Control of Pneumatic Servo System Based on Neural Network PID Algorithm

• Published in: Applied Mechanics and Materials Vol. 457-458; no. Frontiers of Mechanical Engineering and Materials Engineering II; pp. 1344 - 1347
• Main Author: Gong, Qin Hui
• Format: Journal Article
• Language: English
• Published: Zurich Trans Tech Publications Ltd 01.10.2013
• Subjects: Algorithms; Control systems; Disturbances; Neural networks; Pneumatics; Proportional integral derivative; Servocontrol; Servomechanisms; Robustness; Pneumatic Servo System; Single Neuron Adaptive PID Controller; Algorithm (GA); Neural Network PID Control
• ISBN: 9783037859247; 3037859245
• ISSN: 1660-9336; 1662-7482; 1662-7482
• DOI: 10.4028/www.scientific.net/AMM.457-458.1344

The pneumatic servo system has characteristics of nonlinear, time-variant, large parameter variations and external disturbances, which is difficult to control. The conventional PID control is not suitable for the variable parameters of the controlled object, external disturbances. In this paper, the neural network controller combined with PID control is used to control the pneumatic servo system, and the structure diagram, algorithm and learning rule of the single neuron adaptive PID controller are put forward. The results show that,compared with the traditional PID control, the controller has significantly improved the control performance of system, Namely, the system has faster computational speed (real-time), stronger robustness and better adaptive ability.