多源稀疏优化方法研究及其在齿轮箱复合故障检测中的应用

doi:10.3901/JME.2021.07.087

机械工程学报 ›› 2021, Vol. 57 ›› Issue (7): 87-99.doi: 10.3901/JME.2021.07.087

扫码分享

多源稀疏优化方法研究及其在齿轮箱复合故障检测中的应用

黄伟国¹, 李仕俊¹, 毛磊², 马玉强³, 王俊¹, 沈长青¹, 阙红波³, 朱忠奎¹

1. 苏州大学轨道交通学院苏州 215131;
2. 中国科学技术大学精密机械与精密仪器系合肥 230027;
3. 中车戚墅堰机车车辆工艺研究所有限公司常州 213011

收稿日期:2020-05-08 修回日期:2020-12-01 出版日期:2021-04-05 发布日期:2021-05-25
通讯作者: 朱忠奎(通信作者),男,1974年出生,博士,教授,博士研究生导师。主要研究方向为机械设备故障诊断,车辆系统动力学与控制,测试技术与信号处理。E-mail:zhuzhongkui@suda.edu.cn
作者简介:黄伟国，男，1981年出生，博士，教授，博士生导师。主要研究方向为机械设备状态监测与故障诊断，信号特征提取方法。E-mail：wghuang@suda.edu.cn;李仕俊，男，1995年出生，硕士研究生。主要研究方向为机械设备状态监测与故障诊断研究，信号特征提取方法研究。E-mail：sjli526@stu.suda.edu.cn;毛磊，男，1982年出生，博士，研究员，博士生导师。主要研究方向为无损检测技术，设备状态监测，故障诊断与预测性维护。Email：leimao82@ustc.edu.cn;马玉强，男，1982年出生，硕士，高级工程师，主要研究方向为轨道交通齿轮传动系统试验技术研究。Email：mayuqiang.qs@crrcgc.cc;王俊，男，1987年出生，博士，副教授。主要研究方向为机电系统动态监控，故障诊断与智能维护。E-mail：junking@suda.edu.cn;沈长青，男，1987年出生，博士，副教授。主要研究方向为机械故障诊断与寿命预测。E-mail：cqshen@suda.edu.cn;阙红波，男，1980年出生，硕士，正高级工程师。主要研究方向为轨道交通齿轮传动技术研究。E-mail：quehongbo.qs@crrcgc.cc
基金资助:
国家自然科学基金(52075353，51875376，51805342)和江苏省自然科学基金(BK20180842)资助项目。

Research on Multi-source Sparse Optimization Method and Its Application in Compound Fault Detection of Gearbox

HUANG Weiguo¹, LI Shijun¹, MAO Lei², MA Yuqiang³, WANG Jun¹, SHEN Changqing¹, QUE Hongbo³, ZHU Zhongkui¹

1. School of Rail Transportation, Soochow University, Suzhou 215131;
2. Department of PMPI, University of Science and Technology of China, Hefei 230027;
3. CRRC Qishuyan Institute Co., Ltd., Changzhou 213011

Received:2020-05-08 Revised:2020-12-01 Online:2021-04-05 Published:2021-05-25

摘要/Abstract

摘要： 齿轮箱因其工作环境恶劣，极易出现复合故障，其故障振动信号往往包含多种成分且伴随着强烈的背景噪声，给齿轮箱故障诊断带来了很大的困难。稀疏分解能够在强背景噪声下有效地提取微弱故障特征，针对传统稀疏分解方法存在信号保真能力欠缺，目标函数非凸导致局部最优解，模型通用性差等问题，基于广义极小极大凹(Generalized minimax concave,GMC)惩罚函数推导构建了具有保凸性的多源稀疏优化目标函数，并利用前向后向分裂(Forward-backward splitting,FBS)算法，基于Laplace小波字典，Morlet小波字典与DFT字典分别求解轴承瞬态成分，齿轮瞬态成分，谐波成分的稀疏表示，最终实现各成分的准确提取。仿真信号和试验信号的分析均验证了所提出的模型能够在不需要故障具体数目的先验知识下，准确实现齿轮箱复合故障的信号分解和故障诊断。

关键词: 齿轮箱, 复合故障诊断, 稀疏分解, 凸优化

Abstract: Gearbox is prone to compound fault because of its harsh working environment. The fault vibration signal of gearbox often contains multiple components and is corrupted by heavy background noise, which brings great difficulties to gearbox fault diagnosis. Weak fault features corrupted by heavy background noise can be effectively extracted through sparse decomposition. In order to solve the problems of traditional sparse decomposition method, such as the lack of signal fidelity, the local optimal solution caused by the non-convex objective function, and the poor universality of the model, a multi-source sparse optimization objective function with convexity is constructed based on the generalized minimax concave penalty function. Then the sparse coefficients of bearing transient components, gear transient components and harmonic components are calculated respectively based on Laplace wavelet dictionary, Morlet wavelet dictionary and DFT dictionary using forward backward splitting algorithm. Finally, each component can be extracted based on these sparse coefficients. The analysis of simulation signal and experimental signal verify that the proposed model can realize the accurate decomposition of compound fault signal and compound fault diagnosis of gearbox without the prior knowledge of specific number of faults.

