Adaptive control of dynamic systems by back propagation networks

• Published in: Neural networks Vol. 6; no. 4; pp. 517 - 524
• Main Authors: Schiffmann, Wolfram H., Geffers, H. Willi
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 1993; Elsevier Science
• Subjects: Applied sciences; Electric, optical and optoelectronic circuits; Electronics; Error back propagation; Exact sciences and technology; Generalized delta-rule; Global and local learning rate adaptation; Interactive and autonomous learning; Neural networks; Qualitative knowledge; Self-tuning; Error back propagation; Interactive and autonomous learning; Qualitative knowledge; Self-tuning; Generalized delta-rule; Global and local learning rate adaptation; Learning; Neural network; Dynamical system; Simulation; Algorithm; Adaptive control
• ISSN: 0893-6080; 1879-2782
• DOI: 10.1016/S0893-6080(05)80055-3

Artificial neural networks—especially those using the error back propagation algorithm—are capable of learning to control an unknown plant by autonomously extracting the necessary information from the plant. Following the approach of Psaltis, Sideris, and Yamamura, and Saerens and Soquet, a control architecture based on error back propagation has been developed and trained to control a third order linear and time invariant plant with dead-time Simulation results show that the network is able to invert the plant's behaviour and characteristics, thus learning to control the plant accurately. The time to reach the desired outputs of the plant decreases while learning. It is accelerated by local adaptation of the learning rate.