You are previewing Design and Implementation of Intelligent Manufacturing Systems: From Expert Systems, Neural Networks, to Fuzzy Logic.
O'Reilly logo
Design and Implementation of Intelligent Manufacturing Systems: From Expert Systems, Neural Networks, to Fuzzy Logic

Book Description

The introduction of artificial intelligence, neural networks, and fuzzy logic into industry has given a new perspective to manufacturing processes in the U.S. and abroad. To help readers keep pace, this book addresses topics of intelligent manufacturing from a variety of theoretical, empirical, design, and implementation perspectives.

Table of Contents

  1. Copyright
    1. Dedication
  2. Prentice Hall Series on Environmental and Intelligent Manufacturing Systems
  3. Series Editor’s Foreword
  4. Preface
  5. 1. Workcell Programming Environment for Intelligent Manufacturing Systems
    1. 1.1. Introduction
    2. 1.2. Manufacturing Workcell
    3. 1.3. Workcell Programming
      1. 1.3.1. Robot Programming
      2. 1.3.2. Milling Machine Programming
      3. 1.3.3. Other Accessories
      4. 1.3.4. Cart and Sensors
    4. 1.4. Data Acquisition
    5. 1.5. Real Time Programming
    6. 1.6. State Transition Logic
    7. 1.7. Communication and Control
    8. 1.8. Implementation
    9. 1.9. Conclusion
    10. 1.10. Acknowledgments
    11. 1.11. References
  6. 2. An Intelligent System for Automating the Inspection of Manufactured Parts
    1. Introduction
    2. The ANC Framework
      1. Obtain Operation from the Process Plan
      2. Decompose Material to be Removed
      3. Determine Machine Tool and NC Methods
      4. Determine Set-Up
      5. Determine Cutting Tool and Holder
      6. Detail/Optimize NC Plan
      7. Generate/Simulate Tool Path
      8. Produce Machine Control Information
      9. Produce Support Information
      10. ANC Research Issues
    3. Development of an Automated Inspection Process Planning Framework Using Advanced Numerical Control Concepts
      1. The EPS-1 Architecture
      2. Obtain Operation Plan
      3. Task Decomposition
      4. Determine Methods and DME
      5. Determine Setup
      6. Determine Probe/Holder
      7. Detail/Optimize Operation Plan
      8. Generate/Simulate Probe Path
      9. Produce Control Information
      10. Produce Support Information
    4. Operational Environment of the EPS-1
      1. Geometric Modeler
      2. Dimensioning and Tolerance Modeler
      3. Applications Interface Specification
      4. Dimensioning and Tolerance Applications Interface Specification
      5. Dimensional Measuring Interface Specification
    5. Summary and Conclusions
    6. References
  7. 3. An Intelligent Hybrid System for Synthesis and Control of Metal Forming Processes
    1. 3.1. Introduction
    2. 3.2. Optimal Design Strategy
      1. 3.2.1. Identification of process sequence
      2. 3.2.2. Conceptual design
      3. 3.2.3. Working of the Process
      4. 3.2.4. Optimization of the process
    3. 3.3. The Pack Rolling Process
    4. 3.4. Intelligent Hybrid System
      1. 3.4.1. Data Collection
      2. 3.4.2. Data Evaluation and Analysis
      3. 3.4.3. Inferences and Conclusions
    5. 3.5. Development of the Intelligent Hybrid System
      1. 3.5.1. Development of the Neural Network
        1. 3.5.1.1. Conceptual Design: Identification of the input and output parameters
        2. 3.5.1.2. Data Collection: Design of Experiments
        3. 3.5.1.3. Building and Training the Neural Network
        4. 3.5.1.4. Data Evaluation
      2. 3.5.2. Development of the Expert System
        1. 3.5.2.1. Material Data Base Development - Generation of Stability Regions
        2. 3.5.2.2. Development of the User Interface
        3. 3.5.2.3. Incorporation of Constraints
        4. 3.5.2.4. Interface with the Neural Network
      3. 3.5.3. Intelligent Control Algorithm
    6. 3.6. Validation
      1. 3.6.1. Sample Pack Rolling Design - A Case Study
    7. 3.7. Conclusions and Recommendations
    8. Acknowledgements
    9. References
  8. 4. Intelligent Diagnostics for Integrated Manufacturing Systems
    1. 4.1. Introduction
    2. 4.2. Overview of Knowledge-Based Diagnosis
    3. 4.3. Hybrid Diagnostic Algorithm
    4. 4.4. Learning Capabilities
      1. 4.4.1. Conversion of a diagnostic case into rule form
