLLER FOR TRAFFIC LIGHTS;76
8.5.1;1. INTRODUCTION;76
8.5.2;2. FUZZY LOGIC AND TRAFFIC LIGHT DESIGN;76
8.5.3;3. THE PROBLEM CONSIDERED;77
8.5.4;4. SIMULATION EXPERIMENTS AND THEIR RESULTS;79
8.5.5;5. CONCLUDING REMARKS;80
8.5.6;Acknowledgements;80
8.5.7;6. REFERENCES;81
8.6;CHAPTER 10.
REAL TIME FUZZY CONTROL OF COLUMN FLOTATION PROCESS;82
8.6.1;1. INTRODUCTION;82
8.6.2;2. FUZZY CONTROLLER DESCRIPTION;83
8.6.3;3. GRAPHICAL USER INTERFACE;84
8.6.4;4. FUZZY CONTROLLER APPLICATION AND RESULTS;84
8.6.5;5. CONCLUSIONS;86
8.6.6;6. REFERENCES;87
8.7;CHAPTER 11. ANALYSIS OF RULEBASE COHERENCE IN FUZZY CONTROL SYSTEMS;88
8.7.1;1. INTRODUCTION;88
8.7.2;2. FUZZY SYSTEMS;88
8.7.3;3. COHERENCE OF RULEBASES;89
8.7.4;4. REDEFINITION OF THE IDEAL DEFUZZIFIER;91
8.7.5;5. RULEBASE ANALYSIS;92
8.7.6;6. CONCLUSIONS;93
8.7.7;7. REFERENCES;93
8.8;CHAPTER 12. DERIVATION OF FUZZY HYBRID MODELS FOR REAL-TIME FUZZY CONTROL DESIGN: APPLICATION TO A FURNACE;94
8.8.1;1. INTRODUCTION;94
8.8.2;2. THEORETICAL BACKGROUND;94
8.8.3;3. IDENTIFICATION OF MODEL PARAMETERS;96
8.8.4;4. REAL-TIME CONTROL DESIGN METHODOLOGY;96
8.8.5;5. RESULTS;97
8.8.6;6. CONCLUSIONS;98
8.8.7;7. REFERENCES;98
8.9;Chapter 13. Comparison of Fuzzy, Rule-Based, and Conventional Process Control;100
8.9.1;1. INTRODUCTION;100
8.9.2;2. CONVENTIONAL CONTROL;101
8.9.3;3. FUZZY CONTROL;102
8.9.4;4. RULE-BASED CONTROLLER;102
8.9.5;5. COMPARING THE CONTROL PRINCIPLES;103
8.9.6;6. CONCLUDING REMARKS;105
8.9.7;7. REFERENCES;105
8.10;CHAPTER 14.
LEARNING TO DIAGNOSE FAILURES OF ASSEMBLY TASKS;106
8.10.1;1. INTRODUCTION;106
8.10.2;2. THE EXECUTION SUPERVISOR;106
8.10.3;3. QUALITATIVE ERROR ANALYSIS;109
8.10.4;4. TRAINING AND LEARNING;110
8.10.5;5. CONCLUSIONS;112
8.10.6;Acknowledgments;112
8.10.7;References;112
8.11;CHAPTER 15. LEARNING OF SPECIFIC PROCESS MONITORS IN MACHINE TOOL SUPERVISION;114
8.11.1;1. INTRODUCTION;114
8.11.2;2. PROGNOSTIC AND MONITORING OF CNC MACHINES;114
8.11.3;3. TAXONOMY OF LEARNING;115
8.11.4;4. IMPLEMENTATION OF THE SPECIFIC PROCESS MONITOR;116
8.11.5;5. EXPERIMENTAL RESULTS;118
8.11.6;6. LIMITATIONS AND CONCLUSIONS;119
8.11.7;7. REFERENCES;119
8.12;CHAPTER 16. NEURAL-BASED LEARNING IN GRASP FORCE CONTROL OF A ROBOT HAND;120
8.12.1;1. INTRODUCTION;120
8.12.2;2. FORCE CONTROL PROBLEM;120
8.12.3;3. MULTI-LEVEL CONTROL SYSTEM;122
8.12.4;4. NEURAL FORCE CONTROL;122
8.12.5;5. CONCLUSION;125
8.12.6;6. REFERENCES;125
8.13;CHAPTER 17. INTEGRATED ACQUISITION, EXECUTION, EVALUATION, AND TUNING OF ELEMENTARY SKILLS FOR INTELLIGENT ROBOTS;126
8.13.1;1. INTRODUCTION;126
