Using Accelerated Evolutionary Programming in Self-turning Control for Uncertainty Systems
Ping Wang, Qingjie Zhao, Ruqing Yang · 2006
This paper proposes a self-turning control scheme based on an artificial neural network (ANN) with accelerated evolutionary programming algorithm. The neural network is used to model the uncertainty process, from which the teacher signals are produced for online regulating the parameters of the controller. The accelerated evolutionary programming is used to train the neural network. The experiment results show that the proposed control method can obviously improve the dynamic performance of the system with uncertainty