An improved nondominate sorting genetic algorithm-II (NSGA-II) is used to optimize the intake and exhaust system of a single cylinder gasoline engine, whose torque at middle range speed was decreased a lot after a catalyst added. First a full GT-power model was set up and verified based on experiment data. Then the intake and exhaust system was selected as the optimization variables, the effects of the diameters and lengths of intake/exhause pipe on the engine performance were investigated individually. Finally an improved nondominate sorting genetic algorithm-II (NSGA-II) is used to solve the multi-objective optimization problem. The results show that the diameters and lengths of intake/exhause pipe have different range and degree of influence on the engine torque. It is different to satisfy the multi-objectives optimization simultaneity by adjusting those variables separately. The improved NSGA-II, with an elitist preserve strategy and duplicates removing algorithm added, can get the Pareto solution set effectively and satisfy the multi-objective optimization.