Lyapunov Analysis of Neural Network Stability in an Adaptive Flight Control System

The paper presents the role of self-stabilization analysis in the design, verification and validation of the dynamics of an Adaptive Flight Control System (AFCS). Since the traditional self-stabilization approaches lack the flexibility to deal with the continuous adaptation of the neural network within the AFCS, the paper emphasizes an alternate self-stability analysis approach, namely Lyapunov's Second Method. A Lyapunov function for the neural network is constructed and used in presenting a formal mathematical proof that verifies the following claim: While learning from a fixed input manifold, the neural network is self-stabilizing in a Globally Asymptotically Stable manner. When dealing with variable data manifolds, we propose the need for a real-time stability monitor that can detect unstable state deviations. The test results based on the data collected from an F-15 flight simulator provide substantial heuristic evidence to support the idea of using a Lyapunov function to prove the self-stabilization properties of the neural network adaptation.

[1]  手島 通,et al.  Advanced control system , 1984 .

[2]  Murat Demirbas,et al.  Graybox stabilization , 2001, 2001 International Conference on Dependable Systems and Networks.

[3]  Bernd Fritzke,et al.  A Growing Neural Gas Network Learns Topologies , 1994, NIPS.

[4]  Marco Schneider,et al.  Self-stabilization , 1993, CSUR.

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

[6]  Thomas Martinetz,et al.  Topology representing networks , 1994, Neural Networks.

[7]  Xinghuo Yu,et al.  A backpropagation learning framework for feedforward neural networks , 2001, ISCAS 2001. The 2001 IEEE International Symposium on Circuits and Systems (Cat. No.01CH37196).

[8]  V. Zubov.  Methods of A.M. Lyapunov and their application , 1965 .

[9]  Bojan Cukic,et al.  Lyapunov stability analysis of the quantization error for DCS neural networks , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[10]  C. C. Jorgensen,et al.  Feedback Linearized Aircraft Control Using Dynamic Cell Structure , 1998 .

[11]  Edsger W. Dijkstra,et al.  Self-stabilizing systems in spite of distributed control , 1974, CACM.

[12]  Christian Blum,et al.  On the Role of Hierarchy for Neural Network Interpretation , 1997, IJCAI.

[13]  P. Antsaklis.  Intelligent control , 1986, IEEE Control Systems Magazine.

[14]  Gerald Sommer,et al.  On-line Learning with Dynamic Cell Structures , 2004 .

[15]  N. Rouche,et al.  Stability Theory by Liapunov's Direct Method , 1977 .

[16]  Gerald Sommer,et al.  Dynamic Cell Structures , 1994, NIPS.

[17]  Gerald Sommer,et al.  Dynamic Cell Structure Learns Perfectly Topology Preserving Map , 1995, Neural Computation.

[18]  Oliver E. Theel.  An exercise in proving self-stabilization through Lyapunov functions , 2001, Proceedings 21st International Conference on Distributed Computing Systems.

[19]  Xiaoou Li,et al.  Some stability properties of dynamic neural networks , 2001 .

[20]  Munther A. Dahleh,et al.  Computational Complexity of Lyapunov Stability Analysis Problems for a Class of Nonlinear Systems , 1998 .

[21]  K S Narendra,et al.  IDENTIFICATION AND CONTROL OF DYNAMIC SYSTEMS USING NEURAL NETWORKS , 1990 .

[22]  W DijkstraEdsger.  Self-stabilizing systems in spite of distributed control , 1974 .

[23]  Joep L. W. Kessels,et al.  An Exercise in Proving Self-Stabilization with a Variant Function , 1988, Information Processing Letters.

[24]  Teuvo Kohonen,et al.  The self-organizing map , 1990, Neurocomputing.

[25]  W. Brogan.  Modern Control Theory , 1971 .

[26]  Hilbert J. Kappen,et al.  On-line learning processes in artificial neural networks , 1993 .

[27]  Jürgen Rahmel,et al.  On the Role of Topology for Neural Network Interpretation , 1996, ECAI.

[28]  Barbara Hayes-Roth,et al.  Intelligent Control , 1994, Artif. Intell..