Gearbox Fault Diagnosis Based on Dynamic Weighted Feature Fusion with Maximum Information Coefficient

Nie Yongjun; Liu Zhijun; Tang Zhenyu; Liu Zhihua; Zhou Qiang

doi:10.16578/j.issn.1004.2539.2022.12.022

您当前的位置：

首页 >

文章列表页 >

Gearbox Fault Diagnosis Based on Dynamic Weighted Feature Fusion with Maximum Information Coefficient

Development·Application | 更新时间：2023-01-06

- Gearbox Fault Diagnosis Based on Dynamic Weighted Feature Fusion with Maximum Information Coefficient
- Journal of Mechanical Transmission Vol. 46, Issue 12, Pages: 142-147(2022)
- 作者机构：
  
  1.广州航海学院机械工程系，广东广州 510725
  2.河南工业大学机电工程学院，河南郑州 450007
  3.郑州机械研究所有限公司，河南郑州 450052
- 作者简介：
- 基金信息：
- DOI：10.16578/j.issn.1004.2539.2022.12.022
  CLC：
扫描看全文
聂勇军,刘志军,唐振宇等.基于最大信息系数的动态加权特征融合的齿轮箱故障诊断[J].机械传动,2022,46(12):142-147.

Nie Yongjun,Liu Zhijun,Tang Zhenyu,et al.Gearbox Fault Diagnosis Based on Dynamic Weighted Feature Fusion with Maximum Information Coefficient[J].Journal of Mechanical Transmission,2022,46(12):142-147.
聂勇军,刘志军,唐振宇等.基于最大信息系数的动态加权特征融合的齿轮箱故障诊断[J].机械传动,2022,46(12):142-147. DOI： 10.16578/j.issn.1004.2539.2022.12.022.

Nie Yongjun,Liu Zhijun,Tang Zhenyu,et al.Gearbox Fault Diagnosis Based on Dynamic Weighted Feature Fusion with Maximum Information Coefficient[J].Journal of Mechanical Transmission,2022,46(12):142-147. DOI： 10.16578/j.issn.1004.2539.2022.12.022.

摘要

随着机械设备的精细化和复杂化，用于监测其运行状态的传感器数量和类型不断增多，为了能有效地将多传感器信息融合，补全时间和空间上的信息，提高传感器信息的可靠性，提出了一种基于最大信息系数的动态加权特征融合的齿轮故障诊断方法。利用小波包变换对多传感器采集到的振动信号分解到时频域；计算时频域的特征，通过最大信息系数计算各传感器的权重并以并联融合的方式对特征进行融合；将融合后的特征输入到支持向量机模型进行故障分类。实验证明，融合后的特征聚合度更好，更有利于分类；在两种转速条件下，融合后的故障诊断准确率分别达到了87.72%和99.16%，动态加权融合的诊断效果好于定权重融合的诊断效果。

Abstract

With the refinement and complexity of mechanical equipment, the number and types of sensors used to monitor their operating status are increasing. In order to effectively fuse multi-sensor information, complete the information in time and space, and improve the reliability of sensor information, a gear fault diagnosis method based on dynamic weighted feature fusion with maximum information coefficient is proposed. The wavelet packet transform is used to decompose the vibration signals collected by multi-sensor into time-frequency domain; the time and frequency domain features are calculated, the weight of each sensor is calculated by the maximum information coefficient, and the features are fused in parallel; the fused features are input into the support vector machine model for fault classification. Experiments show that the fusion features have better aggregation and are more conducive to classification; under the two speed conditions, the accuracy of fault diagnosis after fusion is 87.72% and 99.16% respectively; the experiment also proves that the diagnosis effect of dynamic weighted fusion is better than that of fixed weight fusion.

关键词

最大信息系数动态加权特征融合故障诊断支持向量机

Keywords

Maximum information coefficientDynamic weightingFeature fusionFault diagnosisSupport vector machine

references

RADZEVICH S P.Dudley's handbook of practical gear design and manufacture［M］.3rd ed.Boca Raton Crc Press，USA，2012：1-10.

刘天羽，李国正.齿轮故障不均衡分类问题的研究［J］.计算机工程与应用，2010，46（20）：146-148.

LIU Tianyu，LI Guozheng.Research on imbalanced problems in gear fault diagnosis［J］.Computer Engineering and Applications，2010，46（20）：146-148.

YAO Y，WANG H，LI S，et al.End-to-end convolutional neural network model for gear fault diagnosis based on sound signals［J］.Applied Sciences，2018，8（9）：1584.

许萌.基于声发射技术的高速列车滚动轴承健康监测方法研究［D］.北京：北京化工大学，2019：9-27.

