Gearbox fault diagnosis method based on multi-sensor data fusion and GAN

YANG Xingyu; SONG Chunsheng; WU Xiaoyang

doi:DOI：10.16579/j.issn.1001.9669.2025.06.005

您当前的位置：

首页 >

文章列表页 >

Gearbox fault diagnosis method based on multi-sensor data fusion and GAN

·Vibration·Noise·Monitoring·Diagnosis· | 更新时间：2025-06-09

- Gearbox fault diagnosis method based on multi-sensor data fusion and GAN
- Journal of Mechanical Strength Vol. 47, Issue 6, Pages: 37-47(2025)
- 作者机构：
  
  武汉理工大学机电工程学院，武汉 430070
- 作者简介：
  
  SONG Chunsheng, E-mail: song_chsh@163.com
- 基金信息：
- DOI：DOI：10.16579/j.issn.1001.9669.2025.06.005
  CLC： S611
- Received：07 October 2023，
  
  Revised：06 December 2023，
  
  Published：15 June 2025
- 稿件说明：
移动端阅览
杨星宇，宋春生，吴啸阳. 基于多传感器数据融合及GAN的齿轮箱故障诊断方法［J］. 机械强度，2025，47（6）：37-47.

YANG Xingyu，SONG Chunsheng，WU Xiaoyang. Gearbox fault diagnosis method based on multi-sensor data fusion and GAN［J］. Journal of Mechanical Strength，2025，47（6）：37-47.
杨星宇，宋春生，吴啸阳. 基于多传感器数据融合及GAN的齿轮箱故障诊断方法［J］. 机械强度，2025，47（6）：37-47. DOI： DOI：10.16579/j.issn.1001.9669.2025.06.005.

YANG Xingyu，SONG Chunsheng，WU Xiaoyang. Gearbox fault diagnosis method based on multi-sensor data fusion and GAN［J］. Journal of Mechanical Strength，2025，47（6）：37-47. DOI： DOI：10.16579/j.issn.1001.9669.2025.06.005.

摘要

针对数据集不平衡条件下基于多传感器数据的齿轮箱故障诊断分析问题，提出一种基于峭度指标数据融合及生成对抗神经网络（Generative Adversarial Neural Network

GAN）的齿轮箱故障诊断方法。首先，基于信号峭度对多个传感器数据进行加权融合，使融合后的信号中突出齿轮箱的故障敏感成分；其次，利用小波包变换提取信号各频段的能量系数作为信号特征；最后，基于反向传播（Back Propagation

BP）神经网络实现信号特征的分类与识别。由于实际工况中，故障信号较正常信号更不易获取，所以采用GAN对数据集中故障数据部分进行扩展，并采用扩展后的数据集训练BP神经网络。试验分析表明，所述方法故障准确率高达98%，验明了所提方法的正确性，为多传感数据融合及故障诊断问题提供了新的思路与方法。

Abstract

In response to the problem of the gearbox fault diagnosis and analysis based on multi-sensor data under dataset imbalanced conditions

a gearbox fault diagnosis method based on a kurtosis index data fusion and a generative adversarial neural networks (GAN) was proposed. This method weighted the fusion of multiple sensor data based on signal kurtosis

highlighting the fault sensitive components of the gearbox in the fused signal. Then

a wavelet packet transform was used to extract the energy coefficients of each frequency band of the signal as signal features. Finally

the classification and recognition of signal features were implemented based on a back propagation (BP) neural network. Due to the fact that in actual working conditions

fault signals were more difficult to obtain than normal signals

GAN was used to expand the fault data section of the dataset

and the expanded dataset was used to train BP neural network. Through test analysis

it is shown that the fault accuracy of the described method is as high as 98%

which verifies the correctness of the proposed method and provides new ideas and methods for multi-sensor data fusion and fault diagnosis problems.

关键词

Keywords

references

张龙，甄灿壮，易剑昱，等 . 双通道特征融合CNN-GRU齿轮箱故障诊断［J］. 振动与冲击， 2021 ， 40 （ 19 ）： 239 - 245，294 .

ZHANG Long ， ZHEN Canzhuang ， YI Jianyu ， et al . Dual channel feature fusion CNN-GRU gearbox fault diagnosis ［J］. Journal of Vibration and Shock ， 2021 ， 40 （ 19 ）： 239 - 245 . （In Chinese）

乔宁国 . 基于多传感器数据融合的高速列车传动系统故障诊断与健康状态预测［D］. 长春：吉林大学， 2019 ： 33 - 50 .

