Self-tuning PID control of a flexible micro-actuator using neural networks

A neural network approach to online self-tuning control and real time implementation for a flexible microactuator is presented. The control scheme consists of a gain tuning neural network and a variable-gain PID controller. This neural network is trained to reduce the error between the plant output and reference signal to zero. In the process, the neural network learns the optimal gain of the PID controller. The flexible microactuator is made of a bimorph piezoelectric high-polymer material (PVDF). The bimorph piezoelectric microactuator consists of two PVDF films cemented with a metal shim in proper polarity. Numerical and experimental results indicate that the self-tuning PID neural network control system is effective for accurate trajectory tracking