XU Meng.Research on health monitoring method of high-speed train rolling bearing based on acoustic emission technology［D］.Beijing：Beijing University of Chemical Technology，2019：9-27.

丁嘉鑫，王振亚，姚立纲，等.广义复合多尺度加权排列熵与参数优化支持向量机的滚动轴承故障诊断［J］.中国机械工程，2021，32（2）：147-155.

DING Jiaxin，WANG Zhenya，YAO Ligang，et al.Rolling bearing fault diagnosis based on generalized composite multi-scale weighted permutation entropy and parameter optimization support vector machine［J］.China Mechanical Engineering，2021，32（2）：147-155.

朱兴统.基于小波包分解和K最近邻算法的轴承故障诊断方法［J］.装备制造技术，2020（2）：24-27.

ZHU Xingtong.Bearing fault diagnosis method based on wavelet packet decomposition and K-nearest neighbor algorithm［J］.Equipment Manufacturing Technology，2020（2）：24-27.

周旺平，王蓉，许沈榕，等.VMD能量熵与随机森林相结合的齿轮故障诊断［J］.机械设计与制造，2021（3）：270-275.

ZHOU Wangping，WANG Rong，XU Shenrong，et al.Gear fault diagnosis based on VMD energy entropy and random forest［J］.Machinery Design and Manufacture，2021（3）：270-275.

刘长良，张书瑶，王梓齐.基于改进KNN回归算法的风电机组齿轮箱状态监测［J］.中国测试，2021，47（1）：153-159.

LIU Changliang，ZHANG Shuyao，WANG Ziqi.Condition monitoring of wind turbine gearbox based on improved KNN regression algorithm［J］.China Measurement & Test，2021，47（1）：153-159.

王二化，刘颉.基于PCA和改进型SVM的齿轮裂纹故障诊断方法［J］.机械设计与研究，2021，37（2）：83-87.

WANG Erhua，LIU Jie.Fault diagnosis method of gear crack based on PCA and improved SVM［J］.Machine Design and Research，2021，37（2）：83-87.

张立智，谭继文，徐卫晓，等.多深度学习模型决策融合的滚动轴承故障诊断［J］.组合机床与自动化加工技术，2019（8）：59-62.

ZHANG Lizhi，TAN Jiwen，XU Weixiao，et al.Fault diagnosis methods of rolling bearings based on decision fusion of multiple deep learning models［J］.Modular Machine Tool ＆ Automatic Manufacturing Technique，2019（8）：59-62.

RESHEF D N，RESHEF Y A，FINUCANE H K，et al.Detecting novel associations in large data sets［J］.Science，2011，334（6062）：1518-1524.

TANG X，WANG J，LU J，et al.Improving bearing fault diagnosis using maximum information coefficient based feature selection［J］.Applied Sciences，2018，8（11）：2143.

LIANG Y，HE W L，ZHONG W，et al.Objective reduction particle swarm optimizer based on maximal information coefficient for many-objective problems［J］.Neurocomputing，2018，281（15）：1-11.

MANGAI U G，SAMANTA S，DAS S，et al.A survey of decision fusion and feature fusion strategies for pattern classification［J］.IETE Technical Review，2010，27（4）：293-307.

高爽.齿轮故障特征参数提取及最佳特征参数选择研究［D］.沈阳：沈阳航空航天大学，2017：20-25.

GAO Shuang.Research on gear fault feature parameter extraction and optimum feature parameter selection［D］.Shenyang：Shenyang Aerospace University，2017：20-25.

WEI F，WANG G，REN B，et al.Multisensor fused fault diagnosis for rotation machinery based on supervised second-order tensor locality preserving projection and weighted K-nearest neighbor classifier under assembled matrix distance metric［J］.Shock and Vibration，2016：1-14.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Fault Diagnosis of Vehicle Gearbox based on Support Vector Machine Optimized by Improved Beetle Antennae Search

Gear Fault Diagnosis Method based on Variational Modal Decomposition and Symbol Entropy

Gearbox Fault Diagnosis Method Based on Improved Multi-Scale Mean Permutation Entropy and Parameter Optimization SVM

Study on the Intelligent Fault Recognition Algorithm for Wind Power Unit Drivetrain

Gear Fault Diagnosis based on Feature Fusion and Sparse Representation

Related Author

No data

Related Institution

College of Automotive Technology，Zhejiang Technical Institute of Economics

School of Mechatronics Engineering，Nanjing Forestry University

Engineering Training Center，Nanjing Forestry University

Department of Mechanical Engineering， Tianjin Polytechnic College

Chongqing University， College of Mechanical Engineering

⁰