Precision tracking control of shape memory alloy actuators using neural networks and a sliding-mode based robust controller

This paper presents a new approach to controlling shape memory alloy (SMA) actuators with hysteresis compensation by using a neural network feedforward controller and a sliding-mode based robust feedback controller. SMA actuators exhibit severe hysteresis, which is often responsible for position inaccuracy in a regulation or tracking system and may even cause instability in some cases. A single SMA wire actuator is used in this research. A testing system, which includes a wire stand, a linear bearing, a bias spring, a position sensor, a programmable current amplifier and a PC-based digital data acquisition and real-time control system, is used to test the SMA wire actuator in both open-and closed-loop fashions. The proposed control includes two major parts: a feedforward neural network controller, which is used to cancel or reduce the hysteresis, and a sliding-mode based robust feedback controller, which is employed to compensate uncertainties such as the error in hysteresis cancellation and ensures the system's stability. The feedforward neural network controller is designed based on the experimental results of open-loop testing of the wire actuator. With the proposed control, tests of the SMA actuator following sinusoidal commands with different frequencies and magnitudes are conducted. The experiments show that the actual displacement of the SMA actuator with the proposed control closely followed that of the desired sinusoidal command.