Design of a Switching Control Scheme for Uncertain Objects based on PID-Type FNN and LS_SVMs

摘要

PID control schemes have been widely used for industrial process systems over the past several decades. Recently, by combining traditional PID method with modem intelligent control scheme, various control design methodologies have been proposed such as fuzzy PID, neural PID and PID self-tuning by pattern recognition. However, the serious problem here is that the controller parameters must be suitably adjusted according to the property of the controlled object, which often changes gradually. Many identification methods are introduced to cope with this problem, among which the neural network identification is widely used. Generally a static network cannot adequately approximate a dynamic system and the training speed of dynamic network is very slow while the convergence cannot be guaranteed. Moreover, if the range of system uncertainty is very wide, the control performance becomes quite conservative. In this paper, a kind of objects with the wide range of uncertainty is considered and a novel control scheme with switching structure is proposed for the objects' control. A PID-type fuzzy neural network is designed as the controller and is optimized by offline quantum-behaved particle swarm optimization (QPSO) with chaos strategy and online error back propagation tuning. The least square support vector machines (LSSV'Ms) are introduced to determine the suitable controller parameters by switching and identifying the controlled plant. Finally, the simulation results show the feasibility and validity of the proposed method.