Few-Shot Fault Diagnosis Based on Heterogeneous Information Fusion and Meta Learning

Abstract

Intelligent fault diagnosis algorithms require large amounts of data to train models, and the fusion of heterogeneous information from multiple sensors increases the computational complexity exponentially. To address these problems, a few-shot cross-domain motor fault diagnosis method based on multisensor information fusion and meta learning is proposed. First, a multisensor heterogeneous information fusion framework, named low-pass pyramidal ratio-color symmetric dot pattern (RP-CSDP), is proposed. It enables to achieve the information fusion of a three-axis vibration sensor and three-phase current sensor without increasing the computational burden of the intelligent diagnosis algorithm. Second, RP-CSDP fuses and reconstructs the data from both types of sensors into color images. Based on this, a meta learning database is constructed. The relation network (RN) is improved, and various cross-working conditions and few-shot experiments are set up. Finally, the proposed method is promoted to diagnose motor faults that are not present in the training phase. The results show that the proposed method can be quickly adapted to new tasks without repeating the training network when faced with new working conditions and faulty types with limited training samples.