      2. 4.4.2. Integration of a new rule into the knowledge base
      3. 4.4.3. Updating Rule Probabilities
    5. 4.5. Implementation
      1. 4.5.1. CIM System Case Study
    6. 4.6. Conclusions and Future Directions
    7. Acknowledgements
    8. References
  9. 5. Fuzzy Logic Controller for Part Routing
    1. 5.1. Background
    2. 5.2. Introduction
      1. The Routing Problem Description
    3. 5.3. The Linguistic Variables: The Basis for the FLC
    4. 5.4. Fuzzy Control Rules
    5. 5.5. Selecting the Control Action
      1. Example
    6. 5.6. Experimental Results
      1. Fine Tuning the System
    7. 5.7. Summary
    8. References
  10. 6. Fuzzy-Logic Control as an Industrial Control Language for Embedded Controllers
    1. 6.1. Introduction
    2. 6.2. Industrial Control Languages
    3. 6.3. A Code Generator for FLC
    4. 6.4. Overview of Fuzzy-Logic Control Methods
      1. 6.4.1. Acquisition of crisp inputs
      2. 6.4.2. Fuzzification
      3. 6.4.3. Rule Evaluation
      4. 6.4.4. Inference
      5. 6.4.5. Aggregation
      6. 6.4.6. Defuzzification
      7. 6.4.7. Output Generation
      8. 6.4.8. Remarks
    5. 6.5. Productivity and Utility Tools for Rule Generation
      1. 6.5.1. The PID Translator (PIDX)
      2. 6.5.2. The Rule-Base Reviewer (RBR)
      3. 6.5.3. The Fuzzy Rule Learner (FRL)
      4. 6.5.4. The Adaptive Fuzzy-Logic Controller (AFLC)
    6. 6.6. A Detailed Example
      1. 6.6.1. Input Acquisition
      2. 6.6.2. Fuzzification
      3. 6.6.3. Rule Evaluation
      4. 6.6.4. Inference, Aggregation, and Defuzzification
        1. 6.6.4.1. The TVFI (Truth Value Flow Inference) Method
        2. 6.6.4.2. The Mamdani Method
        3. 6.6.4.3. The Min-Product Method
        4. 6.6.4.4. The Mill-Correlation Method
    7. 6.7. Conclusions
    8. Acknowledgment
    9. References
  11. 7. Using Neural Networks for the Automatic Monitoring and Recognition of Signals in Manufacturing Processes
    1. 7.1. Introduction
    2. 7.2. The Back Propagation Neural Network
    3. 7.3. A Generalized Manufacturing Process Monitoring System
    4. 7.4. Applications
      1. Applications in Periodic Signals
      2. Applications to Aperiodic Signals
    5. 7.5. Concluding Remarks
    6. Acknowledgements
    7. References
  12. 8. Artificial Neural Network Approach in Modeling of EDM and Wire-EDM Processes
    1. 8.1. Introduction
    2. 8.2. Electro-Discharge Machining
    3. 8.3. Artificial Neural Network
    4. 8.4. Orbital EDM Modeling
    5. 8.5. Wedm Modeling
    6. 8.6. Results and Discussion
    7. 8.7. Conclusions
    8. Acknowledgement
    9. References
  13. 9. A Knowledge-Based Expert System for Selection of Industrial Robots
    1. 9.1. Introduction
    2. 9.2. Automation
    3. 9.3. Industrial Robots
      1. 9.3.1. Robot’s manipulator and anatomy
      2. 9.3.2. Drive systems
      3. 9.3.3. Programming Techniques
      4. 9.3.4. The Controller Unit
      5. 9.3.5. Precision of Movement
    4. 9.4. Robot Applications and Their Characteristics
      1. 9.4.1. Material Handling Operations
      2. 9.4.2. Processing Applications
    5. 9.5. Economic Justification for Robotics
    6. 9.6. Artificial Intelligence
    7. 9.7. Knowledge-Based Expert Systems
    8. 9.8. A Knowledge-Based Expert System for Selection of Industrial Robots
      1. 9.8.1. Knowledge acquisition
      2. 9.8.2. Decision tree
      3. 9.8.3. Knowledge base development
      4. 9.8.4. Sample scenario
    9. 9.9. Conclusion
    10. References
      1. APPENDIX 9-A: Sample Robots Specifications
  14. 10. A Case-Based Knowledge System Employed to Trouble Shoot Failures in a Manufacturing Environment
    1. 10.1. Introduction
    2. 10.2. A Rule-Based Expert System
    3. 10.3. Case-Based Versus Rule-Based
    4. 10.4. CBR Express Basic Architecture
      1. 10.4.1. ToolBook Interface
      2. 10.4.2. RDM Databases
      3. 10.4.3. C Libraries as DLL’s
    5. 10.5. The Fundamental Roles of Case Bases
    6. 10.6. Cases of ShootDem-Ks
    7. 10.7. Matching Algorithms
      1. 10.7.1. String Feature Matching
      2. 10.7.2. Word Feature Matching
      3. 10.7.3. Character Feature Matching
      4. 10.7.4. Number Feature Matching
    8. 10.8. Performance and Benchmark
    9. 10.9. Conclusions
    10. References
  15. 11. Partially Overlapped Systems: The Scheduling Problem
