Comparisons of different deep learning-based methods on fault diagnosis for geared system

Comparisons of different deep learning-based methods on fault diagnosis for geared system

The running state of a geared transmission system affects the stability and reliability of the whole mechanical system. It will greatly reduce the maintenance cost of a mechanical system to identify the faulty state of the geared transmission system. Based on the measured gear fault vibration signal...

Full description

Bibliographic Details
Main Authors: Bing Han, Xiaohui Yang, Yafeng Ren, Wanggui Lan
Format: Article
Language:English
Published: SAGE Publishing 2019-11-01
Series:International Journal of Distributed Sensor Networks
Online Access:https://doi.org/10.1177/1550147719888169
id doaj-4999d34b9a56419e9172e2445043b81d
record_format Article
spelling doaj-4999d34b9a56419e9172e2445043b81d2020-11-25T03:49:38ZengSAGE PublishingInternational Journal of Distributed Sensor Networks1550-14772019-11-011510.1177/1550147719888169Comparisons of different deep learning-based methods on fault diagnosis for geared systemBing Han0Xiaohui Yang1Yafeng Ren2Wanggui Lan3Shaanxi Engineering Laboratory for Transmissions and Controls, Northwestern Polytechnical University, Xi’an, P.R. ChinaShaanxi Engineering Laboratory for Transmissions and Controls, Northwestern Polytechnical University, Xi’an, P.R. ChinaSchool of Mechanical Engineering, Taiyuan University of Science and Technology, Taiyuan, P.R. ChinaShaanxi Engineering Laboratory for Transmissions and Controls, Northwestern Polytechnical University, Xi’an, P.R. ChinaThe running state of a geared transmission system affects the stability and reliability of the whole mechanical system. It will greatly reduce the maintenance cost of a mechanical system to identify the faulty state of the geared transmission system. Based on the measured gear fault vibration signals and the deep learning theory, four fault diagnosis neural network models including fast Fourier transform–deep belief network model, wavelet transform–convolutional neural network model, Hilbert-Huang transform–convolutional neural network model, and comprehensive deep neural network model are developed and trained respectively. The results show that the gear fault diagnosis method based on deep learning theory can effectively identify various gear faults under real test conditions. The comprehensive deep neural network model is the most effective one in gear fault recognition.https://doi.org/10.1177/1550147719888169
collection DOAJ
language English
format Article
sources DOAJ
author Bing Han
Xiaohui Yang
Yafeng Ren
Wanggui Lan
spellingShingle Bing Han
Xiaohui Yang
Yafeng Ren
Wanggui Lan
Comparisons of different deep learning-based methods on fault diagnosis for geared system
International Journal of Distributed Sensor Networks
author_facet Bing Han
Xiaohui Yang
Yafeng Ren
Wanggui Lan
author_sort Bing Han
title Comparisons of different deep learning-based methods on fault diagnosis for geared system
title_short Comparisons of different deep learning-based methods on fault diagnosis for geared system
title_full Comparisons of different deep learning-based methods on fault diagnosis for geared system
title_fullStr Comparisons of different deep learning-based methods on fault diagnosis for geared system
title_full_unstemmed Comparisons of different deep learning-based methods on fault diagnosis for geared system
title_sort comparisons of different deep learning-based methods on fault diagnosis for geared system
publisher SAGE Publishing
series International Journal of Distributed Sensor Networks
issn 1550-1477
publishDate 2019-11-01
description The running state of a geared transmission system affects the stability and reliability of the whole mechanical system. It will greatly reduce the maintenance cost of a mechanical system to identify the faulty state of the geared transmission system. Based on the measured gear fault vibration signals and the deep learning theory, four fault diagnosis neural network models including fast Fourier transform–deep belief network model, wavelet transform–convolutional neural network model, Hilbert-Huang transform–convolutional neural network model, and comprehensive deep neural network model are developed and trained respectively. The results show that the gear fault diagnosis method based on deep learning theory can effectively identify various gear faults under real test conditions. The comprehensive deep neural network model is the most effective one in gear fault recognition.
url https://doi.org/10.1177/1550147719888169
work_keys_str_mv AT binghan comparisonsofdifferentdeeplearningbasedmethodsonfaultdiagnosisforgearedsystem
AT xiaohuiyang comparisonsofdifferentdeeplearningbasedmethodsonfaultdiagnosisforgearedsystem
AT yafengren comparisonsofdifferentdeeplearningbasedmethodsonfaultdiagnosisforgearedsystem
AT wangguilan comparisonsofdifferentdeeplearningbasedmethodsonfaultdiagnosisforgearedsystem
_version_ 1724494257073422336

Similar Items