For the problem of nonlinearity and time-delay of traditional hydraulic servo system,a nonlinear predictive control system for hydraulic servo based on multi-objective particle swarm optimization and quasi-circular mapping (QCMPSO-NPC) was proposed．High dimensional target space was mapped to a 2-dimensional coordinate plot by the quasi-circular mapping in order to monitor evolutionary status of the particle population.In order to balance the convergence and diversity of the profiles,area-dominant and individual distance were used to manage the profiles,and the globally optimal particles were selected adaptively according to the population evolutionary state.The improved algorithm was applied to a hydraulic servo system and the set value could be tracked accurately by the system.The simulation experiment results show that:the convergence and diversity of the solution set can be ensured by using 〖JP2〗QCMPSO-NPC algorithm,it has the fastest output response and the least error,the position tracking performance is better than PSO-NPC algorithm and GPC algorithm.The effectiveness and feasibility of the hydraulic servo control system based on QCMPSO-NPC algorithm are verified.