“…However, position control of SMA actuators represents a major challenge for practical applications due to their nonlinear hysteretic behavior, producing steady-state errors when conventional controllers are used [18]. To overcome this problem, proportional-integral-derivate (PID) controllers with hysteresis models have been implemented [18,19,20]; for position control of SMA actuators using the generalized Prandtl鈥揑shlinskii inverse model [18], for micro-positioning control of SMA actuators by modeling the hysteresis using NNs [19], and for magnetic SMA actuators by using a radial basis function NN to obtain the Jacobian information of the system in order to adjust the controller parameters [20]. In addition, neural network controllers, previously trained to identify the system were proposed to control SMA actuators [21,22,23,24]; using the inverse of the ANN that replicate the dynamics of the SMA force actuator to implement the controller [21], implementing a model predictive controller based on a functional link ANN to control the linear memory metal actuator displacement [22], and realizing a recurrent neural model predictive, variable structure, controller designed to control a one degree of freedom (1-DOF) rotary manipulator actuated by an SMA wire [23,24].…”