    1. 11.1. Introduction
    2. 11.2. Multi-Machine Systems: A General Model
      1. 11.2.1. Multi-Machine Structure: Graph Representation
    3. 11.3. Unit-Time Single Operation Jobs
      1. 11.3.1. Solution Methodology
        1. 11.3.1.1. The Algorithm
      2. 11.3.2. Complexity Analysis for P.O.S.U Algorithm
      3. 11.3.3. Example
    4. 11.4. Single Arbitrary-Time Operation Jobs
      1. 11.4.1. Solution Methodology
      2. 11.4.2. Example
    5. 11.5. Scheduling Multiple Unit-Time Operation Jobs
      1. 11.5.1. Problem Formulation
      2. 11.5.2. Heuristic Solution Using Graphical Representation
        1. 11.5.2.1. The Strategy
        2. 11.5.2.2. The Algorithm
        3. 11.5.2.3. Example
    6. 11.6. Conclusion
    7. Acknowledgement
    8. References
  16. 12. Object Oriented Approach to Feature-Based Process Planning
    1. 12.1. Introduction
    2. 12.2. Background on Process Planning
      1. 12.2.1. Variant Approach
      2. 12.2.2. Generative Approach
    3. 12.3. Feature-Based Generative CAPP
    4. 12.4. Object-Oriented Process Planning
      1. 12.4.1. The Object-Oriented Paradigm
      2. 12.4.2. The Object-Oriented Approach
      3. 12.4.3. Object-Oriented Process Planning Systems
    5. 12.5. Experimental System
      1. 12.5.1. Part Description
      2. 12.5.2. Operation Selection
      3. 12.5.3. Setup Identification
      4. 12.5.4. Tool Selection
      5. 12.5.5. Machining Parameter Determination
      6. 12.5.6. Machine Selection
      7. 12.5.7. Operation Sequencing
    6. 12.6. Part Versus Product Planning
      1. 12.6.1. Product Modeling
      2. 12.6.2. Product Planning
      3. 12.6.3. Assembly Planning Extension
    7. 12.7. Example
    8. 12.8. Conclusion
    9. References
  17. 13. Intelligent Feature Extraction for Concurrent Design and Manufacturing
    1. 13.1. Introduction
    2. 13.2. Literature Review
      1. 13.2.1. Computer Aided Process Planning(CAPP)
      2. 13.2.2. Feature-based Technologies
      3. 13.2.3. Feature Recognition/Extraction
      4. 13.2.4. Feature-based Process Planning
    3. 13.3. Prototype Feature-Based Automated Process Planning (FBAPP) System
      1. 13.3.1. CAD Interface
      2. 13.3.2. Process Planning
      3. 13.3.3. Post-processing
    4. 13.4. The Implementation
      1. 13.4.1. I-DEAS Solid Modeling Software and FBAPP
      2. 13.4.2. FBAPP and CLIPS Expert System Shell
      3. 13.4.3. The Operation of Prototype FBAPP System
      4. 13.4.4. Example
    5. 13.5. Conclusion
    6. 13.6. References
  18. 14. CAD in Automatic Machine Programming
    1. 14.1. Introduction
    2. 14.2. Desired CAD Data
    3. 14.3. Feature, Feature Representation and Classification
      1. 14.3.1. Feature Concept
      2. 14.3.2. The Euler Formula for Features
      3. 14.3.3. Representation of Feature Graph using Face-Edge Matrix
      4. 14.3.4. Feature Database
    4. 14.4. Feature Classification
    5. 14.5. Applications
      1. 14.5.1. Feature-based Design System
      2. 14.5.2. Feature Recognition System
      3. 14.5.3. Criteria Used for Feature Recognition
      4. 14.5.4. Pattern Matching
      5. 14.5.5. Feature Decomposition
    6. 14.6. Conclusion
    7. References
  19. 15. Fault Diagnosis of Large Manufacturing Processes
    1. 15.1. Introduction
    2. 15.2. Methods of Fault Diagnosis
    3. 15.3. Statement of the Problem
    4. 15.4. Architecture
      1. Design versus Decomposition
      2. Representation Component
      3. Reasoning Component
      4. ATMS versus JTMS for Fault Diagnosis
    5. 15.5. Characterization of Large-Scale Manufacturing Processes
      1. System Inputs
      2. Comparison to Previous Efforts
    6. 15.6. Process Model
      1. Methods of Process Modeling
      2. Recursive Network Modeling
      3. Modeling Operators
    7. 15.7. Fault Diagnosis Problem Solver
      1. Formalization of Fault Diagnosis
      2. Logic for Fault Diagnosis
      3. Creating the Nodes and Justifications
      4. Fault Diagnosis
    8. 15.8. Example Process Model
      1. Example Results
    9. 15.9. Conclusions
      1. Model-Based Fault Diagnosis
      2. Fault Diagnosis of Manufacturing Processes
      3. Fault Diagnosis of Large-Scale Manufacturing Processes
      4. Future Work
    10. Acknowledgments
    11. References