收藏切换
Bearing remaining useful life prediction method based on a hybrid Wiener-ANN model
收藏切换
PDF
Xin YE1, Shaoquan SU2, Wei SHANG3, Fan YANG1, Long WEN2, 4
Journal of Mechanical Strength | 2025, 47(9) : 233 - 240
Less
收藏切换
Journal of Mechanical Strength | 2025, 47(9): 233-240
Bearing remaining useful life prediction method based on a hybrid Wiener-ANN model
Full
Xin YE1, Shaoquan SU2, Wei SHANG3, Fan YANG1, Long WEN2, 4
Affiliations
  • 1.School of Electrical and Information Engineering, Wuhan Institute of Technology, Wuhan 430205, China
  • 2.School of Mechanical and Electronic Information, China University of Geosciences (Wuhan), Wuhan 430074, China
  • 3.China Railway Science & Industry Group Equipment Engineering Co., Ltd., Wuhan 430077, China
  • 4.Shenzhen Research Institute, China University of Geosciences, Shenzhen 518057, China
Published: 2025-09-15 doi: 10.16579/j.issn.1001.9669.2025.09.023
Outline
收藏切换

Bearings, as critical rotating components in precision instruments, directly affect the safety and stability of the system. Therefore, accurate prediction of their remaining useful life (RUL) is crucial. Existing RUL prediction methods for bearings can be classified into two types: physical model-based and data-driven approaches. Physical models offer high interpretability and require fewer samples but suffer from low prediction accuracy and cannot be used for online prediction.Data-driven methods, on the other hand, provide higher accuracy and support online prediction but require large amounts of data and have poor generalization ability under varying operating conditions or between different equipment. To address these limitations, a Wiener-ANN hybrid model is proposed for bearing RUL prediction, combining the advantages of both physical models and data-driven approaches. The model optimizes the Wiener process using time-frequency domain features as multi-source input data for the first-stage prediction. Subsequently, a three-layer artificial neural network (ANN) is trained using the first-stage prediction results to optimize the model. The optimized Wiener model is then combined with the ANN to predict the RUL of the test dataset. Comparisons with traditional Wiener models and ANN methods show that the proposed approach significantly outperforms these methods in prediction accuracy and application performance, demonstrating strong potential for engineering applications.

Bearing  /  Remaining useful life  /  Prediction method  /  Wiener process model  /  Artificial neural network
Xin YE, Shaoquan SU, Wei SHANG, Fan YANG, Long WEN. Bearing remaining useful life prediction method based on a hybrid Wiener-ANN model[J]. Journal of Mechanical Strength, 2025 , 47 (9) : 233 -240 . DOI: 10.16579/j.issn.1001.9669.2025.09.023
  • Shenzhen Science and Technology Program(JCYJ20230807113708016)
  • Guangdong Basic and Applied Basic Research Foundation(2024A1515011025)
  • National Natural Science Foundation of China(52575605)
Year 2025 volume 47 Issue 9
PDF
87
43
Cite this Article
BibTeX
Article Info
doi: 10.16579/j.issn.1001.9669.2025.09.023
  • Receive Date:2025-02-15
  • Online Date:2026-03-20
  • Published:2025-09-15
Article Data
Affiliations
History
  • Received:2025-02-15
Funding
Shenzhen Science and Technology Program(JCYJ20230807113708016)
Guangdong Basic and Applied Basic Research Foundation(2024A1515011025)
National Natural Science Foundation of China(52575605)
Affiliations
    1.School of Electrical and Information Engineering, Wuhan Institute of Technology, Wuhan 430205, China
    2.School of Mechanical and Electronic Information, China University of Geosciences (Wuhan), Wuhan 430074, China
    3.China Railway Science & Industry Group Equipment Engineering Co., Ltd., Wuhan 430077, China
    4.Shenzhen Research Institute, China University of Geosciences, Shenzhen 518057, China

Corresponding:

WEN Long, E-mail:
References
Share
https://castjournals.cast.org.cn/joweb/jxqd/EN/10.16579/j.issn.1001.9669.2025.09.023
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT