PMCFormer: a lightweight bearing fault diagnosis framework using multiscale partial convolution and pooling agent self-attention
- 21 March 2025
- journal article
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (4) , 046107
Abstract
The collaborative modeling of convolutional neural networks (CNN) and transformer had gained some results in the field of fault diagnosis because of the advantages of transformer in extracting global information and CNN in extracting local features. However, in actual industrial production, it was frequently faced with lots of noise interference and the huge difficulties of limited hardware equipment. To solve this problem, a lightweight and robust fault diagnosis framework called PMCFormer is proposed. Firstly, a multiscale partial convolution module was designed to improve the attention of the model to multiple local receptive fields in the vibration signal, extract local feature information, and greatly reduce the amount of calculation. Secondly, a pooling agent self-attention block was developed to capture the global features of the input signal, enhance the perception of the relationship between local and global signals, and ensure the linear complexity of the computation to avoid tedious operations such as multi-dimensional exponential operations. Three experimental results showed that compared with existing mainstream transformer and CNN fault diagnosis methods, this framework had lightweight and robustness in strong noise environments. Among them, PMCFormer achieved an average accuracy of 94.72% in the fault diagnosis of subway bogie axle box bearings under 0–10 dB noise interference.Keywords
Funding Information
- China Energy Railway Equipment Co., Ltd. (TZKY-21-26)
- Meishan CRRC Brake Science & Technology Co., Ltd. (M21L01550)
This publication has 27 references indexed in Scilit:
- Evolvable graph neural network for system-level incremental fault diagnosis of train transmission systemsMechanical Systems and Signal Processing, 2024
- C-ECAFormer: A new lightweight fault diagnosis framework towards heavy noise and small samplesEngineering Applications of Artificial Intelligence, 2023
- LiConvFormer: A lightweight fault diagnosis framework using separable multiscale convolution and broadcast self-attentionExpert Systems with Applications, 2023
- An improved GNN using dynamic graph embedding mechanism: A novel end-to-end framework for rolling bearing fault diagnosis under variable working conditionsMechanical Systems and Signal Processing, 2023
- Multi-sensor information fusion and coordinate attention-based fault diagnosis method and its interpretability researchEngineering Applications of Artificial Intelligence, 2023
- GTFE-Net: A Gramian Time Frequency Enhancement CNN for bearing fault diagnosisEngineering Applications of Artificial Intelligence, 2023
- Intelligent fault diagnosis of rotating machinery based on continuous wavelet transform-local binary convolutional neural networkKnowledge-Based Systems, 2021
- Fault diagnosis of rotating machines based on the EMD manifoldMechanical Systems and Signal Processing, 2020
- Bearing vibration data collected under time-varying rotational speed conditionsData in Brief, 2018
- Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark studyMechanical Systems and Signal Processing, 2015