8.13.2;2. SKILLS IN ROBOT PROGRAMMING AND CONTROL;127
8.13.3;3. IDENTIFICATION OF LEARNING TASKS;128
8.13.4;4. THE INTERACTIVE PROGRAMMING ENVIRONMENT;129
8.13.5;5. AN ARCHITECTURE SUPPORTING REAL-TIME CONTROL AND ENHANCEMENT;130
8.13.6;6. CONCLUSION;130
8.13.7;ACKNOWLEDGEMENT;131
8.13.8;REFERENCES;131
8.14;CHAPTER 18. NEURAL-NET BASED OPTICAL ELLIPSOMETRY FOR MONITORING GROWTH OF SEMICONDUCTOR FILMS;132
8.14.1;1. INTRODUCTION;132
8.14.2;2. OPTICAL ELLIPSOMETRY FOR MONITORING FILM PROPERTIES AND THICKNESS;132
8.14.3;3. FUNCTIONAL LINK NETWORK;133
8.14.4;4. NEURAL-NET BASED OPTICAL ELLIPSOMETRY FOR MONITORING GROWTH OF SEMICONDUCTOR FILMS;133
8.14.5;5. EXPERIMENTAL RESULTS;135
8.14.6;6, CONCLUSION;137
8.14.7;7. REFERENCES;137
8.15;CHAPTER 19. ARTIFICIAL INTELLIGENCE IN PROCESS CONTROL OF PULSED LASER DEPOSITION;138
8.15.1;1. INTRODUCTION;138
8.15.2;2. PROBLEM DESCRIPTION;139
8.15.3;3. SOLUTION APPROACH AND IPM;140
8.15.4;4. RESULTS;142
8.15.5;5 ACKNOWLEDGMENTS;143
8.15.6;6 REFERENCES;143
8.16;CHAPTER 20. THE REAL ISSUES IN FUZZY LOGIC APPLICATIONS;144
8.16.1;1. INTRODUCTION;144
8.16.2;2. BINARY THINKING;144
8.16.3;3. ANALOG THINKING;145
8.16.4;4. RULE GENERATION;146
8.16.5;5. FUZZYFICATION AND DEFUZZYFICATION;146
8.16.6;6. IMPORTANT OBSERVATIONS AND RECOMMENDATIONS;147
8.16.7;7. FUZZY TANK CONTROL - AN APPLICATION;147
8.16.8;8. FUZZY LOGIC CAR CONTROLLER - AN APPLICATION;148
8.16.9;9. CONCLUSION;149
8.16.10;10. REFERENCES;149
8.17;CHAPTER 21. CASE STUDIES IN PROCESS MODELLING AND CONDITION MONITORING USING ARTIFICIAL NEURAL NETWORKS;150
8.17.1;1. INTRODUCTION;150
8.17.2;2. PROCESS DESCRIPTION;151
8.17.3;4. APPLICATION OF ARTIFICIAL NEURAL NETWORKS TO PROCESS MODELLING;151
8.17.4;5. MODELLING USING LINEAR MODELS;152
8.17.5;6. MELTER MODELLING RESULTS;153
8.17.6;7. APPLICATION OF ARTIFICIAL NEURAL NETWORKS TO CONDITION MONITORING;154
8.17.7;8. CONCLUSIONS;155
8.17.8;9. ACKNOWLEDGEMENTS;155
8.17.9;10. REFERENCES;155
8.18;CHAPTER 22. DAI-DEPUR ARCHITECTURE: DISTRIBUTED AGENTS FOR REAL-TIME WWTP SUPERVISION AND CONTROL;156
8.18.1;1. INTRODUCTION;156
8.18.2;2. DISTRIBUTED AI;156
8.18.3;3. ARCHITECTURE;157
8.18.4;4. A CASE STUDY;159
8.18.5;5. CONCLUSIONS AND FUTURE WORK;160
8.18.6;ACKNOWLEDGEMENTS;161
8.18.7;REFERENCES;161
8.19;CHAPTER 23. FAULT DIAGNOSIS OF A CSTR USING FUZZY NEURAL NETWORKS;162
8.19.1;1 INTRODUCTION;162
8.19.2;2 THE CSTR SYSTEM;163
8.19.3;3 FUZZY NEURAL NETWORKS FOR FAULT DIAGNOSIS;163
8.19.4;4 APPLICATION TO THE CSTR SYSTEM;164
8.19.5;5 CONCLUSIONS;166
8.19.6;6 REFERENCES;167
8.20;CHAPTER 24.
