## Fuzzy-neural Control: Principles, Algorithms, and ApplicationsShows how Fuzzy Logic and Neural Networks can be intgrated into a Model Reference Control context for real-time control of multivariable systems. It provides a unified architecture which accommodates several popular learning/reasoning paradigms, including Counter Propagation Networks, Radial Basis Functions and CMAC a fuzzy context. Unified treatment of fuzzy-algorithm-based and neural network based control systems. Introduces new fuzzy-nueral controller structures. Demonstrates the feasibility of proposed approach by showing applications. Graduate students of Neural Networks, Intellegent Control and fuzzy matters in depts of Electrical Engineering, Computer Science and Maths. |

### What people are saying - Write a review

We haven't found any reviews in the usual places.

### Contents

Preface | xi |

A unified approximate reasoning approach | 23 |

an application | 37 |

Copyright | |

10 other sections not shown

### Common terms and phrases

adaptive approach assumed back-propagation BNN-based change-in-error Chapter CMAC computational constructed control action control performance control rules control system controlled process convergence corresponding defined defuzzification denoted derived desired drug dynamics EC type environment expert system fuzzified fuzzy control algorithm fuzzy control system fuzzy logic fuzzy sets fuzzy subsets fuzzy systems fuzzy-neural system gain matrix given hidden units IF-THEN implementation indicated inference input data input-output iteration number knowledge representation layer learning algorithm learning control learning error learning gains linear loop mapping matching degree matrix measured membership function Multivariable fuzzy control neural networks nonlinear obtained on-line operation PID controller possible ppm ppc presented procedures process parameters proposed reasoning algorithms reference model represented respect response robustness rule-base SAMPLING INSTANT scheme self-learning self-organizing set-point SFCA shown in Figure simulation results specific steady-state gains supervised learning teacher signals tion universes of discourse values variables weight vector