Adaptive integral position control using RBF neural networks for brushless DC linear motor drive

The paper presents an adaptive integral position controller usingRBF (Radial Basis Function) neural networks (NNs) for a brushless DC linear motor. By assuming that the upper bounds of the nonlinear friction and force ripple, an RBF NN is used for approximating the friction, the force ripple and the load; an adaptive backstepping control with integral action is then proposed to achieve position tracking of the linear motor. The parameter adjustment rules for the overall controller are derived via the Lyapunov stability theory. Based on the LaSalle-Yoshizawa lemma, the proposed controller is proven asymptotically stable. Experimental results are conducted to show the efficacy and usefulness of the proposed control method.