Neural networks for feedback feedforward nonlinear control systems

This paper deals with the problem of designing feedback feedforward control strategies to drive the state of a dynamic system (in general, nonlinear) so as to track any desired trajectory joining the points of given compact sets, while minimizing a certain cost function (in general, nonquadratic). Due to the generality of the problem, conventional methods are difficult to apply. Thus, an approximate solution is sought by constraining control strategies to take on the structure of multilayer feedforward neural networks. After discussing the approximation properties of neural control strategies, a particular neural architecture is presented, which is based on what has been called the "linear-structure preserving principle". The original functional problem is then reduced to a nonlinear programming one, and backpropagation is applied to derive the optimal values of the synaptic weights. Recursive equations to compute the gradient components are presented, which generalize the classical adjoint system equations of N-stage optimal control theory. Simulation results related to nonlinear nonquadratic problems show the effectiveness of the proposed method.

[1]  Thomas Parisini,et al.  Backpropagation for N-stage optimal control problems , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[2]  Andrew P. Sage,et al.  Closed Loop Optimization of Fixed Configuration Systems , 1966 .

[3]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

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

[5]  Thomas Parisini,et al.  Multi-Layer Neural Networks for the Optimal Control of Nonlinear Dynamic Systems , 1991 .

[6]  Derrick H. Nguyen,et al.  Neural networks for self-learning control systems , 1990 .

[7]  T. Hanaoka.  NONLINEAR CONTROL SYSTEM DESIGN BASED ON NEWLY DEVELOPED DYNAMIC PROGRAMMING ALGORITHM , 1991 .

[8]  Tom Tollenaere,et al.  SuperSAB: Fast adaptive back propagation with good scaling properties , 1990, Neural Networks.

[9]  Y. Ho,et al.  Team decision theory and information structures in optimal control problems--Part II , 1972 .

[10]  Robert Hecht-Nielsen,et al.  Theory of the backpropagation neural network , 1989, International 1989 Joint Conference on Neural Networks.

[11]  Andrew R. Barron,et al.  Universal approximation bounds for superpositions of a sigmoidal function , 1993, IEEE Trans. Inf. Theory.

[12]  P. Makila,et al.  Computational methods for parametric LQ problems--A survey , 1987 .

[13]  M. Aicardi,et al.  On the existence of stationary optimal receding-horizon strategies for dynamic teams with common past information structures , 1992 .

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

[15]  G. Siouris,et al.  Optimum systems control , 1979, Proceedings of the IEEE.

[16]  M. Athans,et al.  The design of suboptimal linear time-varying systems , 1968 .