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.

Tracking control of shape memory alloy (SMA) actuators is essential in many applications such as vibration controls. Due to the hysteresis, an inherent nonlinear phenomenon associated with SMAs, open-loop control design has proven inadequate for tracking control of these actuators. Aimed at eliminating the position sensor to reduce cost of an SMA actuator system, in this paper, a neural network open loop controller is proposed for tracking control of an SMA actuator. A test stand, including a titanium-nickel (TiNi, or Nitinol) SMA wire actuator, a position sensor, bias springs, and a programmable current amplifier, is used to generate training data and to verify the neural networks open loop controller. A digital data acquisition and real-time control system was used to record experimental data and to implement the control strategy. Based on the training data obtained from the test stand, two neural networks are used to respectively model the forward and inverse hysteresis relations between the applied voltage and the displacement of the SMA wire actuator. To control the SMA actuator without using a position sensor, the neural network inverse model is used as a feedforward controller. The experimental results demonstrate the effectiveness of the neural network open loop controller for tracking control of the SMA wire actuator.

No abstract

No abstract

No abstract