A novel method for early gear pitting fault diagnosis using stacked SAE and GBRBM

Jialin Li, Xueyi Li, David He, Yongzhi Qu

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Research on data-driven fault diagnosis methods has received much attention in recent years. The deep belief network (DBN) is a commonly used deep learning method for fault diagnosis. In the past, when people used DBN to diagnose gear pitting faults, it was found that the diagnosis result was not good with continuous time domain vibration signals as direct inputs into DBN. Therefore, most researchers extracted features from time domain vibration signals as inputs into DBN. However, it is desirable to use raw vibration signals as direct inputs to achieve good fault diagnosis results. Therefore, this paper proposes a novel method by stacking spare autoencoder (SAE) and Gauss-Binary restricted Boltzmann machine (GBRBM) for early gear pitting faults diagnosis with raw vibration signals as direct inputs. The SAE layer is used to compress the raw vibration data and the GBRBM layer is used to effectively process continuous time domain vibration signals. Vibration signals of seven early gear pitting faults collected from a gear test rig are used to validate the proposed method. The validation results show that the proposed method maintains a good diagnosis performance under different working conditions and gives higher diagnosis accuracy compared to other traditional methods.

Original languageEnglish (US)
Article number758
JournalSensors (Switzerland)
Volume19
Issue number4
DOIs
StatePublished - Feb 2 2019

Fingerprint

pitting
Bayesian networks
Vibration
Pitting
belief networks
Failure analysis
Gears
vibration
learning
Research Personnel
Learning
Research

Keywords

  • Early gear pitting fault diagnosis
  • GBRBM
  • SAE
  • Vibration signals

Cite this

A novel method for early gear pitting fault diagnosis using stacked SAE and GBRBM. / Li, Jialin; Li, Xueyi; He, David; Qu, Yongzhi.

In: Sensors (Switzerland), Vol. 19, No. 4, 758, 02.02.2019.

Research output: Contribution to journalArticle

@article{f018dffc1ffa4c75a953a0ba26051160,
title = "A novel method for early gear pitting fault diagnosis using stacked SAE and GBRBM",
abstract = "Research on data-driven fault diagnosis methods has received much attention in recent years. The deep belief network (DBN) is a commonly used deep learning method for fault diagnosis. In the past, when people used DBN to diagnose gear pitting faults, it was found that the diagnosis result was not good with continuous time domain vibration signals as direct inputs into DBN. Therefore, most researchers extracted features from time domain vibration signals as inputs into DBN. However, it is desirable to use raw vibration signals as direct inputs to achieve good fault diagnosis results. Therefore, this paper proposes a novel method by stacking spare autoencoder (SAE) and Gauss-Binary restricted Boltzmann machine (GBRBM) for early gear pitting faults diagnosis with raw vibration signals as direct inputs. The SAE layer is used to compress the raw vibration data and the GBRBM layer is used to effectively process continuous time domain vibration signals. Vibration signals of seven early gear pitting faults collected from a gear test rig are used to validate the proposed method. The validation results show that the proposed method maintains a good diagnosis performance under different working conditions and gives higher diagnosis accuracy compared to other traditional methods.",
keywords = "Early gear pitting fault diagnosis, GBRBM, SAE, Vibration signals",
author = "Jialin Li and Xueyi Li and David He and Yongzhi Qu",
year = "2019",
month = "2",
day = "2",
doi = "10.3390/s19040758",
language = "English (US)",
volume = "19",
journal = "Sensors",
issn = "1424-3210",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "4",

}

TY - JOUR

T1 - A novel method for early gear pitting fault diagnosis using stacked SAE and GBRBM

AU - Li, Jialin

AU - Li, Xueyi

AU - He, David

AU - Qu, Yongzhi

PY - 2019/2/2

Y1 - 2019/2/2

N2 - Research on data-driven fault diagnosis methods has received much attention in recent years. The deep belief network (DBN) is a commonly used deep learning method for fault diagnosis. In the past, when people used DBN to diagnose gear pitting faults, it was found that the diagnosis result was not good with continuous time domain vibration signals as direct inputs into DBN. Therefore, most researchers extracted features from time domain vibration signals as inputs into DBN. However, it is desirable to use raw vibration signals as direct inputs to achieve good fault diagnosis results. Therefore, this paper proposes a novel method by stacking spare autoencoder (SAE) and Gauss-Binary restricted Boltzmann machine (GBRBM) for early gear pitting faults diagnosis with raw vibration signals as direct inputs. The SAE layer is used to compress the raw vibration data and the GBRBM layer is used to effectively process continuous time domain vibration signals. Vibration signals of seven early gear pitting faults collected from a gear test rig are used to validate the proposed method. The validation results show that the proposed method maintains a good diagnosis performance under different working conditions and gives higher diagnosis accuracy compared to other traditional methods.

AB - Research on data-driven fault diagnosis methods has received much attention in recent years. The deep belief network (DBN) is a commonly used deep learning method for fault diagnosis. In the past, when people used DBN to diagnose gear pitting faults, it was found that the diagnosis result was not good with continuous time domain vibration signals as direct inputs into DBN. Therefore, most researchers extracted features from time domain vibration signals as inputs into DBN. However, it is desirable to use raw vibration signals as direct inputs to achieve good fault diagnosis results. Therefore, this paper proposes a novel method by stacking spare autoencoder (SAE) and Gauss-Binary restricted Boltzmann machine (GBRBM) for early gear pitting faults diagnosis with raw vibration signals as direct inputs. The SAE layer is used to compress the raw vibration data and the GBRBM layer is used to effectively process continuous time domain vibration signals. Vibration signals of seven early gear pitting faults collected from a gear test rig are used to validate the proposed method. The validation results show that the proposed method maintains a good diagnosis performance under different working conditions and gives higher diagnosis accuracy compared to other traditional methods.

KW - Early gear pitting fault diagnosis

KW - GBRBM

KW - SAE

KW - Vibration signals

UR - http://www.scopus.com/inward/record.url?scp=85061867566&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061867566&partnerID=8YFLogxK

U2 - 10.3390/s19040758

DO - 10.3390/s19040758

M3 - Article

C2 - 30781784

AN - SCOPUS:85061867566

VL - 19

JO - Sensors

JF - Sensors

SN - 1424-3210

IS - 4

M1 - 758

ER -