A sparse stacked denoising autoencoder with optimized transfer learning applied to the fault diagnosis of rolling bearings

•Fault diagnosis by stacked autoencoder requires less professional knowledge.•Domain adaptation by optimized transfer learning reduces the algorithm’s complexity.•Stronger feature extraction ability improves the accuracy of diagnosis.•Combined algorithm can be better applied to the target domain in...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Measurement : journal of the International Measurement Confederation Ročník 146; s. 305 - 314
Hlavní autori: Sun, Meidi, Wang, Hui, Liu, Ping, Huang, Shoudao, Fan, Peng
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: London Elsevier Ltd 01.11.2019
Elsevier Science Ltd
Predmet:
Algorithms
Bearings
Data centers
Deep learning
Diagnostic systems
Fault diagnosis
Feature extraction
Industrial safety
Machine learning
Noise reduction
Roller bearings
Signal processing
Sparse stacked denoising autoencoder (SSDAE)
Studies
Transfer learning (TL)
Fault diagnosis
Deep learning
Transfer learning (TL)
Sparse stacked denoising autoencoder (SSDAE)
Bearings
ISSN:0263-2241, 1873-412X
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:•Fault diagnosis by stacked autoencoder requires less professional knowledge.•Domain adaptation by optimized transfer learning reduces the algorithm’s complexity.•Stronger feature extraction ability improves the accuracy of diagnosis.•Combined algorithm can be better applied to the target domain in fault diagnosis. Fault diagnosis is an important technology in the development of modern industrial safety. Vibration information is commonly used to determine the state of bearings. Driven by big data, deep learning brings new opportunities to fault diagnosis. As an unsupervised deep learning algorithm, a stacked autoencoder (SAE) can relieve the pressure of labelling data. Due to the diversity and variability of the actual fault diagnosis distribution, an optimized transfer learning (TL) algorithm is proposed to solve the domain adaptation. By directly inheriting features obtained from the pre-training process in the source domain and changing only the fine-tuning process, the complexity of the algorithm is reduced. Considering the data reconstruction ability and robustness, a sparse stacked denoising autoencoder (SSDAE) is proposed for feature extraction, which can indirectly improve the diagnostic accuracy in the target domain. The results for data from the Case Western Reserve University Bearing Data Center show that the proposed SSDAE-TL algorithm is feasible and easy to implement for the fault diagnosis of bearings.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0263-2241
1873-412X
DOI:10.1016/j.measurement.2019.06.029