In order to improve the accuracy of wear debris intelligent recognition,a support vector machine(SVM) recognition model based on improved particle swarm optimization(PSO) algorithm is proposed on the basis of traditional SVM and PSO.The penalty parameter and kernel function parameters of the recognition model can be best optimized at the same time,so that selfadaptive SVM recognition model with optimal parameters was established.The wear debris in the lubricating oil was recognized by using the proposed recognition model.The results show that the model recognition accuracy rate is as high as 98%,which is significantly higher than the BP neural network model.