Deep convolutional neural network based planet bearing fault classification

Dezuo Zhao, Tianyang Wang, Fulei Chu

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Condition monitoring and fault diagnosis of the planet bearing is key to operational reliability of the planetary gearbox, and also have remained challenging due to complex modulation phenomenon and strong planetary gear noise. As such, a new fault diagnosis strategy based on the synchrosqueezing transform (SST) and the deep convolutional neural network (DCNN) is proposed in this paper. Specifically, the envelope time-frequency representations (TFRs) of the vibration signals of the planetary gearbox are firstly calculated using the Hilbert transform and the SST. Next, a DCNN is constructed to learn the underlying features from the TFRs and then the fault types can be determined automatically. As its main contribution, the proposed method automatically recognizes the planet bearing fault type, which is free from artificially capturing fault characteristic frequencies in spectrum or time-frequency spectrum that contain many interference items, and effectively avoid missed diagnosis and misdiagnosis. In addition, it is also free from considering frequency band selection, which is difficult duo to the strong interferences of the gear meshing vibration. The analysis results of the planetary gearbox data demonstrate effectiveness of the proposed approach with a classification accuracy better than 98.3%.
Original languageEnglish
Pages (from-to)59-66
Number of pages8
JournalComputers in Industry
Volume107
Early online date8 Feb 2019
DOIs
Publication statusPublished - 1 May 2019
Externally publishedYes

Fingerprint

Bearings (structural)
Planets
Failure analysis
Neural networks
Condition monitoring
Acoustic noise
Frequency bands
Gears
Modulation

Cite this

@article{fdb24068e93f40d589d3a1e98e5e8dc6,
title = "Deep convolutional neural network based planet bearing fault classification",
abstract = "Condition monitoring and fault diagnosis of the planet bearing is key to operational reliability of the planetary gearbox, and also have remained challenging due to complex modulation phenomenon and strong planetary gear noise. As such, a new fault diagnosis strategy based on the synchrosqueezing transform (SST) and the deep convolutional neural network (DCNN) is proposed in this paper. Specifically, the envelope time-frequency representations (TFRs) of the vibration signals of the planetary gearbox are firstly calculated using the Hilbert transform and the SST. Next, a DCNN is constructed to learn the underlying features from the TFRs and then the fault types can be determined automatically. As its main contribution, the proposed method automatically recognizes the planet bearing fault type, which is free from artificially capturing fault characteristic frequencies in spectrum or time-frequency spectrum that contain many interference items, and effectively avoid missed diagnosis and misdiagnosis. In addition, it is also free from considering frequency band selection, which is difficult duo to the strong interferences of the gear meshing vibration. The analysis results of the planetary gearbox data demonstrate effectiveness of the proposed approach with a classification accuracy better than 98.3{\%}.",
keywords = "Planet bearing, Fault classification, Synchrosqueezing transform, Deep convolution neural network",
author = "Dezuo Zhao and Tianyang Wang and Fulei Chu",
year = "2019",
month = "5",
day = "1",
doi = "10.1016/j.compind.2019.02.001",
language = "English",
volume = "107",
pages = "59--66",
journal = "Computers in Industry",
issn = "0166-3615",
publisher = "Elsevier",

}

Deep convolutional neural network based planet bearing fault classification. / Zhao, Dezuo; Wang, Tianyang; Chu, Fulei.

In: Computers in Industry, Vol. 107, 01.05.2019, p. 59-66.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Deep convolutional neural network based planet bearing fault classification

AU - Zhao, Dezuo

AU - Wang, Tianyang

AU - Chu, Fulei

PY - 2019/5/1

Y1 - 2019/5/1

N2 - Condition monitoring and fault diagnosis of the planet bearing is key to operational reliability of the planetary gearbox, and also have remained challenging due to complex modulation phenomenon and strong planetary gear noise. As such, a new fault diagnosis strategy based on the synchrosqueezing transform (SST) and the deep convolutional neural network (DCNN) is proposed in this paper. Specifically, the envelope time-frequency representations (TFRs) of the vibration signals of the planetary gearbox are firstly calculated using the Hilbert transform and the SST. Next, a DCNN is constructed to learn the underlying features from the TFRs and then the fault types can be determined automatically. As its main contribution, the proposed method automatically recognizes the planet bearing fault type, which is free from artificially capturing fault characteristic frequencies in spectrum or time-frequency spectrum that contain many interference items, and effectively avoid missed diagnosis and misdiagnosis. In addition, it is also free from considering frequency band selection, which is difficult duo to the strong interferences of the gear meshing vibration. The analysis results of the planetary gearbox data demonstrate effectiveness of the proposed approach with a classification accuracy better than 98.3%.

AB - Condition monitoring and fault diagnosis of the planet bearing is key to operational reliability of the planetary gearbox, and also have remained challenging due to complex modulation phenomenon and strong planetary gear noise. As such, a new fault diagnosis strategy based on the synchrosqueezing transform (SST) and the deep convolutional neural network (DCNN) is proposed in this paper. Specifically, the envelope time-frequency representations (TFRs) of the vibration signals of the planetary gearbox are firstly calculated using the Hilbert transform and the SST. Next, a DCNN is constructed to learn the underlying features from the TFRs and then the fault types can be determined automatically. As its main contribution, the proposed method automatically recognizes the planet bearing fault type, which is free from artificially capturing fault characteristic frequencies in spectrum or time-frequency spectrum that contain many interference items, and effectively avoid missed diagnosis and misdiagnosis. In addition, it is also free from considering frequency band selection, which is difficult duo to the strong interferences of the gear meshing vibration. The analysis results of the planetary gearbox data demonstrate effectiveness of the proposed approach with a classification accuracy better than 98.3%.

KW - Planet bearing

KW - Fault classification

KW - Synchrosqueezing transform

KW - Deep convolution neural network

UR - http://www.scopus.com/inward/record.url?scp=85061190559&partnerID=8YFLogxK

U2 - 10.1016/j.compind.2019.02.001

DO - 10.1016/j.compind.2019.02.001

M3 - Article

VL - 107

SP - 59

EP - 66

JO - Computers in Industry

JF - Computers in Industry

SN - 0166-3615

ER -