Title :
Study of PID Neural Network Control for Nonlinear System
Author :
Zhang, Ming-Guang ; Qiang, Ming-hui
Author_Institution :
Sch. of Electr. & Inf. Eng., Lanzhou Univ. of Technol.
Abstract :
The PID (proportional-integral-derivative) neural network (PIDNN) controller for nonlinear system is proposed in this paper, which is different from the hybrid controllers of the PID and the neural networks. The PID neural network is a new kind of multilayer neural network in which the neurons have proportional, integral and derivative functions. And the controller is optimized by the learning processing of PIDNN. The principle of PIDNN is discussed and the learning method based on back-propagation-algorithm is given. The simulation results show that the proposed controller has the adaptability, strong robustness and satisfactory control performance in the nonlinear and time varying system
Keywords :
backpropagation; neurocontrollers; nonlinear control systems; three-term control; PID neural network control; back-propagation-algorithm; learning processing; multilayer neural network; nonlinear system; proportional-integral-derivative; time varying system; Control systems; Learning systems; Multi-layer neural network; Neural networks; Neurons; Nonlinear control systems; Nonlinear systems; Pi control; Proportional control; Three-term control;
Conference_Titel :
Signal Processing, 2006 8th International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-9736-3
Electronic_ISBN :
0-7803-9736-3
DOI :
10.1109/ICOSP.2006.345787
