App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 7

Source-free adaptive fault diagnosis based on pseudo-label optimization and feature discrimination enhancement

Qiu Xiaohong1,2
Mao Jianwen1
1. School of Software Engineering, Jiangxi University of Science and Technology, Nanchang 330013, China
2. Jiangxi University of Science and Technology, Virtual Digital Engineering and Cultural Communication Key Laboratory of Nanchang, Nanchang 330013, China
DOI: 10.19734/j.issn.1001-3695.2025.11.0460

Abstract

To address the domain shift problem caused by missing target domain labels in bearing fault diagnosis, as well as the defects of existing source-free adaptation methods—such as pseudo-label noise interference and insufficient discriminative power—this paper propose a novel source-free domain adaptation method for pseudo-label optimization and feature discrimination enhancement. This method does not require source domain data during the model adaptation stage. Specifically, during the model adaptation stage, the framework first generates initial pseudo-labels and confidence levels via a pre-trained source model and a voting mechanism. Then, the method employs graph propagation to correct the pseudo-labels, yielding more reliable soft labels. Furthermore,this paper utilize information maximization and contrastive learning to extract discriminative features, thereby enhancing intra-class compactness and inter-class separability. Finally, a dynamic curriculum adaptation module guides the model to prioritize learning from reliable samples, effectively suppressing noise interference. Extensive experiments on the JNU and PU public bearing fault diagnosis datasets demonstrate that the proposed method outperforms the suboptimal methods SFAD and SF-CA, improving average fault diagnosis accuracy by 1.61% and 5.87%, respectively. Consequently,this approach achieves higher diagnostic precision and stronger cross-domain robustness, providing a feasible solution for equipment fault diagnosis in actual industrial scenarios under unlabeled conditions.

Foundation Support

国家自然科学基金资助项目(62341307)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.11.0460
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 7

Publish History

[2026-03-25] Accepted Paper

Cite This Article

邱晓红, 毛建文. 伪标签优化与特征判别增强的无源域自适应故障诊断 [J]. 计算机应用研究, 2026, 43 (7). (2026-03-27). https://doi.org/10.19734/j.issn.1001-3695.2025.11.0460. (Qiu Xiaohong, Mao Jianwen. Source-free adaptive fault diagnosis based on pseudo-label optimization and feature discrimination enhancement [J]. Application Research of Computers, 2026, 43 (7). (2026-03-27). https://doi.org/10.19734/j.issn.1001-3695.2025.11.0460. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)