Key words: gearbox, compound fault diagnosis, sparse decomposition, convex optimization

中图分类号:

TH165
TN911

黄伟国, 李仕俊, 毛磊, 马玉强, 王俊, 沈长青, 阙红波, 朱忠奎. 多源稀疏优化方法研究及其在齿轮箱复合故障检测中的应用[J]. 机械工程学报, 2021, 57(7): 87-99.

HUANG Weiguo, LI Shijun, MAO Lei, MA Yuqiang, WANG Jun, SHEN Changqing, QUE Hongbo, ZHU Zhongkui. Research on Multi-source Sparse Optimization Method and Its Application in Compound Fault Detection of Gearbox[J]. Journal of Mechanical Engineering, 2021, 57(7): 87-99.

参考文献

[1] WANG L,CAI G,YOU W,et al. Transients extraction based on averaged random orthogonal matching pursuit algorithm for machinery fault diagnosis[J]. IEEE Transactions on Instrumentation and Measurement,2017,66(12):3237-3248.
[2] LIN H,WU F,HE G. Rolling bearing fault diagnosis using impulse feature enhancement and nonconvex regularization[J]. Mechanical Systems and Signal Processing,2020,142,106790. Doi:10.1016/j.ymssp.2020.106790.
[3] 李永焯,丁康,何国林,等. 齿轮系统振动响应信号调制边频带产生机理[J]. 机械工程学报,2018,54(5):105-112. LI Yongzhuo,DING Kang,HE Guolin,et al. Modulation sidebands of the vibration signal of gearbox[J]. Journal of Mechanical Engineering,2018,54(5):105-112.
[4] YANG X,DING K,HE G,et al. Double-dictionary signal decomposition method based on split augmented Lagrangian shrinkage algorithm and its application in gearbox hybrid faults diagnosis[J]. Journal of Sound and Vibration,2018,432:484-501.
[5] 李庆,LIANG S Y. 非凸罚正则化稀疏低秩矩阵的大型减速机圆锥滚子轴承微弱故障诊断[J]. 机械工程学报,2018,54(23):102-111. LI Qing,LIANG S Y. Incipient fault diagnosis for large reducer taper roller bearings based on non-convex penalty regularization sparse low-rank matrix approach[J]. Journal of Mechanical Engineering,2018,54(23):102-111.
[6] LI N,HUANG W,GUO W,et al. Multiple enhanced sparse decomposition for gearbox compound fault diagnosis[J]. IEEE Transactions on Instrumentation and Measurement,2019,69(3):770-781.
[7] 樊薇,李双,蔡改改,等. 瞬态成分Laplace小波稀疏表示及其轴承故障特征提取应用[J]. 机械工程学报,2015,51(15):110-118. FAN Wei,LI Shuang,CAI Gaigai,et al. Sparse representation for transients in Laplace wavelet basis and its application in feature extraction of bearing fault[J]. Journal of Mechanical Engineering,2015,51(15):110-118.
[8] HE W,CHEN B,ZENG N,et al. Sparsity-based signal extraction using dual Q-factors for gearbox fault detection[J]. ISA Transactions,2018,79:147-160.
[9] HUANG W,LI S,FU X,et al. Transient extraction based on minimax concave regularized sparse representation for gear fault diagnosis[J]. Measurement,2019,151. DOI:10.1016/j.measurement.2019.107273.
[10] WANG S,SELESNICK I,CAI G,et al. Nonconvex sparse regularization and convex optimization for bearing fault diagnosis[J]. IEEE Transactions on Industrial Electronics,2018,65(9):7332-7342.
[11] CAI G,SELESNICK I,WANG S,et al. Sparsity-enhanced signal decomposition via generalized minimax-concave penalty for gearbox fault diagnosis[J]. Journal of Sound and Vibration,2018,432:213-234.
[12] ZHAO Z,WANG S,AN B,et al. Hierarchical hyper-Laplacian prior for weak fault feature enhancement[J]. ISA Transactions,2019,96:429-443.
[13] AN B,ZhAO Z,WANG S,et al. Sparsity-assisted bearing fault diagnosis using multiscale period group lasso[J]. ISA Transactions,2019,98:338-348.
[14] 王华庆,任帮月,宋浏阳,等. 基于终止准则改进K-SVD字典学习的稀疏表示特征增强方法[J]. 机械工程学报,2019,55(7):35-43. WANG Huaqing,REN Bangyue,SONG Liuyang,et al. Sparse representation method based on termination criteria improved K-SVD dictionary learning for feature enhancement[J]. Journal of Mechanical Engineering,2019,55(7):35-43.
[15] ZHOU H,LI H,LIU T,et al. A weak fault feature extraction of rolling element bearing based on attenuated cosine dictionaries and sparse feature sign search[J]. ISA Transactions,2019,97:143-154.
[16] ZHAO Z,WU S,QIAO B,et al. Enhanced sparse period-group lasso for bearing fault diagnosis[J]. IEEE Transactions on Industrial Electronics,2019,66(3):2143-2153.
[17] ZHAO Z,WANG S,SUN C,et al. Sparse multiperiod group lasso for bearing multifault diagnosis[J]. IEEE Transactions on Instrumentation and Measurement,2019,69(2):419-431.
[18] SELESNICK I. Sparse regularization via convex analysis[J]. IEEE Transactions on Signal Processing, 2017,65(17):4481-4494.
[19] WANG S,SELESNICK I,CAI G,et al. Synthesis versus analysis priors via generalized minimax- concave penalty for sparsity-assisted machinery fault diagnosis[J]. Mechanical Systems and Signal Processing,2019,127:202-233.
[20] WANG L,CAI G,WANG J,et al. Dual-enhanced sparse decomposition for wind turbine gearbox fault diagnosis[J]. IEEE Transactions on Instrumentation and Measurement,2018,68(2):450-461.

