• Home
  • Search
  • Multi-dataset dynamic adaptive collaboration: a novel transfer learning framework for cross-machine fault diagnosis
  • https://doi.org/10.1088/1361-6501/ae6466Copy DOI Icon

Multi-dataset dynamic adaptive collaboration: a novel transfer learning framework for cross-machine fault diagnosis

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

Abstract Most existing methods for domain adaptation and generalization in fault diagnosis only target the transfer from one source domain dataset to another target one. Moreover, they often ignore the dynamic shifts in marginal and conditional distributions across diverse training datasets during model training. These factors limit the performance and generalization capability of current transfer learning models in the fault diagnosis practice. Therefore, to extract the domain-invariant features across multiple fault diagnosis datasets and get the effective distribution discrepancy metric between source and target domains, a multi-dataset dynamic adaptive collaborative network (MDACN) is proposed in this paper. It designs a data consistency preprocessing scheme based on amplitude and frequency normalization, and proposes an improved distribution discrepancy metric along with a dynamic adaptive alignment strategy to guide the model in aligning features from multiple datasets within a unified feature space. Under the unlabeled target domain samples, seven cross-machine fault diagnosis tasks were constructed using three publicly available bearing datasets and one proprietary bearing dataset. Experimental results demonstrate that the proposed MDACN can more effectively exploit the rich information in multiple datasets compared to other representative domain adaptation methods, thereby achieving superior performance in transfer fault diagnosis.

Similar Papers
  • Research Article
  • Citations263

A New Deep Transfer Learning Method for Bearing Fault Diagnosis Under Different Working Conditions

  • Aug 01, 2020
  • IEEE Sensors Journal
  • Jun Zhu +2
  • Research Article
  • Citations111

Targeted transfer learning through distribution barycenter medium for intelligent fault diagnosis of machines with data decentralization

  • Dec 22, 2023
  • Expert Systems with Applications
  • Bin Yang +3
  • Research Article
  • Citations27

A New Multisource Domain Bearing Fault Diagnosis Method With Adaptive Dual-Domain Obfuscation Weighting Strategy

  • Jan 01, 2023
  • IEEE Transactions on Instrumentation and Measurement
  • Changqing Shen +5
  • Research Article
  • Citations9

A new indirect transfer fault diagnosis method based on feature separation

  • Jun 22, 2024
  • Knowledge-Based Systems
  • Chenhui Qian +5
  • Research Article
  • Citations358

Deep discriminative transfer learning network for cross-machine fault diagnosis

  • Oct 25, 2022
  • Mechanical Systems and Signal Processing
  • Quan Qian +4
  • Research Article
  • Citations4

Structure information preserving domain adaptation network for fault diagnosis of Sucker Rod Pumping systems.

  • Aug 01, 2025
  • Neural networks : the official journal of the International Neural Network Society
  • Xiaohua Gu +6
  • Conference Article
  • Citations11

Deep Transfer Learning Network for Fault Diagnosis Under Variable Working Conditions

  • Dec 17, 2021
  • Yiyao An +4
  • Dissertation

Novel deep cross-domain framework for fault diagnosis or rotary machinery in prognostics and health management

  • May 01, 2021
  • Behnoush Rezaeianjouybari
  • PDF
  • Research Article
  • Citations80

Triplet Loss Guided Adversarial Domain Adaptation for Bearing Fault Diagnosis.

  • Jan 06, 2020
  • Sensors
  • Xiaodong Wang +1
  • Research Article
  • Citations3

An integrating multidimensional features method based on multi-view learning for intelligent fault diagnosis of rolling bearings

  • Apr 18, 2025
  • Engineering Computations
  • Min Wang +5
  • Research Article

An attention guided joint distribution domain adaptation method for fault diagnosis

  • Jun 26, 2025
  • Journal of Vibration and Control
  • Songli Tang +1
  • Research Article
  • Citations30

Optimal Transport Based Deep Domain Adaptation Approach for Fault Diagnosis of Rotating Machine

  • Jan 01, 2021
  • IEEE Transactions on Instrumentation and Measurement
  • Zhao-Hua Liu +4
  • Research Article
  • Citations99

A Stacked Auto-Encoder Based Partial Adversarial Domain Adaptation Model for Intelligent Fault Diagnosis of Rotating Machines

  • Dec 15, 2020
  • IEEE Transactions on Industrial Informatics
  • Zhao-Hua Liu +5
  • PDF
  • Research Article
  • Citations19

A Deep Transfer Learning Method for Bearing Fault Diagnosis Based on Domain Separation and Adversarial Learning

  • Jan 01, 2021
  • Shock and Vibration
  • Shoubing Xiang +4
  • Research Article
  • Citations2

Residual Adversarial Subdomain Adaptation Network Based on Wasserstein Metrics for Intelligent Fault Diagnosis of Bearings

  • Oct 07, 2024
  • Applied Sciences
  • Haichao Cai +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.