Since the system dynamic of a voice coil motor (VCM) is difficult to obtain, this paper uses a B-spline neural network to online approximate an unknown nonlinear term in the system dynamics of a VCM by tuning its interior parameters. Meanwhile, a B-spline neural position control (BNPC) system, which is composed of a position controller and a fuzzy compensator, is proposed. A proportional-integral adaptation law is derived to speed up the convergence of tracking error in the sense of the projection algorithm and Lyapunov stability theorem. Finally, the proposed BNPC system is implemented on a 32-b microcontroller. The experimental results show that the proposed BNPC system is robust against payload variations with high accuracy motion response.