出版社：Japan Society for Fuzzy Theory and Intelligent Informatics
摘要：This paper presents a self-tuning system of PID gain parameters for an inverted pendulum control system using three-layer neural networks. The inverted pendulum system which has one input and two output system is expressed as the plant by the transfer functions, which are used to identify the plant with a neural network based on the back-propagation for temporal sequences and then the system Jacobian of the plant is derived. The system Jacobian of the plant is used in the self-tuning process of the PID controller. The PID parameters are determined so as to minimize the error function, in which another three-layer neural network is used in the tuning process. Experimental results of the angle of the pendulum and the position of the cart which are controlled by the tuned parameteres are compared with simulation results. It is shown that they are good agreement.
关键词：neural networks ; self-tuning ; PID control ; inverted pendulum