NEURAL NETWORKS FOR ROBOT CONTROL;168
8.20.1;1. INTRODUCTION;168
8.20.2;2. LEARNING INVERSE KINEMATICS;169
8.20.3;3. CONTROLLING INVERSE DYNAMICS WITH NEURAL NETWORKS;170
8.20.4;4. LEARNING VISUAL POSITIONING;172
8.20.5;5. CONCLUSIONS;173
8.20.6;Acknowledgements;174
8.20.7;References;174
8.21;Chapter 25. The NECTAR-project Research into the application of Neural Networks for Flight Control;176
8.21.1;Introduction;176
8.21.2;Neural Networks for Control;177
8.21.3;Preliminary results applying application of neural networks for flight control;180
8.21.4;Conclusions;181
8.21.5;Literature;181
8.22;Chapter 26. Optimal Attitude Control of Satellites by Artificial Neural Networks: a Pilot Study;182
8.22.1;1. Introduction;182
8.22.2;2. The ISO;182
8.22.3;3. Reinforcement Learning;183
8.22.4;4. Attitude control of ISO;184
8.22.5;5. Conclusion;187
8.22.6;References;187
8.23;CHAPTER 27.
LOGICAL DESIGN OF NEURAL CONTROLLERS;188
8.23.1;1. INTRODUCTION;188
8.23.2;2. TERMINOLOGY AND SPECIAL SYMBOLS;188
8.23.3;3. REASONING ABOUT NEURAL COMPUTATION WITH TIMED PROOFNETS;189
8.23.4;4. APPLICATION: IDENTIFICATION AND TRACKING SYSTEM CONTROLLER;190
8.23.5;5. SUMMARY;193
8.23.6;REFERENCES;193
8.24;CHAPTER 28. A NEURAL NETWORK BASED QUALITY CONTROL SYSTEM FOR STEEL STRIP MANUFACTURING;194
8.24.1;1. INTRODUCTION;194
8.24.2;2. SYSTEM DESCRIPTION;194
8.24.3;3. THE NEURAL CLASSIFIER;196
8.24.4;5. EXPERIMENTAL RESULTS;199
8.24.5;6. CONCLUSIONS;199
8.24.6;7. ACKNOWLEDGEMENTS;199
8.24.7;8. REFERENCES;199
8.25;CHAPTER 29.
