Modeling SMA actuated systems based on BoucWen hysteresis model and feedforward neural network

Despite the fact that shape-memory alloy (SMA) has several mechanical advantages as it continues being used as an actuator in engineering applications, using it still remains as a challenge since it shows both non-linear and hysteretic behavior. To improve the efficiency of SMA application, it is required to do research not only on modeling it, but also on control hysteresis behavior of these materials which are the fundamentals of several research opportunities in this area. Having considered these requirements, we have introduced a mathematical model to describe the hysteresis behavior of a mechanical system attached to SMA wire actuators using Bouc-Wen hysteresis model and feed-forward neural network. Due to inability of linear mass-spring-damper equations of classic Bouc-wen model to explain the hysteresis behavior of SMA actuators, in this paper we have applied changes in the mentioned equations of classic Bouc-Wen model to describe hysteresis loops of model. We also have used flexibility of the neural network systems to describe Bouc-Wen output in the main equation. Parameters of the developed model have been trained for a real mechanical system using simulation data after selecting proper configuration for the selected neural network. Finally, we have checked the accuracy of our model by applying two different series of validation data. The result shows the acceptable accuracy of the developed model.