Evolutionary control of discrete-time nonlinear system using PIPE algorithm
Yuehui Chen, Shigeyasu Kawaji · 2003
An indispensable ability for intelligent control is to comprehend and learn about plants, disturbances, environment, and operating conditions. In the paper, the probabilistic incremental probability evolution (PIPE) algorithm, with its self-organizing and learning ability, is used as a promising tool for such purposes. In order to control discrete-time nonlinear systems, the input-output data of the system is first approximated by the individual structure of PIPE (PIPE emulator). Secondly, a self-tuning neuro-PID controller of a nonlinear system is designed, in which the control error of the open-loop PIPE controller is compensated by the self-tuning PID controller. Simulation results show the feasibility and effectiveness of the proposed method.