TRAINING NEUROFUZZY SYSTEMS;200
8.25.1;1. INTRODUCTION;200
8.25.2;2. NEUROFUZZY SYSTEMS;201
8.25.3;3. THE CURSE OF DIMENSIONALITY;202
8.25.4;4. GLOBAL PARTITIONING;202
8.25.5;5. TRAINING;203
8.25.6;6. CONCLUSIONS;205
8.25.7;REFERENCES;205
9;PART 3: INTELLIGENT CONTROLLERS AND APPLICATIONS;206
9.1;CHAPTER 30. LEARNING TASK APPLIED TO IDENTIFICATION OF A MARINE VEHICLE;206
9.1.1;1. INTRODUCTION;206
9.1.2;2. SOLVING THE MODEL PARAMETER ESTIMATION TASK;207
9.1.3;3. STATE OBSERVER DESIGN;208
9.1.4;4. LEARNING ALGORITHM;208
9.1.5;5. IMPLEMENTATION PROCEDURE ON A SHIP STEERING CONTROL TASK;208
9.1.6;6. SIMULATION RESULTS AND CONCLUDING REMARKS;209
9.1.7;7. REFERENCES;210
9.1.8;8. ACKNOWLEDGEMENTS;210
9.2;CHAPTER 31. A LOCAL GUIDANCE METHOD FOR LOW-COST MOBILE ROBOTS USING FUZZY LOGIC;212
9.2.1;1. INTRODUCTION;212
9.2.2;2. APPROACH;212
9.2.3;3. LOCAL GUIDANCE;213
9.2.4;4. IMPLEMENTATION;215
9.2.5;5. ACKNOWLEDGMENTS;216
9.2.6;6. REFERENCES;216
9.2.7;CONCLUSIONS;215
9.3;CHAPTER 32. ROAD FOLLOWING BY ARTIFICIAL VISION USING NEURAL NETWORK;218
9.3.1;1. INTRODUCTION;218
9.3.2;2. DESCRIPTION;218
9.3.3;3. CHARACTERISTICS OBTAINING;218
9.3.4;4. SEGMENTATION;219
9.3.5;5. PREESTABUSHED PATTERNS;220
9.3.6;6. NEURAL NET;220
9.3.7;7. TIME DELAY NEURAL NET;221
9.3.8;8. ESTIMATION FUNCTION;222
9.3.9;9. DECISION-MAKING BLOCK;222
9.3.10;10. SYSTEM ADAPTATION;223
9.3.11;11. FUTURE IMPROVEMENTS;223
9.3.12;12. REFERENCES;223
9.4;CHAPTER 33. NAVIGATION WITH UNCERTAIN POSITION ESTIMATION IN THE RAM-1 MOBILE ROBOT;224
9.4.1;1. INTRODUCTION;224
9.4.2;2. LOCATION ESTIMATION IN THE RAM-1;225
9.4.3;3. UNCERTAINTY MODEL;226
9.4.4;4. APPLICATION TO RAM-1;227
9.4.5;5. CONCLUSIONS;228
9.4.6;6. REFERENCES;228
9.5;CHAPTER 34. REAL-TIME VISION-BASED NAVIGATION AND 3D DEPTH ESTIMATION FOR AN INDOOR AUTONOMOUS MOBILE ROBOT;230
9.5.1;1. INTRODUCTION;230
9.5.2;2. NAVIGATION;231
9.5.3;3. EGOMOTION AND DEPTH;233
9.5.4;3. IMPLEMENTATION;235
9.5.5;4. ACKNOWLEDGMENTS;235
9.5.6;REFERENCES;235
9.6;CHAPTER 35. REAL-TIME NEURAL CONTROLLER IMPLEMENTED ON PARALLEL ARCHITECTURE;236
9.6.1;1. INTRODUCTION;236
9.6.2;2. PARALLEL ALGORITHM;236
9.6.3;3. NEURAL CONTROLLER;238
9.6.4;4. CONCLUSION;241
9.6.5;References;241
9.7;CHAPTER 36. ACHIEVING HIGH PERFORMANCE SONAR-BASED WALL-FOLLOWING;242
9.7.1;Introduction;242
9.7.2;Assumptions;242
9.7.3;The Sonar Sensor Model;243
9.7.4;Control Laws;243
9.7.5;Achieving High Performance Behavior;243
