No abstract

In recent years, continual learning for class increments has attracted much attention. Continual Learning Classification Method (CLCM) based on artificial immune system can identify unknown faults during testing. However, CLCM still has the problem of excessive running consumption. Therefore, it is crucial to improve the efficiency of the immune algorithm and take advantage of its continual learning mechanism in the field of fault diagnosis. In this paper, a continual learning fault diagnosis method based on sparse grid and artificial immune system (SGCM) is proposed, which inspired by grid-based technique and continual learning classification method based on artificial immune system. Firstly, a new cell generation strategy is proposed to reduce the time complexity and improve the diagnosis efficiency, therefore, the problem of dimension explosion can be avoided. Besides, memory cells coding capabilities of SGCM rises the utilization rate of cells so as to simplify the calculation of affinity. At the same time, the conceived cell backtracking strategy enhances the continual learning ability of the algorithm so that new fault types can be quickly identified though the existing learning results. Ultimately, the model adaptive adjustment method inspired by single-layer feed forward neural network improves the generalization power and the accuracy of classification. We conduct experiments on well-known datasets from UCI repository to assess the performance of SGCM. To evaluate fault diagnosis performance of SGCM, experiments on reciprocating compressor experimental dataset and XJTU-SY rolling element bearing datasets were performed. The results show that SGCM is a fast fault diagnosis method with low time complexity and continual learning ability.