IGWO-FNN Based Position Control for Stepper Motor

The traditional stochastic descent based gradient Fuzzy Neural Networks (FNN) are prone to falling into local optimal solutions when used to position control of stepper motor. To improve the performance of position control algorithm based on FNN, this article proposes a novel FNN to achieve the position control of stepper motor. In the proposed FNN, an Improved Grey Wolf Optimization (IGWO) algorithm is devised for adjusting the weights of FNN. The Logistic-tent chaotic mapping is used in population initialization of the IGWO to improve the uniformity of population distribution. This method enhances the authority of \(\alpha\) wolves in prey detection, making the algorithm more effective in finding the optimal solution. Compared with position control methods based on traditional FNN, the first position tracking time of stepper motors is reduced by 11.7%, and the fluctuation range of position tracking is reduced by 68%. In the second position tracking, the fluctuation range is reduced by 44%. Simulink simulation experiments showed that the proposed control scheme could accurately and stably track the position of stepper motor.