This paper developed a model reference control scheme by introducing a PI controller and CMAC neural network (CMACNN) controller for speed control of high precision servo systems. It contemporarily improved the conception mapping algorithm of the CMACNN, which gave a determined expression of the physical memory size and designed a physical memory address function. In the proposed control scheme, the CMAC controller is able to online learn the unknown model dynamics, parameter variation and disturbance of the system. The model reference adaptive control (MRAC) scheme is used to give better solutions with online adaptation. By using a PI controller, the dynamic performance of the system is improved. Thus, it is feasible to preserve favorable model-following characteristics under various conditions. The effectiveness of the proposed control scheme is demonstrated by simulation. It is found that the proposed scheme can reduce the plantpsilas sensitivity to parameter variation and disturbance. High precision performance is obtained when given constant and sine wave disturbance at the same time.