9.7.6;Initial Exploration;244
9.7.7;Actual Navigation;244
9.7.8;Performance Evaluation;245
9.7.9;Conclusions and Future Work;245
9.7.10;Appendix: Accuracy of Odometry;245
9.7.11;References;245
9.8;CHAPTER 37. APPLICATION OF AN OBJECT-ORIENTED EXPERT SYSTEM SHELL TO A FERMENTATION PROCESS;246
9.8.1;1. INTRODUCTION;246
9.8.2;2. KNOWLEDGE ACQUISITION;246
9.8.3;3. EXPERIMENTAL STUDY OF THE PROCESS;247
9.8.4;4. APPLICATION OF AN ARTIFICIAL INTELLIGENCE TOOL;249
9.8.5;5. CONCLUSION;251
9.8.6;6. REFERENCES;251
9.9;CHAPTER 38. COMMUNICATION PROBLEMS OF EXPERT SYSTEMS IN MANUFACTURING ENVIRONMENT;252
9.9.1;1. INTRODUCTION;252
9.9.2;2. EXPERT SYSTEMS AND COMMUNICATION;252
9.9.3;3. THE SSQA APPROACH;254
9.9.4;4. CONNECTING G2 and SIMAN;254
9.9.5;5. CONCLUSIONS, FUTURE PLANS;256
9.9.6;6. REFERENCES;256
9.10;CHAPTER 39. ELECTRONIC CONTROL FOR A WHEEL-CHAIR GUIDED BY ORAL COMMANDS AND ULTRASONIC AND INFRARED SENSORS;258
9.10.1;1. INTRODUCTION;258
9.10.2;2. ELECTRONIC SYSTEM CONFIGURATION;259
9.10.3;3. SENSOR SYSTEM OF THE WHEEL-CHAIR;259
9.10.4;4. PHYSICAL DESCRIPTION AND MECHANICAL MODEL OF THE WHEEL-CHAIR;260
9.10.5;5. CONTROL;261
9.10.6;6. SPEECH RECOGNITION;263
9.10.7;7. RESULTS;263
9.10.8;8. REFERENCES;263
9.11;CHAPTER 40. HUMAN INTERACTION FOR PROCESS SUPERVISION BASED ON END-USER KNOWLEDGE AND PARTICIPATION;264
9.11.1;1. INTRODUCTION;264
9.11.2;2. TASK AND KNOWLEDGE ANALYSES;264
9.11.3;3. LOGICAL DESIGN OF HUMAN-MACHINE INTERFACE FUNCTIONALITIES;266
9.11.4;4. RAPID PROTOTYPING AND USABILITY TESTING;267
9.11.5;5. CONCLUSIONS;268
9.11.6;6. ACKNOWLEDGEMENTS;268
9.11.7;7. REFERENCES;268
9.12;CHAPTER 41.
NATURAL LANGUAGE FRONT END TO TEST SYSTEMS;270
9.12.1;1. Introduction;270
9.12.2;2. S/T Flight Test-Procedures Application Domain;271
9.12.3;3. Review of the State of the Art;272
9.12.4;4. Approaching NL and Test Definition;273
9.12.5;5. Front-End Architecture and Prototyping;275
9.12.6;6. Conclusions;276
9.12.7;Acknowledgements;276
9.12.8;References;276
9.13;Chapter 42.
Knowledge Integration for Improved Bioprocess Supervision;278
9.13.1;1. INTRODUCTION;278
9.13.2;2. BIOPROCESS DESCRIPTION;278
9.13.3;3. BUILDING THE INTELLIGENT SUPERVISORY SYSTEM;279
9.13.4;4. PATTERN RECOGNITION TECHNIQUES;279
9.13.5;5. APPLICATION OF PATTERN RECOGNITION TECHNIQUES;281
9.13.6;6. CONCLUSIONS AND FUTURE WORK;282
9.13.7;7. ACKNOWLEDGEMENTS;282
9.13.8;8. REFERENCES;282
9.14;CHAPTER 43.
