BP neural network tuned PID controller for position tracking of a pneumatic artificial muscle

Although Pneumatic Artificial Muscle (PAM) has a promising future in rehabilitation robots, it's difficult to realize accurate position control due to its highly nonlinear properties.

This paper deals with position control of PAM.

To describe the hysteresis inside PAM, a polynomial based phenomenological function is developed. Based on the phenomenological model for PAM and analysis of pressure dynamics within PAM, an adaptive cascade controller is proposed. Both outer loop and inner loop employ BP Neural Network tuned PID algorithm. The outer loop is to handle high nonlinearities and unmodeled dynamics of PAM, while the inner loop is responsible for nonlinearities caused by pressure dynamics.

Experimental results show high tracking accuracy as compared with a convention PID controller.

The proposed controller is effective in improving performance of PAM and will be implemented in a rehabilitation robot.