Stability analysis of neural net controllers using fuzzy neural networks

Neural networks can only be trained with a crisp and finite data set. Therefore, the approximation quality of a trained network is hard to verify. So, a common way in proving stability of a trained neural net controller is to demonstrate the existence of a Lyapunov function. In this article we propose a new method how stability of a neural net controller, used as a closed-loop feedback controller, can be proven. Instead of finding a Lyapunov function, conditions for a fuzzy training set are developed. If a fuzzy neural net is trained using this training set special properties of fuzzy neural nets can be used for estimating the generalization error. After defuzzification of the fuzzy net finite stability of the process can be concluded.

[1]  James J. Buckley.  Erratum: Universal fuzzy controllers , 1997, Autom..

[2]  James J. Buckley,et al.  Neural nets can be universal approximators for fuzzy functions , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[3]  J. Buckley,et al.  Backpropagation and genetic algorithms for training fuzzy neural nets , 1996, Proceedings of IEEE 5th International Fuzzy Systems.

[4]  Liang Jin,et al.  Globally asymptotical stability of discrete-time analog neural networks , 1996, IEEE Trans. Neural Networks.

[5]  T. Feuring,et al.  Fuzzy neural networks are overlapping , 1996, Proceedings of IEEE 5th International Fuzzy Systems.

[6]  Eugenius Kaszkurewicz,et al.  Existence and stability of a unique equilibrium in continuous-valued discrete-time asynchronous Hopfield neural networks , 1996, IEEE Trans. Neural Networks.

[7]  T. Feuring,et al.  Learning in fuzzy neural networks , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[8]  Yuguang Fang,et al.  Stability analysis of dynamical neural networks , 1996, IEEE Trans. Neural Networks.

[9]  H. Ishibuchi,et al.  A learning algorithm of fuzzy neural networks with triangular fuzzy weights , 1995 .

[10]  T H Feuring,et al.  FUZZY NEURAL NETWORKS ARE UNIVERSAL APPROXIMATORS , 1995 .

[11]  T. Feuring,et al.  Stability analysis of neural networks , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[12]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[13]  James J. Buckley,et al.  Can fuzzy neural nets approximate continuous fuzzy functions , 1994 .

[14]  Kazuo Tanaka,et al.  An approach to stability criteria of neural-network control systems , 1996, IEEE Trans. Neural Networks.

[15]  Robert M. Sanner,et al.  Gaussian Networks for Direct Adaptive Control , 1991, 1991 American Control Conference.

[16]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[17]  J. J. Buckley,et al.  Stability and the fuzzy controller , 1996, Fuzzy Sets Syst..

[18]  R. Rees Fullmer,et al.  A training rule which guarantees finite-region stability for a class of closed-loop neural-network control systems , 1996, IEEE Trans. Neural Networks.

[19]  James J. Buckley,et al.  Universal approximators for fuzzy functions , 2000, Fuzzy Sets Syst..

[20]  Thomas Feuring,et al.  The fuzzy neural network approximation lemma , 1999, Fuzzy Sets Syst..

[21]  Constantin V. Negoita,et al.  On Fuzzy Systems , 1978 .

[22]  Derek P. Atherton,et al.  Stability of nonlinear systems , 1981 .

[23]  G. P. Szegö,et al.  Stability theory of dynamical systems , 1970 .

[24]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[25]  Liang Jin,et al.  Absolute stability conditions for discrete-time recurrent neural networks , 1994, IEEE Trans. Neural Networks.

[26]  Hisao Ishibuchi,et al.  Learning of fuzzy connection weights in fuzzified neural networks , 1996, Proceedings of IEEE 5th International Fuzzy Systems.

[27]  James J. Buckley,et al.  Can neural nets be universal approximators for fuzzy functions? , 1999, Fuzzy Sets Syst..