• Home
  • Search
  • A Novel Multi-Task Self-Supervised Transfer Learning Framework for Cross-Machine Rolling Bearing Fault Diagnosis
  • Cite Icon11
  • https://doi.org/10.3390/electronics13234622Copy DOI Icon

A Novel Multi-Task Self-Supervised Transfer Learning Framework for Cross-Machine Rolling Bearing Fault Diagnosis

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

In recent years, intelligent methods based on transfer learning have achieved significant research results in the field of rolling bearing fault diagnosis. However, most studies focus on the transfer diagnosis scenario under different working conditions of the same machine. The transfer fault diagnosis methods used for different machines have problems such as low recognition accuracy and unstable performance. Therefore, a novel multi-task self-supervised transfer learning framework (MTSTLF) is proposed for cross-machine rolling bearing fault diagnosis. The proposed method is trained using a multi-task learning paradigm, which includes three self-supervised learning tasks and one fault diagnosis task. First, three different scales of masking methods are designed to generate masked vibration data based on the periodicity and intrinsic information of the rolling bearing vibration signals. Through self-supervised learning, the attention to the intrinsic features of data in different health conditions is enhanced, thereby improving the model’s feature expression capability. Secondly, a multi-perspective feature transfer method is proposed for completing cross-machine fault diagnosis tasks. By integrating two types of metrics, probability distribution and geometric similarity, the method focuses on transferable fault diagnosis knowledge from different perspectives, thereby enhancing the transfer learning ability and accomplishing cross-machine fault diagnosis of rolling bearings. Two experimental cases are carried out to evaluate the effectiveness of the proposed method. Results suggest that the proposed method is effective for cross-machine rolling bearing fault diagnosis.

Similar Papers
  • Research Article
  • Citations33

Initial Fault Diagnosis of Rolling Bearing Based on Second-Order Cyclic Autocorrelation and DCAE Combined With Transfer Learning

  • Jan 01, 2022
  • IEEE Transactions on Instrumentation and Measurement
  • Huaitao Shi +1
  • Research Article

Self-Supervised and Multi-Task Learning Framework for Rapeseed Above-Ground Biomass Estimation

  • Dec 04, 2025
  • Agriculture
  • Pengfei Hao +5
  • Research Article
  • Citations140

Fault Feature Selection and Diagnosis of Rolling Bearings Based on EEMD and Optimized Elman_AdaBoost Algorithm

  • Jun 15, 2018
  • IEEE Sensors Journal
  • Qiang Fu +4
  • Research Article
  • Citations19

Rolling bearing transfer fault diagnosis method based on adversarial variational autoencoder network

  • Jul 27, 2021
  • Measurement Science and Technology
  • Yisheng Zou +4
  • Research Article
  • Citations18

Fault diagnosis of rolling bearing under time-varying speed conditions based on EfficientNetv2

  • Mar 28, 2022
  • Measurement Science and Technology
  • Haoyang Qu +4
  • Research Article

Lightweight Self-Supervised Hybrid Learning for Generalizable and Real-Time Fault Diagnosis in Photovoltaic Systems

  • Feb 25, 2026
  • Algorithms
  • Ghalia Nassreddine +4
  • PDF
  • Research Article
  • Citations28

Deep Residual Network Combined with Transfer Learning Based Fault Diagnosis for Rolling Bearing

  • Aug 03, 2022
  • Applied Sciences
  • Jianmin Zhou +2
  • Research Article
  • Citations11

An unsupervised transfer learning approach for rolling bearing fault diagnosis based on dual pseudo-label screening

  • Nov 08, 2023
  • Structural Health Monitoring
  • Chunran Huo +5
  • Research Article
  • Citations3

Time varying filter empirical mode decomposition and MobileNet-V3 algorithms for fault diagnosis of rolling bearing with efficient channel attention mechanism

  • Feb 09, 2025
  • Journal of Vibration and Control
  • Wentao Dong +3
  • Research Article
  • Citations122

Fault diagnosis for rolling bearing based on VMD-FRFT

  • Jan 28, 2020
  • Measurement
  • Xin Li +3
  • PDF
  • Research Article
  • Citations27

Fault Feature Extraction and Diagnosis of Rolling Bearings Based on Enhanced Complementary Empirical Mode Decomposition with Adaptive Noise and Statistical Time-Domain Features.

  • Sep 19, 2019
  • Sensors
  • Liwei Zhan +5
  • Research Article
  • Citations6

A novel compound data classification method and its application in fault diagnosis of rolling bearings

  • Mar 13, 2017
  • International Journal of Intelligent Computing and Cybernetics
  • Anxin Sun +1
  • Research Article
  • Citations3

A clustering multi-stage training transfer learning framework for cross simulation domain and experimental domain fault diagnosis

  • Mar 01, 2024
  • Measurement Science and Technology
  • Shubo Yu +3
  • Research Article
  • Citations1

Digital twins enable domain adaptive rolling bearing fault diagnosis

  • Sep 19, 2025
  • Engineering Research Express
  • Hong Qian +3
  • PDF
  • Conference Article
  • Citations238

Self-supervised Learning for Large-scale Item Recommendations

  • Oct 26, 2021
  • Tiansheng Yao +10
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.