QIAO Ningguo . Fault diagnosis and health status prediction of high-speed train transmission system based on multi-sensor fusion ［D］. Changchun ： Jilin University ， 2019 ： 33 - 50 . （In Chinese）

史志远，滕虎，马驰 . 基于多信息融合和卷积神经网络的行星齿轮箱故障诊断［J］. 工矿自动化， 2022 ， 48 （ 9 ）： 56 - 62 .

SHI Zhiyuan ， TENG Hu ， MA Chi . Fault diagnosis of planetary gearbox based on multi-information fusion and convolutional neural network ［J］. Journal of Mine Automation ， 2022 ， 48 （ 9 ）： 56 - 62 . （In Chinese）

刘玉梅，乔宁国，庄娇娇，等 . 基于多传感器数据融合的轨道车辆齿轮箱异常检测［J］. 吉林大学学报（工学版）， 2019 ， 49 （ 5 ）： 1465 - 1470 .

LIU Yumei ， QIAO Ningguo ， ZHUANG Jiaojiao ， et al . Anomaly detection of rail vehicle gearbox based on multi-sensor data fusion ［J］. Journal of Jilin University （Engineering and Technology Edition）， 2019 ， 49 （ 5 ）： 1465 - 1470 . （In Chinese）

何庆飞，王旭平，李禹生 . 基于MCKD和峭度的液压泵故障特征提取［J］. 机床与液压， 2023 ， 51 （ 1 ）： 208 - 211 .

HE Qingfei ， WANG Xuping ， LI Yusheng . Fault feature extraction of hydraulic pumps based on MCKD and kurtosis ［J］. Machine Tool & Hydraulics ， 2023 ， 51 （ 1 ）： 208 - 211 . （In Chinese）

佟博 . 基于GAN和DBN模型的伺服电机轴承故障诊断研究［D］. 昆明：昆明理工大学， 2019 ： 29 - 50 .

TONG Bo . Research on fault diagnosis of servo motor bearing based on GAN and DBN model ［D］. Kunming ： Kunming University of Science and Technology ， 2019 ： 29 - 50 . （In Chinese）

郝俊腾 . 小波变换故障诊断方法在无线传感器网络中的应用［D］. 北京：华北电力大学， 2019 ： 9 - 30 .

HAO Junteng . Application of wavelet transform fault diagnosis method in wireless sensor networks ［D］. Beijing ： North China Electric Power University ， 2019 ： 9 - 30 . （In Chinese）

黄华，薛文虎，姚嘉靖，等 . 基于图论诊断法与小波包变换的数控机床进给系统故障诊断研究［J］. 振动与冲击， 2022 ， 41 （ 15 ）： 130 - 137 .

HUANG Hua ， XUE Wenhu ， YAO Jiajing ， et al . Fault diagnosis of NC machine tool feed system based on graph theory diagnosis method and wavelet packet transform ［J］. Journal of Vibration and Shock ， 2022 ， 41 （ 15 ）： 130 - 137 . （In Chinese）

赵善飞 . 基于PSO-BP神经网络的变压器故障诊断方法研究与应用［D］. 广州：广东工业大学， 2021 ： 20 - 30 .

ZHAO Shanfei . Research and application of transformer fault diagnosis method based on PSO-BP neural network ［D］. Guangzhou ： Guangdong University of Technology ， 2021 ： 20 - 30 . （In Chinese）

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

FAULT DIAGNOSIS OF GEARBOX UNDER VARIABLE WORKING CONDITION BASED ON WEIGHTED SUBDOMAIN ADAPTIVE ADVERSARIAL NETWORK

Cross-device fault diagnosis method based on graph convolution and multi-sensor fusion

Semi-supervised gearbox fault diagnosis under variable working conditions based on masked contrastive learning

Bearing fault diagnosis method based on improved compressed sensing and deep multi-kernel extreme learning machine

Research on bearing fault diagnosis based on improved northern goshawk algorithm optimizing SVM

Related Author

ZHANG Huiyun

ZUO Fangjun

YU Xi

YANG Ting

SUN Yuanshuai

KONG Fanqin

NIE Xiaoyin

XIE Gang

Related Institution

School of Intelligent Manufacturing, Chengdu Technological University

College of Mechanical Engineering, Sichuan University

School of Electronic Information Engineering, Taiyuan University of Science and Technology

Shanxi Key Laboratory Of Advanced Control and Industrial Intelligence

School of Mechanical Engineering, Sichuan University

⁰