Decoupling control of bearingless brushless DC motor using particle swarm optimized neural network inverse system
Tao Tao, Lianghao Hua
Abstract
Neural network inverse system decoupling control can effectively solve the nonlinear strong coupling problem of bearingless brushless DC motor, but it has the problem of slow convergence and easy to fall into local extreme value. An Improved Particle Swarm Optimization (IPSO) algorithm has been employed to optimize the initial weights of the BP neural network inverse system. Comparisons between traditional inverse system decoupling control and the proposed method through simulations were conducted to confirm the efficacy and superiority of the proposed decoupling strategy. Furthermore, experiment research indicates that effective decoupling control can be achieved for both speed and radial displacement, as well as between the x and y-axis radial displacements, showcasing the good dynamic decoupling performance and stability of the proposed decoupling control strategy.