多源稀疏优化方法研究及其在齿轮箱复合故障检测中的应用

Research on Multi-source Sparse Optimization Method and Its Application in Compound Fault Detection of Gearbox

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	叶壮, 余建波. 基于多通道加权卷积神经网络的齿轮箱振动信号特征提取[J]. 机械工程学报, 2021, 57(1): 110-120.
[2]	周兴康, 余建波. 基于深度一维残差卷积自编码网络的齿轮箱故障诊断[J]. 机械工程学报, 2020, 56(7): 96-108.
[3]	熊鹏, 汤宝平, 邓蕾, 赵明航. 基于动态加权密集连接卷积网络的变转速行星齿轮箱故障诊断[J]. 机械工程学报, 2019, 55(7): 52-57.
[4]	胡茑庆, 陈徽鹏, 程哲, 张伦, 张宇. 基于经验模态分解和深度卷积神经网络的行星齿轮箱故障诊断方法[J]. 机械工程学报, 2019, 55(7): 9-18.
[5]	滕儒民, 李玉鑫, 王欣, 赵哲. 基于凸优化的举高消防车时间最优轨迹规划[J]. 机械工程学报, 2019, 55(6): 138-144.
[6]	吴淑明, 胡海峰, 赵志斌, 杨志勃, 杨来浩, 田绍华, 陈雪峰. 增强稀疏分解及其在叶片振动参数识别中的应用[J]. 机械工程学报, 2019, 55(19): 19-27.
[7]	胡超凡, 王衍学. 基于张量分解的滚动轴承复合故障多通道信号降噪方法研究[J]. 机械工程学报, 2019, 55(12): 50-57.
[8]	李广全, 王文静, 杨广雪. 高速列车齿轮箱载荷特性分析[J]. 机械工程学报, 2018, 54(4): 270-277.
[9]	刘镇星, 刘占生, 于香宇, 庞学佳. 舰船摇摆作用下滑动轴承-齿轮副系统动力学分析[J]. 机械工程学报, 2018, 54(17): 226-234.
[10]	张涛, 李强, 王曦, 王斌杰. 高速列车齿轮箱箱体在位模态识别[J]. 机械工程学报, 2018, 54(12): 31-41.
[11]	林腾蛟, 曹洪, 谭自然, 何泽银, 吕和生. 四级行星齿轮减速器耦合系统动态性能优化[J]. 机械工程学报, 2018, 54(11): 161-171.
[12]	李广全, 刘志明, 王文静, 杨广雪. 高速动车组齿轮箱疲劳裂纹机理分析研究^*[J]. 机械工程学报, 2017, 53(2): 99-105.
[13]	宋传学, 周放, 肖峰, 常成, 邵玉龙. 基于凸优化的车载复合电源参数匹配[J]. 机械工程学报, 2017, 53(16): 44-51.
[14]	黄奕宏, 丁康, 何国林. 行星传动系统振动信号数学模型及特征频率分析[J]. 机械工程学报, 2016, 52(7): 46-53.
[15]	黄文涛, 付强, 窦宏印. 基于自适应优化品质因子的共振稀疏分解方法及其在行星齿轮箱复合故障诊断中的应用^*[J]. 机械工程学报, 2016, 52(15): 44-51.