Few-shot intelligent fault diagnosis based on an improved meta-relation network

In recent decades, fault diagnosis methods based on machine learning and deep learning have achieved excellent results in fault diagnosis and are characterized by powerful automatic feature extraction and accurate identification capabilities. In many real-world scenarios, gathering enough samples of each fault type can be time-consuming and difficult. The scarcity of samples may significantly degrade the performance of these learning-based methods, making it extremely challenging to train a robust fault diagnosis classifier. In this paper, a few-shot fault diagnosis method based on the improved meta-relation network (IMRN) model is proposed to overcome the challenge of implementing fault diagnosis with limited data samples. First, a multiscale feature encoder module that utilizes two one-dimensional convolutional neural networks with different kernel sizes is used to automatically extract signal features from the original support dataset and query dataset. Then, a metric meta-learner module is designed to obtain relation scores between support samples and query samples. Finally, the feature vector output by the feature encoder module is input to the metric meta-learner module to determine the category of query samples by comparing the relation scores between the query dataset and support dataset, thus implementing the classification of fault categories. Experiments are conducted on three public datasets (TE, PU and CWRU), and the experimental results show that the proposed method outperforms other benchmark few-shot learning methods in terms of accuracy and exhibits remarkable robustness and adaptability in fault diagnosis.