Aiming at the problem of insufficient labeled samples in the process of rolling bearing fault diagnosis, a rolling bearing fault diagnosis model based on semi supervised Laplace score（SSLS） and kernel principal component analysis（KPCA） is proposed by combining with the idea of feature selection and secondary mining. SSLS applies the semi supervised idea to the Laplace score feature selection method, uses a small number of labeled samples and a large number of unlabeled samples, and combines KPCA to excavate fault features for a second time. At the same time, particle swarm optimization-based support vector machine（PSO-SVM） algorithm is used for fault classification. Finally, the model is applied to the process of experimental data analysis. The results show that the model can not only reduce the workload of sample marking, but also maintain a high accuracy in rolling bearing fault classification, which verifies the effectiveness and engineering practicability of the model.