Mechanical fault diagnosis is an important method to accurately identify the health condition of mechanical equipment and ensure its safe operation. Fault diagnosis based on transfer learning usually refers to the diagnostic method verified in simulation or laboratory that can be generalized to actual operating equipment. The implementation methods of transfer learning include feature-based transfer, model-based transfer, etc., through enhancement, fine-tuning, and other technical techniques.

This topic introduces the principle of transfer learning, summarizes the research and application of transfer learning in the field of fault diagnosis, discusses the shortcomings of transfer learning in the field of fault diagnosis, and discusses the future research direction of transfer learning in the field of fault diagnosis.

Make a new submission to the Topic: Mechanical Fault Diagnosis Based on Transfer Learning section.

List of Publication

     
2026
Diagnosis of Multiple Bearing Faults in BLDC Motors Using ReliefF Feature Selection and Random Forest Classifier
Meiyanto Eko Sulistyo, Didik Djoko Susilo*, Muhammad Nizam, Ubaidillah, and Felly Anta

Assessment of Braking Dynamics of Passenger Cars Operating in the Mekong Delta Region of Vietnam
Phat Khau Tan and Danh Nguyen Thanh*

2025
Algorithms and Software for Computing Inverse Distribution Functions in Power Equipment Based on Digital Twins
Agamirov L. Vladimirovich, Oparin M. Vitalievich, Chechetkin D. Andreevich, Kislitsyn M. Andreevich, and Muhammad Maaz Shaikh*

2024
Misalignment Diagnostic System for Linear Motion Robots Using Long Short-Term Memory
Chanwoo Moon