Diagnosis and Control for Multi-agent Systems Using Immune Networks

Soft computing (SC) is an evolving collection of methodologies, i.e., fuzzy, neuro, and evolutionary computing. Chaotic computing and immune systems are added later to enhance the soft computing capabilities. The fusion of SC components creates new functions i.e. flexible knowledge representation (symbol and pattern), acquisition and inference (tractability, machine intelligent quotient), and robust and low cost product. Among them immune systems are very suitable for control and diagnosis of multi-agent systems (large-scale and complex systems) that interact among human beings, environment and artificial objects corresponding to the usage of complex interactions among antibodies and antigens in the immune systems. This paper describes novel sensor fault diagnosis for an uninterruptible power supply control system and new decision making of a robot in a changeable environment using immune networks. Simulation studies show that the proposed methods are feasible and promising for control and diagnosis of large-scale and complex dynamical systems.

[1]  Xizhao Wang,et al.  Improving learning accuracy of fuzzy decision trees by hybrid neural networks , 2000, IEEE Trans. Fuzzy Syst..

[2]  Nicholas R. Jennings,et al.  Foundations of distributed artificial intelligence , 1996, Sixth-generation computer technology series.

[3]  Dipankar Dasgupta,et al.  Artificial neural networks and artificial immune systems: similarities and differences , 1997, 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation.

[4]  Rolf Isermann,et al.  Hierarchical motor diagnosis utilizing structural knowledge and a self-learning neuro-fuzzy scheme , 2000, IEEE Trans. Ind. Electron..

[5]  M. Kubat,et al.  Decision trees can initialize radial-basis function networks , 1998, IEEE Trans. Neural Networks.

[6]  D. Dasgupta,et al.  Immunity-based systems: a survey , 1997, 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation.

[7]  Yoshiki Uchikawa,et al.  Fault diagnosis of plant systems using immune networks , 1994, Proceedings of 1994 IEEE International Conference on MFI '94. Multisensor Fusion and Integration for Intelligent Systems.

[8]  Fernando José Von Zuben,et al.  Immune and Neural Network Models: Theoretical and Empirical Comparisons , 2001, Int. J. Comput. Intell. Appl..

[9]  Seppo J. Ovaska,et al.  Fuzzy neural network with general parameter adaptation for modeling of nonlinear time-series , 2001, IEEE Trans. Neural Networks.

[10]  Eiji O'Shima,et al.  A GRAPHICAL APPROACH TO THE PROBLEM OF LOCATING THE ORIGIN OF THE SYSTEM FAILURE , 1980 .

[11]  Yoshiki Uchikawa,et al.  Immunoid: an architecture for behavior arbitration based on the immune networks , 1996, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. IROS '96.

[12]  Jerne Nk.  Towards a network theory of the immune system. , 1974 .

[13]  Jirí Benes,et al.  On neural networks , 1990, Kybernetika.

[14]  Yoshiteru Ishida.  An immune network model and its applications to process diagnosis , 1993, Systems and Computers in Japan.

[15]  David B. Fogel,et al.  Evolutionary Computation: Towards a New Philosophy of Machine Intelligence , 1995 .

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

[17]  Eiji O'Shima,et al.  A graphical approach to cause and effect analysis of chemical processing systems , 1980 .

[18]  M. Iri,et al.  An algorithm for diagnosis of system failures in the chemical process , 1979 .

[19]  Koichi Tanno,et al.  Adaptive Multi-Valued Immune Network And Its Applications , 2001 .

[20]  Yoichi Sugita,et al.  Distributed diagnosis system combining the immune network and learning vector quantization , 1995, Proceedings of IECON '95 - 21st Annual Conference on IEEE Industrial Electronics.