Adaptive neural control of stochastic nonlinear systems with multiple time-varying delays and input saturation

• Published in: Neural computing & applications Vol. 25; no. 3-4; pp. 779 - 791
• Main Authors: Cui, Guozeng, Jiao, Ticao, Wei, Yunliang, Song, Gongfei, Chu, Yuming
• Format: Journal Article
• Language: English
• Published: London Springer London 01.09.2014; Springer
• Subjects: Adaptative systems; Applied sciences; Artificial Intelligence; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Computer science; control theory; systems; Connectionism. Neural networks; Control theory. Systems; Data Mining and Knowledge Discovery; Exact sciences and technology; Image Processing and Computer Vision; Original Article; Probability and Statistics in Computer Science; System theory; Input saturation; Adaptive neural control; Razumikhin lemma; Time-varying delay; Stochastic nonlinear systems; Non linear control; Feedback regulation; Function approximation; Adaptive control; Stochastic system; Time varying system; Uncertain system; Learning algorithm; Capability index; Closed loop; Probabilistic approach; Delay system; Neural network; Non linear system; Recursive algorithm; Backstepping control; Closed feedback; Neurocontrollers; Artificial intelligence; Lyapunov function
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-014-1548-6

This paper investigates the problem of adaptive neural control for a class of strict-feedback stochastic nonlinear systems with multiple time-varying delays, which is subject to input saturation. Via the backstepping technique and the minimal learning parameters algorithm, the problem is solved. Based on the Razumikhin lemma and neural networks’ approximation capability, a new adaptive neural control scheme is developed. The proposed control scheme can ensure that the error variables are semi-globally uniformly ultimately bounded in the sense of four-moment, while all the signals in the closed-loop system are bounded in probability. Two simulation examples are provided to demonstrate the effectiveness of the proposed control approach.