The use of a self-contained dual neural network architecture for the solution of nonlinear optimal control problems is investigated in this study. The network structure solves the dynamic programming equations in stages and at the convergence, one network provides the optimal control and the second network provides a fault tolerance to the control system. We detail the steps in design and solve a linearized and a nonlinear, unstable, four-dimensional inverted pendulum on a cart problem. Numerical results are presented and compared with linearized optimal control. Unlike the previously published neural network solutions, this methodology does not need any external training, solves the nonlinear problem directly and provides a feedback control.
S. N. Balakrishnan and V. Biega, "A Dual Neural Network Architecture for Linear and Nonlinear Control of Inverted Pendulum on a Cart," Proceedings of the 1996 IEEE International Conference on Control Applications, 1996, Institute of Electrical and Electronics Engineers (IEEE), Jan 1996.
The definitive version is available at http://dx.doi.org/10.1109/CCA.1996.558932
1996 IEEE International Conference on Control Applications, 1996
Mechanical and Aerospace Engineering
Keywords and Phrases
Dual Neural Network Architecture; Dynamic Programming; Dynamic Programming Equations; Fault Tolerance; Feedback; Inverted Pendulum; Linear Control; Linear Systems; Neurocontrollers; Nonlinear Control; Nonlinear Control Systems; Optimal Control; Optimal Control Problems
Article - Conference proceedings
© 1996 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.