Planetary Gearboxes Fault Diagnosis Based on Markov Transition Fields and SE-ResNet

The working conditions of planetary gearboxes are complex, and their structural couplings are strong, leading to low reliability. Traditional deep neural networks often struggle with feature learning in noisy environments, and their reliance on one-dimensional signals as input fails to capture the i...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanyan Liu, Tongxin Gao, Wenxu Wu, Yongquan Sun
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/23/7540
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846123860274970624
author Yanyan Liu
Tongxin Gao
Wenxu Wu
Yongquan Sun
author_facet Yanyan Liu
Tongxin Gao
Wenxu Wu
Yongquan Sun
author_sort Yanyan Liu
collection DOAJ
description The working conditions of planetary gearboxes are complex, and their structural couplings are strong, leading to low reliability. Traditional deep neural networks often struggle with feature learning in noisy environments, and their reliance on one-dimensional signals as input fails to capture the interrelationships between data points. To address these challenges, we proposed a fault diagnosis method for planetary gearboxes that integrates Markov transition fields (MTFs) and a residual attention mechanism. The MTF was employed to encode one-dimensional signals into feature maps, which were then fed into a residual networks (ResNet) architecture. To enhance the network’s ability to focus on important features, we embedded the squeeze-and-excitation (SE) channel attention mechanism into the ResNet34 network, creating a SE-ResNet model. This model was trained to effectively extract and classify features. The developed method was validated using a specific dataset and achieved an accuracy of about 98.1%. The results demonstrate the effectiveness and reliability of the developed method in diagnosing faults in planetary gearboxes under strong noise conditions.
format Article
id doaj-art-c2298dc9642e4f0a94ad43f09d55e4dd
institution Kabale University
issn 1424-8220
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-c2298dc9642e4f0a94ad43f09d55e4dd2024-12-13T16:31:52ZengMDPI AGSensors1424-82202024-11-012423754010.3390/s24237540Planetary Gearboxes Fault Diagnosis Based on Markov Transition Fields and SE-ResNetYanyan Liu0Tongxin Gao1Wenxu Wu2Yongquan Sun3School of Mechanical Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Mechanical Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaInstitute of Sensor and Reliability Engineering, Harbin University of Science and Technology, Harbin 150080, ChinaInstitute of Sensor and Reliability Engineering, Harbin University of Science and Technology, Harbin 150080, ChinaThe working conditions of planetary gearboxes are complex, and their structural couplings are strong, leading to low reliability. Traditional deep neural networks often struggle with feature learning in noisy environments, and their reliance on one-dimensional signals as input fails to capture the interrelationships between data points. To address these challenges, we proposed a fault diagnosis method for planetary gearboxes that integrates Markov transition fields (MTFs) and a residual attention mechanism. The MTF was employed to encode one-dimensional signals into feature maps, which were then fed into a residual networks (ResNet) architecture. To enhance the network’s ability to focus on important features, we embedded the squeeze-and-excitation (SE) channel attention mechanism into the ResNet34 network, creating a SE-ResNet model. This model was trained to effectively extract and classify features. The developed method was validated using a specific dataset and achieved an accuracy of about 98.1%. The results demonstrate the effectiveness and reliability of the developed method in diagnosing faults in planetary gearboxes under strong noise conditions.https://www.mdpi.com/1424-8220/24/23/7540Markov transfer fieldsresidual networksgearbox fault diagnosisattention mechanisms
spellingShingle Yanyan Liu
Tongxin Gao
Wenxu Wu
Yongquan Sun
Planetary Gearboxes Fault Diagnosis Based on Markov Transition Fields and SE-ResNet
Sensors
Markov transfer fields
residual networks
gearbox fault diagnosis
attention mechanisms
title Planetary Gearboxes Fault Diagnosis Based on Markov Transition Fields and SE-ResNet
title_full Planetary Gearboxes Fault Diagnosis Based on Markov Transition Fields and SE-ResNet
title_fullStr Planetary Gearboxes Fault Diagnosis Based on Markov Transition Fields and SE-ResNet
title_full_unstemmed Planetary Gearboxes Fault Diagnosis Based on Markov Transition Fields and SE-ResNet
title_short Planetary Gearboxes Fault Diagnosis Based on Markov Transition Fields and SE-ResNet
title_sort planetary gearboxes fault diagnosis based on markov transition fields and se resnet
topic Markov transfer fields
residual networks
gearbox fault diagnosis
attention mechanisms
url https://www.mdpi.com/1424-8220/24/23/7540
work_keys_str_mv AT yanyanliu planetarygearboxesfaultdiagnosisbasedonmarkovtransitionfieldsandseresnet
AT tongxingao planetarygearboxesfaultdiagnosisbasedonmarkovtransitionfieldsandseresnet
AT wenxuwu planetarygearboxesfaultdiagnosisbasedonmarkovtransitionfieldsandseresnet
AT yongquansun planetarygearboxesfaultdiagnosisbasedonmarkovtransitionfieldsandseresnet