Multi-View Information Fusion Fault Diagnosis Method Based on Attention Mechanism and Convolutional Neural Network
Multi-view information fusion can provide more accurate, complete and reliable data descriptions for monitoring objects, effectively improve the limitations and unreliability of single-view data. Existing multi-view information fusion based on deep learning mostly focuses on the feature level and de...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-11-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/12/22/11410 |
_version_ | 1797466063145795584 |
---|---|
author | Hongmei Li Jinying Huang Minjuan Gao Luxia Yang Yichen Bao |
author_facet | Hongmei Li Jinying Huang Minjuan Gao Luxia Yang Yichen Bao |
author_sort | Hongmei Li |
collection | DOAJ |
description | Multi-view information fusion can provide more accurate, complete and reliable data descriptions for monitoring objects, effectively improve the limitations and unreliability of single-view data. Existing multi-view information fusion based on deep learning mostly focuses on the feature level and decision level, with large information loss, and does not distinguish the view weight in the fusion process. To this end, a multi-view data level information fusion model CAM_MCFCNN with view weight was proposed based on a channel attention mechanism and convolutional neural network. The model used the channel characteristics to implement multi-view information fusion at the data level stage, which made the fusion position and mode more natural and reduced the loss of information. A multi-channel fusion convolutional neural network was used for feature learning. In addition, the channel attention mechanism was used to learn the view weight, so that the algorithm could pay more attention to the views that contribute more to the fault identification task during the training process, and more reasonably integrate the information of different views. The proposed method was verified by the data of the planetary gearbox experimental platform. The multi-view data and single-view data were used as the input of the CAM_MCFCNN model and single-channel CNN model respectively for comparison. The average accuracy of CAM_MCFCNN on three constant-speed datasets reached 99.95%, 99.87% and 99.92%, which was an improvement of 0.95%, 2.25%, and 0.04%, compared with the single view with the highest diagnostic accuracy, respectively. When facing limited samples, CAM_MCFCNN had similar performance. Finally, compared with different multi-view information fusion algorithms, CAM_MCFCNN showed better stability and higher accuracy. The experimental results showed that the proposed method had better performance, higher diagnostic accuracy and was more reliable, compared with other methods. |
first_indexed | 2024-03-09T18:30:45Z |
format | Article |
id | doaj.art-e5d18d7dc3fb45b2b89e686e391c9fd6 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-09T18:30:45Z |
publishDate | 2022-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-e5d18d7dc3fb45b2b89e686e391c9fd62023-11-24T07:34:47ZengMDPI AGApplied Sciences2076-34172022-11-0112221141010.3390/app122211410Multi-View Information Fusion Fault Diagnosis Method Based on Attention Mechanism and Convolutional Neural NetworkHongmei Li0Jinying Huang1Minjuan Gao2Luxia Yang3Yichen Bao4College of Computer Science and Technology, Taiyuan Normal University, Jinzhong 030619, ChinaSchool of Mechanical Engineering, North University of China, Taiyuan 030051, ChinaCollege of Computer Science and Technology, Taiyuan Normal University, Jinzhong 030619, ChinaCollege of Computer Science and Technology, Taiyuan Normal University, Jinzhong 030619, ChinaSchool of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, ChinaMulti-view information fusion can provide more accurate, complete and reliable data descriptions for monitoring objects, effectively improve the limitations and unreliability of single-view data. Existing multi-view information fusion based on deep learning mostly focuses on the feature level and decision level, with large information loss, and does not distinguish the view weight in the fusion process. To this end, a multi-view data level information fusion model CAM_MCFCNN with view weight was proposed based on a channel attention mechanism and convolutional neural network. The model used the channel characteristics to implement multi-view information fusion at the data level stage, which made the fusion position and mode more natural and reduced the loss of information. A multi-channel fusion convolutional neural network was used for feature learning. In addition, the channel attention mechanism was used to learn the view weight, so that the algorithm could pay more attention to the views that contribute more to the fault identification task during the training process, and more reasonably integrate the information of different views. The proposed method was verified by the data of the planetary gearbox experimental platform. The multi-view data and single-view data were used as the input of the CAM_MCFCNN model and single-channel CNN model respectively for comparison. The average accuracy of CAM_MCFCNN on three constant-speed datasets reached 99.95%, 99.87% and 99.92%, which was an improvement of 0.95%, 2.25%, and 0.04%, compared with the single view with the highest diagnostic accuracy, respectively. When facing limited samples, CAM_MCFCNN had similar performance. Finally, compared with different multi-view information fusion algorithms, CAM_MCFCNN showed better stability and higher accuracy. The experimental results showed that the proposed method had better performance, higher diagnostic accuracy and was more reliable, compared with other methods.https://www.mdpi.com/2076-3417/12/22/11410fault diagnosismulti-view information fusionconvolutional neural networkattention mechanismplanetary gearbox |
spellingShingle | Hongmei Li Jinying Huang Minjuan Gao Luxia Yang Yichen Bao Multi-View Information Fusion Fault Diagnosis Method Based on Attention Mechanism and Convolutional Neural Network Applied Sciences fault diagnosis multi-view information fusion convolutional neural network attention mechanism planetary gearbox |
title | Multi-View Information Fusion Fault Diagnosis Method Based on Attention Mechanism and Convolutional Neural Network |
title_full | Multi-View Information Fusion Fault Diagnosis Method Based on Attention Mechanism and Convolutional Neural Network |
title_fullStr | Multi-View Information Fusion Fault Diagnosis Method Based on Attention Mechanism and Convolutional Neural Network |
title_full_unstemmed | Multi-View Information Fusion Fault Diagnosis Method Based on Attention Mechanism and Convolutional Neural Network |
title_short | Multi-View Information Fusion Fault Diagnosis Method Based on Attention Mechanism and Convolutional Neural Network |
title_sort | multi view information fusion fault diagnosis method based on attention mechanism and convolutional neural network |
topic | fault diagnosis multi-view information fusion convolutional neural network attention mechanism planetary gearbox |
url | https://www.mdpi.com/2076-3417/12/22/11410 |
work_keys_str_mv | AT hongmeili multiviewinformationfusionfaultdiagnosismethodbasedonattentionmechanismandconvolutionalneuralnetwork AT jinyinghuang multiviewinformationfusionfaultdiagnosismethodbasedonattentionmechanismandconvolutionalneuralnetwork AT minjuangao multiviewinformationfusionfaultdiagnosismethodbasedonattentionmechanismandconvolutionalneuralnetwork AT luxiayang multiviewinformationfusionfaultdiagnosismethodbasedonattentionmechanismandconvolutionalneuralnetwork AT yichenbao multiviewinformationfusionfaultdiagnosismethodbasedonattentionmechanismandconvolutionalneuralnetwork |