The piston performance affects the performance of the Motorcycle. In order to forecast the piston performance effectively, the performance forecast model based on BP neural network is presented. According to the characteristics of piston performance, the training samples are made up of the orthogonal experimental data, which are utilized to ensure higher generalization of BP neural network. And then the trained BP neural network is used to forecast test example. At the same time, the value of test samples is compared with the output of BP network model results. The results show that the output precision of BP neural network is high, and using the BP neural network to forecast the piston performance is practicable and effective.