Mixmamba-fewshot: mamba and attention mixer-based method with few-shot learning for bearing fault diagnosis

Abstract

In recent years, artificial intelligence, particularly machine learning and deep learning has ushered in a new era of technological advancements leading to significant progress across various domains. In the field of computer vision, deep learning has made substantial contributions, impacting everything from daily life to production and industry. When machines, rotating devices, and engines operate, bearing failures are inevitable. Our task is to accurately detect or diagnose these failures. However, a key challenge lies in the lack of sufficient data on bearing faults to train a model capable of delivering highly accurate diagnostic results. To address this issue, in this paper, we propose a new approach named MixMamba-Fewshot, leveraging few-shot learning and using a feature extraction module that integrates an attention mechanism called the Priority Attention Mixer and Mamba - a novel theory that has recently gained considerable attention within the research community. Using Mamba for vision-based feature extraction in classification tasks, particularly in few-shot learning is an innovative approach, and it has shown promising results in improving the accuracy of bearing fault diagnosis. When we tested our model on the datasets provided by Case Western Reserve University (CWRU) and the Paderborn University (PU) Bearing Dataset, we compared it with previously published models. Our proposed approach demonstrated a significant improvement in diagnostic accuracy and clearly outperformed existing approaches. Our code will be available at: https://github.com/linhthan216/MixMamba-Fewshot.