Skip to the main content

Technical gazette, Vol. 30 No. 1, 2023.

Original scientific paper

https://doi.org/10.17559/TV-20221025165425

Gearbox Fault Diagnosis Method Based on Improved MobileNetV3 and Transfer Learning

Yanping Du ; Department of Mechanical and Electrical Engineering, Beijing Institute of Graphic Communication, Beijing 102600, China
Xuemin Cheng ; Department of Mechanical and Electrical Engineering, Beijing Institute of Graphic Communication, Beijing 102600, China
Yuxin Liu ; Department of Mechanical and Electrical Engineering, Beijing Institute of Graphic Communication, Beijing 102600, China
Shuihai Dou ; Department of Mechanical and Electrical Engineering, Beijing Institute of Graphic Communication, Beijing 102600, China
Juncheng Tu ; Department of Mechanical and Electrical Engineering, Beijing Institute of Graphic Communication, Beijing 102600, China
Yanlin Liu ; Department of Mechanical and Electrical Engineering, Beijing Institute of Graphic Communication, Beijing 102600, China
Xianyang Su ; Department of Mechanical and Electrical Engineering, Beijing Institute of Graphic Communication, Beijing 102600, China

Full text: english pdf 2.903 Kb

page 198-206

downloads: 672

cite

Abstract

Under different working conditions of gearbox, the feature extraction of fault signals is difficult, and large difference in data distribution affects the fault diagnosis results. Based on the problems, the research proposes a method based on improved MobileNetV3 network and transfer learning (TL-Pro-MobilenetV3 network). Three time-frequency analysis methods are used to obtain time-frequency distribution. Among them, short time Fourier transform (STFT) combined with Pro-MobilenetV3 network takes the shortest time and has the highest accuracy. Furthermore, transfer learning is introduced into the model, and the optimal training parameters are selected training the network. Using the dataset from Southeast University, the TL-Pro-MobilenetV3 model is compared with four classical fault diagnosis models. The experimental results show the accuracy of the method proposed can reach 100% and the training time is the shortest in two working conditions, proving the proposed model has a good performance in generalization ability, recognition accuracy and training time.

Keywords

deep learning; gearbox fault diagnosis; STFT; TL-Pro-MobileNetV3 network; transfer learning

Hrčak ID:

288413

URI

https://hrcak.srce.hr/288413

Publication date:

15.12.2022.

Visits: 1.687 *