An evaluation of gearbox condition monitoring using infrared thermal images applied with convolutional neural networks

Yongbo Li, James Xi Gu, Dong Zhen, Minqiang Xu, Andrew Ball

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

As an important machine component, the gearbox is widely used in industry for power transmission. Condition monitoring (CM) of a gearbox is critical to provide timely information for undertaking necessary maintenance actions. Massive research efforts have been made in the last two decades to develop vibration-based techniques. However, vibration-based methods usually include several inherent shortages including contact measurement, localized information, noise contamination, and high computation costs, making it difficult to be a cost-effective CM technique. In this paper, infrared thermal (IRT) images, which can contain information covering a large area and acquired remotely, are based on developing a cost-effective CM method. Moreover, a convolutional neural network (CNN) is employed to automatically process the raw IRT images for attaining more comprehensive feature parameters, which avoids the deficiency of incomplete information caused by various feature-extraction methods in vibration analysis. Thus, an IRT–CNN method is developed to achieve online remote monitoring of a gearbox. The performance evaluation based on a bevel gearbox shows that the proposed method can achieve nearly 100% correctness in identifying several common gear faults such as tooth pitting, cracks, and breakages and their compounds. It is also especially robust to ambient temperature changes. In addition, IRT also significantly outperforms its vibration-based counterparts.

Original languageEnglish
Article number2205
Number of pages16
JournalSensors (Switzerland)
Volume19
Issue number9
Early online date13 May 2019
DOIs
Publication statusPublished - May 2019

Fingerprint

transmissions (machine elements)
Condition monitoring
Vibration
Hot Temperature
Infrared radiation
Neural networks
vibration
evaluation
costs
Costs
Machine components
Costs and Cost Analysis
Gear teeth
Vibration analysis
Pitting
Power transmission
power transmission
Gears
Feature extraction
pitting

Cite this

@article{1a85d8a389b3487b8c6f882e610182a0,
title = "An evaluation of gearbox condition monitoring using infrared thermal images applied with convolutional neural networks",
abstract = "As an important machine component, the gearbox is widely used in industry for power transmission. Condition monitoring (CM) of a gearbox is critical to provide timely information for undertaking necessary maintenance actions. Massive research efforts have been made in the last two decades to develop vibration-based techniques. However, vibration-based methods usually include several inherent shortages including contact measurement, localized information, noise contamination, and high computation costs, making it difficult to be a cost-effective CM technique. In this paper, infrared thermal (IRT) images, which can contain information covering a large area and acquired remotely, are based on developing a cost-effective CM method. Moreover, a convolutional neural network (CNN) is employed to automatically process the raw IRT images for attaining more comprehensive feature parameters, which avoids the deficiency of incomplete information caused by various feature-extraction methods in vibration analysis. Thus, an IRT–CNN method is developed to achieve online remote monitoring of a gearbox. The performance evaluation based on a bevel gearbox shows that the proposed method can achieve nearly 100{\%} correctness in identifying several common gear faults such as tooth pitting, cracks, and breakages and their compounds. It is also especially robust to ambient temperature changes. In addition, IRT also significantly outperforms its vibration-based counterparts.",
keywords = "Convolutional neural networks, Fault diagnosis, Gear faults, Infrared thermal imagining, Vibration method",
author = "Yongbo Li and {Xi Gu}, James and Dong Zhen and Minqiang Xu and Andrew Ball",
year = "2019",
month = "5",
doi = "10.3390/s19092205",
language = "English",
volume = "19",
journal = "Sensors",
issn = "1424-3210",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "9",

}

An evaluation of gearbox condition monitoring using infrared thermal images applied with convolutional neural networks. / Li, Yongbo; Xi Gu, James; Zhen, Dong; Xu, Minqiang; Ball, Andrew.

In: Sensors (Switzerland), Vol. 19, No. 9, 2205, 05.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An evaluation of gearbox condition monitoring using infrared thermal images applied with convolutional neural networks

AU - Li, Yongbo

AU - Xi Gu, James

AU - Zhen, Dong

AU - Xu, Minqiang

AU - Ball, Andrew

PY - 2019/5

Y1 - 2019/5

N2 - As an important machine component, the gearbox is widely used in industry for power transmission. Condition monitoring (CM) of a gearbox is critical to provide timely information for undertaking necessary maintenance actions. Massive research efforts have been made in the last two decades to develop vibration-based techniques. However, vibration-based methods usually include several inherent shortages including contact measurement, localized information, noise contamination, and high computation costs, making it difficult to be a cost-effective CM technique. In this paper, infrared thermal (IRT) images, which can contain information covering a large area and acquired remotely, are based on developing a cost-effective CM method. Moreover, a convolutional neural network (CNN) is employed to automatically process the raw IRT images for attaining more comprehensive feature parameters, which avoids the deficiency of incomplete information caused by various feature-extraction methods in vibration analysis. Thus, an IRT–CNN method is developed to achieve online remote monitoring of a gearbox. The performance evaluation based on a bevel gearbox shows that the proposed method can achieve nearly 100% correctness in identifying several common gear faults such as tooth pitting, cracks, and breakages and their compounds. It is also especially robust to ambient temperature changes. In addition, IRT also significantly outperforms its vibration-based counterparts.

AB - As an important machine component, the gearbox is widely used in industry for power transmission. Condition monitoring (CM) of a gearbox is critical to provide timely information for undertaking necessary maintenance actions. Massive research efforts have been made in the last two decades to develop vibration-based techniques. However, vibration-based methods usually include several inherent shortages including contact measurement, localized information, noise contamination, and high computation costs, making it difficult to be a cost-effective CM technique. In this paper, infrared thermal (IRT) images, which can contain information covering a large area and acquired remotely, are based on developing a cost-effective CM method. Moreover, a convolutional neural network (CNN) is employed to automatically process the raw IRT images for attaining more comprehensive feature parameters, which avoids the deficiency of incomplete information caused by various feature-extraction methods in vibration analysis. Thus, an IRT–CNN method is developed to achieve online remote monitoring of a gearbox. The performance evaluation based on a bevel gearbox shows that the proposed method can achieve nearly 100% correctness in identifying several common gear faults such as tooth pitting, cracks, and breakages and their compounds. It is also especially robust to ambient temperature changes. In addition, IRT also significantly outperforms its vibration-based counterparts.

KW - Convolutional neural networks

KW - Fault diagnosis

KW - Gear faults

KW - Infrared thermal imagining

KW - Vibration method

UR - http://www.scopus.com/inward/record.url?scp=85066843702&partnerID=8YFLogxK

U2 - 10.3390/s19092205

DO - 10.3390/s19092205

M3 - Article

VL - 19

JO - Sensors

JF - Sensors

SN - 1424-3210

IS - 9

M1 - 2205

ER -