RELAY LADDER LOGIC DIAGNOSIS;284
9.14.1;1. INTRODUCTION;284
9.14.2;2. KNOWLEDGE ACQUISITION;285
9.14.3;3. RELAY LADDER LOGIC (RLL);286
9.14.4;4. RLL ANALYSIS TOOL (LAT);286
9.14.5;5. CONCLUSIONS;288
9.14.6;6. ACKNOWLEDGMENTS;289
9.14.7;7. REFERENCES;289
10;PART 4:
ARTIFICIAL INTELLIGENCE ARCHITECTURES;290
10.1;CHAPTER 44. DECENTRALIZED CONTROL OF DISTRIBUTED INTELLIGENT ROBOTS AND SUBSYSTEMS;290
10.1.1;1. INTRODUCTION;290
10.1.2;2. THE ARCHITECTURE KAMARA;291
10.1.3;3. ASYNCHRONOUS COMMUNICATION;292
10.1.4;4. SYNCHRONOUS COMMUNICATION;293
10.1.5;5. REAL-TIME CONSTRAINTS;293
10.1.6;6. CONCLUSION;295
10.1.7;7. ACKNOWLEDGEMENT;295
10.1.8;8. REFERENCES;295
10.2;CHAPTER 45. A NEW PARADIGM FOR DISTRIBUTED, INTEGRATED, REAL-TIME CONTROL SYSTEMS;296
10.2.1;1.INTRODUCTION;296
10.2.2;2.TOWARDS AI-BASED INTEGRATED CONTROL;296
10.2.3;3.A NEW PARADIGM;297
10.2.4;4.THE DENIS ARCHITECTURE;300
10.2.5;5.CONCLUSIONS;301
10.2.6;REFERENCES;301
10.3;CHAPTER 46. A SIMULATION STUDY OF DISTRIBUTED INTELLIGENT CONTROL FOR A DEEP SHAFT MINE WINDER;302
10.3.1;1. INTRODUCTION;302
10.3.2;2. DISTRIBUTED INTELLIGENT CONTROL FOR CONTINUOUS PLANTS;302
10.3.3;3. CONTROL REQUIREMENTS FOR DEEP-SHAFT MINE WINDERS;303
10.3.4;4. PROPOSED CONTROL SCHEME;303
10.3.5;5. THE SIMULATION STUDY;304
10.3.6;6. COMMENT ON A PRIORI AND OPERATIONAL KNOWLEDGE;305
10.3.7;7. CONCLUSIONS;306
10.3.8;8. ACKNOWLEDGEMENTS;307
10.3.9;9. REFERENCES;307
10.4;CHAPTER 47. CONTINUATION COMPILATION FOR CONCURRENT LOGIC PROGRAMMING;308
10.4.1;1 Introduction;308
10.4.2;2 Intuition behind Continuation Compilation;309
10.4.3;3 Analysis for Continuation Compilation;310
10.4.4;4 Abstract Machine beneath Continuation Compilation;312
10.4.5;5 Related work;313
10.4.6;6 References;314
10.5;CHAPTER 48.
REAL TIME PLANNING IN N-DIM STATE SPACE;316
10.5.1;Introduction;316
10.5.2;World model;316
10.5.3;Control system;317
10.5.4;Inference mechanism;317
10.5.5;Symbolic layers;318
10.5.6;Low level layers;318
10.5.7;Proposed architecture;319
10.5.8;Low level agent;319
10.5.9;Subgoals agent;320
10.5.10;Conclusions;321
10.5.11;References;321
10.6;CHAPTER 49. INCREASING A KNOWLEDGE REPRESENTATION SCHEMA FOR FMS CONTROL WITH FAULT DETECTION AND ERROR RECOVERY CAPABILITIES;322
10.6.1;1. INTRODUCTION;322
10.6.2;2. THE BASIC REPRESENTATION SCHEMA;323
10.6.3;3. MONITORING AND FAULT DETECTION;324
10.6.4;4 METHOD FOR ERROR RECOVERY;325
10.6.5;5. CONCLUSIONS;325
10.6.6;REFERENCES;325
10.7;CHAPTER 50. REAKT: A Real Time architecture for knowledge based systems;328
10.7.1;Introduction;328
10.7.2;The architecture of the Reakt Toolkit;328
10.7.3;The Knowledge & Data Manager;329
10.7.4;Agents and Knowledge Sources;330
10.7.5;The Control Component;331
10.7.6;Temporal Reasoning;331
10.7.7;Communication protocols;332
10.7.8;Conclusions;332
10.7.9;Acknowledgements;332
10.7.10;Bibliography;332
10.8;Chapter 51.
