On the basis of LuGer friction model, an integrated sliding-mode control strategy is proposed to deal with servo system nonlinear and uncertain factors effectively. The control strategy includes two parts. One is nominal model without considering disturb and uncertain, the other is real model including disturb and uncertain. To one part, choose reasonable sliding surface and design controller law. To another part, PTSC algorithm and NNC algorithm combines together to optimize RBF neural network in order to acquire upper bound of uncertain. Simulation and experiment results show that proposed control strategy better servo system performance.