Review of Data-Driven Fault Diagnosis for Rotating Machinery
Main Article Content
Keywords
fault diagnosis, data-driven, rotating machinery, deep learning
Abstract
With the acceleration of industrialization in modern society, rotating machinery has become an indispensable and important part of various industries. Under long-term high-speed, heavy-load and variable working conditions, key components such as rotors, bearings and gearboxes are prone to failure. Traditional diagnostic methods based on models and experience are difficult to adapt to complex working conditions and multi-source data processing needs. With the advantages of no need for precise physical models, strong adaptability and high diagnostic accuracy, the data-driven method has become the mainstream technology of intelligent fault diagnosis of rotating machinery. This paper reviews the common fault types of rotating machinery, summarizes the research progress of the core technology of data-driven fault diagnosis, discusses its application status in typical industrial equipment, and discusses future research directions, so as to provide references for the research and engineering implementation of intelligent operation and maintenance technology of rotating machinery.
References
- [1]Chen, Y., Cheng, L., & Yang, B. (2026). Research on a data-driven gas-path fault diagnosis method for turboshaft engines. Journal of Chongqing University of Technology (Natural Science), 40(1), 185–192.
- [2]Rong, G., Zhang, Y., Tang, C., et al. (2025). Research on simulation data-driven fault diagnosis technology for unmanned aerial vehicles. Aerospace Defense, 8(6), 73–84.
- [3]Zhang, Y. (2025). Research on an intelligent fault diagnosis mechanism for mine ventilation based on machine learning. Journal of Safety Science and Technology, 21(11), 159–168.
- [4]Li, J., Liu, Y., Wang, H., et al. (2025). A data-driven method for early fault diagnosis of rolling bearings. Cyber Security and Data Governance, 44(Suppl. 1), 341–346.
- [5]Sun, D. (2025). Research on data-driven fault feature analysis and diagnosis methods for wind turbine transmission systems (Master's thesis, Yanshan University).
- [6]Han, D. (2025). Research on a generative data-driven fault diagnosis method for hydraulic pumps based on multi-source domain transfer learning (Master's thesis, Yanshan University).
- [7]Zhao, M. (2025). Research on data-driven fault detection and diagnosis and symptom chain inference for heating, ventilation, and air conditioning systems (Master's thesis, Beijing University of Civil Engineering and Architecture).
- [8]Gao, Z. (2025). Research on rolling bearing fault diagnosis driven by data augmentation and multi-source information fusion (Master's thesis, Beijing University of Civil Engineering and Architecture).
- [9]Li, H. (2025). Research on axle box bearing fault diagnosis for high-speed trains based on the integration of fault mechanism simulation and data-driven methods (Master's thesis, Shijiazhuang Tiedao University).
- [10]Luo, H. (2025). Research on data-driven fault diagnosis and remaining useful life prediction methods for rolling bearings (Master's thesis, Qingdao University of Technology).
- [11]Li, X. (2025). Research on data-driven diagnosis of hybrid eccentricity faults in permanent magnet synchronous motors (Master's thesis, Harbin Institute of Technology).
- [12]Zhang, S. (2025). Research on data-driven fault diagnosis of civil aviation engine gas-path systems (Master's thesis, University of Electronic Science and Technology of China).
Article Sidebar
This work is licensed under a Creative Commons Attribution 4.0 International License.