Application methodology for REAKT1 systems;334
10.8.1;1. Introduction;334
10.8.2;2. Methodology overview;334
10.8.3;3. Conceptual modelling;335
10.8.4;4. Demonstrator application;337
10.8.5;5. Architecture and constraints;340
10.8.6;6. Conclusions;341
10.8.7;References;341
10.9;Chapter 52. The Development of an Artificial Intelligence Real-Time Toolkit: REAKT;342
10.9.1;1. Introduction;342
10.9.2;2.- REAKT Process Concurrency Model;344
10.9.3;3.- The C++ REAKT Architectural Components;344
10.9.4;4.- Performance Measurements;347
10.9.5;5.- Conclusions;348
10.9.6;Acknowledgement;348
10.9.7;References;348
10.10;CHAPTER 53. MORSAF: a real-time assistant for the management of a petrochemical plant;350
10.10.1;1. Introduction;350
10.10.2;2. Problem description;351
10.10.3;3. MORSAF architecture;351
10.10.4;4. Expert Task;352
10.10.5;5. Conclusions;354
10.10.6;6. Acknowledgements;355
10.10.7;7. References;355
10.11;Chapter 54. Temporal Data Representation and Reasoning in REAKT;356
10.11.1;INTRODUCTION;356
10.11.2;TEMPORAL DATA ONTOLOGY;357
10.11.3;TEMPORAL REPRESENTATION;358
10.11.4;TEMPORAL REASONING IN REAKT;359
10.11.5;CONCLUSIONS;361
10.11.6;REFERENCES;361
10.12;CHAPTER 55. AN INTEGRATION METHODOLOGY AND ARCHITECTURE FOR INTELLIGENT SYSTEMS IN PROCESS CONTROL: THE HINT PROJECT;362
10.12.1;1. INTRODUCTION;362
10.12.2;2. INTEGRATION METHODOLOGY;362
10.12.3;3. THE HINT ARCHITECTURE;365
10.12.4;4. RESULTS;366
10.12.5;5. REFERENCES;367
10.13;CHAPTER 56. COMMERCIAL PERSPECTIVE WHEN APPLYING AI TECHNIQUES AND TRADITIONAL IT SKILLS;368
10.13.1;1. INTRODUCTION;368
10.13.2;2. RH&H TASKS IN HINT;369
10.13.3;3. WHY R&D PROJECTS?;371
10.13.4;4. BUSINESS OPPORTUNITIES;371
10.13.5;5. CONCLUSION;371
10.14;CHAPTER 57. DESIGNING USER INTERFACES FOR APPLICATIONS BASED ON THE HINT ARCHITECTURE;374
10.14.1;1. INTRODUCTION;374
10.14.2;2. UIs FOR HINT APPLICATIONS;374
10.14.3;3. DESIGNING THE USER INTERFACE;375
10.14.4;4. DISCUSSION;378
10.14.5;5. CONCLUDING REMARKS;379
10.14.6;6. REFERENCES;379
10.15;CHAPTER 58. A REAL TIME EXPERT SYSTEM FOR CONTINUOUS ASSISTANCE IN PROCESS CONTROL: A SUCCESSFUL APPROACH;380
10.15.1;1. INTRODUCTION;380
10.15.2;2. MODULE DESIGN;381
10.15.3;3. REASONING PROCESS;382
10.15.4;4. RESULTS;383
10.15.5;7. REFERENCES;384
10.16;CHAPTER 59. A BLACKBOARD APPLICATION FOR PROCESS MONITORING AND SUPERVISION;386
10.16.1;1. INTRODUCTION;386
10.16.2;2. GLOBAL SYSTEM STRUCTURE;387
10.16.3;3. TASKS OF THE PROCESS CONTROL SYSTEM;387
10.16.4;4. ARCHITECTURE OF THE PROCESS CONTROL SYSTEM;388
10.16.5;5. CONCLUSION;390
10.16.6;6. ACKNOWLEDGEMENT;391
10.16.7;7. REFERENCES;391
10.17;CHAPTER 60. DEVELOPING E.S. FOR PROCESS CONTROL USING UNIX BASED TOOLS;392
10.17.1;Introduction;392
10.17.2;World model;393
10.17.3;Defmodule Modifications;394
10.17.4;Inference Engine Modifications;394
10.17.5;Communication overview;394
10.17.6;Fuzzy concepts using CLIPS;395
10.17.7;Graphical Interface;395
10.17.8;Conclusions;396
10.17.9;References;396
11;AUTHOR INDEX;398