Neural Networks for Identification, Prediction and Control

1 Artificial Neural Networks.- l.1 Types of Neural Networks.- 1.1.1 Structural Categorisation.- l.1.2 Learning Algorithm Categorisation.- l.2 Example Neural Networks.- l.2.1 Multi-layer Perception (MLP).- 1.2.2 Learning Vector Quantization (LVQ) Network.- 1.2.3 CMAC Network.- 1.2.4 Group Method of Data Handling (GMDH) Network.- 1.2.5 Hopfield Network.- l.2.6 Elman and Jordan Nets.- 1.2.7 Kohonen Network.- 1.2.8 ART Network.- 1.3 Summary.- References.- 2 Dynamic System Identification Using Feedforward Neural Networks.- 2.1Dynamic System Descriptions.- 2.1.1 Input-output Model.- 2.1.2 State-space Model.- 2.2 Identification Based on System Inputs and Outputs.- 2.3 Identification Based on Measurable System States.- 2.4 Input-output Model Identification.- 2.4.1 Simulation Investigations.- 2.4.2 Results.- 2.5 State-space Model Identification.- 2.5.1 Plant Model and Identification Architecture.- 2.5.2 Simulations.- 2.6 Discussion.- 2.6.1 Hybrid Networks.- 2.6.2 Input-output versus State-space Modelling.- 2.7 Analysis of the Hybrid Network.- 2.8 Summary.- References.- 3 Dynamic System Modelling Using Recurrent Neural Networks.- 3.1 Basic Ehnan Network.- 3.1.1 Structure and Principle of Ehnan Network.- 3.1.2 Analysis of Ehnan Network.- 3.2 Modified Ehnan Network.- 3.3 Dynamic System Modelling.- 3.4 Further Analysis of Ehnan Networks.- 3.4.1 Dynamic Backpropagation in Ehnan Networks.- 3.4.2 Relation with the Modified Ehnan Network.- 3.5 Summary.- References.- 4 Modelling and Prediction Using GMDH Networks.- 4.1 N-Adaline Networks and Widrow-Hoff Learning.- 4.2 GMDH Network Based on N-Adalines.- 4.3 Applications.- 4.4 Discussion.- 4.5 Summary.- References.- 5 Financial Prediction Using Neural Networks.- 5.1 Stock Market Prediction.- 5.1.1 System Overview.- 5.1.2 Prediction Simulation.- 5.2 Currency Exchange Rate Prediction.- 5.2.1 Prediction Based on Neural Networks.- 5.3 Data Sets Adopted for Simulation.- 5.4 Prediction Based on GMDH Networks.- 5.5 Prediction Based on Multilayer Perception Networks.- 5.6 Prediction Based on Recurrent Networks.- 5.7 Discussion.- 5.8 Summary.- References.- 6 Neural Network Controllers.- 6.1 Neural Network Controllers.- 6.1.1 CMAC.- 6.1.2 Hierarchical Neural Network Model.- 6.1.3 Multilayered Neural Network Controller.- 6.2 Comparison of Neural Network Controllers.- 6.2.1 Hierarchical Neural Network Model and Multilayered Neural Network Controller.- 6.2.2 Multilayered Neural Network Controller (or Hierarchical Neural Network Model) and CMAC.- 6.2.3 Common Aspects of Neural Network Controllers.- 6.2.4 Comparison with Adaptive Controllers.- 6.3 Summary.- References.- 7 Neuromorphic Fuzzy Controller Design.- 7.1 Integrating Neural Networks and FLCs.- 7.1.1 Representation of a Simple Fuzzy Logic Controller as a Neural Network.- 7.1.2 Learning Algorithm.- 7.2 Results of Neuromorphic Fuzzy Controllers Design.- 7.2.1 Plant 1.- 7.2.2 Plant2.- 7.3 Summary.- References.- 8 Robot Manipulator Control Using Neural Networks.- 8.1 Modelling of a Multi-joint Robot.- 8.2 Control System.- 8.3 Application to a Two-joint Robot Arm.- 8.4 Discussion.- 8.5 Summary.- References.- Appendix A Introduction to Some Conventional Techniques of Identification, Prediction and Control.- Appendix B Fuzzy Sets and Fuzzy Logic Control.- Appendix C Genetic Algorithms.- Appendix D Program: Feedforward Network for System Identification.- Appendix E Program: Modified Elman Network for Identification.- Appendix F Program: GMDH Network for Prediction.- Author Index.