您好,欢迎来到中国测试科技资讯平台!

首页> 《中国测试》期刊 >本期导读>基于VMD-多尺度排列熵和SVM的船用空压机故障诊断方法

基于VMD-多尺度排列熵和SVM的船用空压机故障诊断方法

308    2024-06-26

¥0.50

全文售价

作者:胡以怀1, 李从跃1, 沈威1, 崔德馨1, 张成2, 芮晓松2

作者单位:1. 上海海事大学,上海 201306;
2. 招商局鼎衡造船有限公司,江苏 扬州 225217


关键词:船用往复式空压机;变分模态分解;多尺度排列熵;故障诊断


摘要:

船用机械振动信号存在非线性、非平稳性问题,故障特征难提取,通过变分模态分解(variational mode decomposition, VMD)多尺度排列熵(multiscale permutation entropy, MPE)与支持向量机(support vector machine, SVM)融合的故障诊断方法,对振动信号进行研究。以空压机为例,首先,模拟6种空压机工况,对各工况的热工参数进行测试,分析各工况热工参数的变化程度,并对采集的振动信号进行频域分析。然后通过VMD对振动信号进行分解,得到一系列固有模态分量,计算与原始信号的互相关系数筛选敏感固有模态分量。最后计算出敏感固有模态分量的多尺度排列熵,将其作为特征向量,输入到SVM中,进行故障辨识。实验结果表明:VMD多尺度排列熵与SVM融合的空压机故障辨识方法,能有效地识别故障类型,整体准确率可保持在98.6667%,将此方法与其他方法进行对比,证明此方法有效。


Fault diagnosis of marine air compressor based on VMD multi-scale permutation entropy and SVM
HU Yihuai1, LI Congyue1, SHEN Wei1, CUI Dexin1, ZHANG Cheng2, RUI Xiaosong2
1. Shanghai Maritime University, Shanghai 201306, China;
2. China Merchants Dingheng Shipbuilding Co., Ltd., Yangzhou 225217, China
Abstract: Marine machinery vibration signals have nonlinear and non-stationary problems, and fault features are difficult to extract. Through variational mode decomposition multiscale permutation entropy and support vector machine fusion fault diagnosis method to study the vibration signal. Taking the air compressor as an example, first, 6 kinds of air compressor working conditions are simulated, the thermal parameters of each working condition are tested, the degree of change of the thermal parameters of each working condition is analyzed, and the collected vibration signals are analyzed in the frequency domain. Then the vibration signal is decomposed by VMD to obtain a series of natural modal components, and the cross-correlation coefficient with the original signal is calculated to screen out the sensitive natural modal components. Finally, the multi-scale permutation entropy of the sensitive natural mode components is calculated, which is used as a feature vector and input into the SVM for fault identification. The experimental results show that the air compressor fault identification method based on the fusion of VMD multi-scale arrangement entropy and SVM can effectively identify the fault type, and the overall accuracy rate can be maintained at 98.6667%. The comparison of this method with other methods proves the effectiveness of this method.
Keywords: marine reciprocating air compressor; variational mode decomposition; multiscale permutation entropy; fault diagnosis
2024, 50(6):20-27 收稿日期: 2022-04-21;收到修改稿日期: 2022-07-09
基金项目: 上海市科技计划(20DZ2252300)
作者简介: 胡以怀(1964-),男,江苏高邮市人,教授,博士,研究方向为船舶动力装置振动分析、故障诊断、系统仿真及船舶新能源利用。
参考文献
[1] 杨丰源, 宋辉, 程序, 等. 基于改进EEMD和Cohen类的局部放电信号联合时频分析[J]. 高电压技术, 2016, 42(7): 2345-2352
YANG F Y, SONG H, CHENG X, et al. Analysis of joint time-frequency analysis on partial discharge signal based on improved EEMD and Cohen's class[J]. High Voltage Engineering, 2016, 42(7): 2345-2352
[2] 陈东宁, 张运东, 姚成玉, 等. 基于变分模态分解和多尺度排列熵的故障诊断[J]. 计算机集成制造系统, 2017, 23(12): 2604-2612
CHEN D N, ZHANG Y D, YAO C Y, et al. Fault diagnosis method based on variational mode decomposition and multi-scale permutation entropy[J]. Computer Integrated Manufacturing Systems, 2017, 23(12): 2604-2612
[3] 谢棕, 张丽萍. 基于参数优化VMD和多尺度排列熵的齿轮故障诊断[J]. 机械制造与自动化, 2021, 50(6): 114-117
XIE Z, ZHANG L P. Gear fault diagnosis based on parameter optimization VMD and multi-scale permutation entropy[J]. Machine Building & Automation, 2021, 50(6): 114-117
[4] 唐蕾, 黄天立, 万熹. 基于变分模态分解和同步提取变换识别时变结构瞬时频率[J]. 振动与冲击, 2022, 41(6): 197-205
TANG L, HUANG T L, WAN X. Instantaneous frequency identification of time-varying structures using variational mode decomposition and synchroextracting transform[J]. Journal of Vibration and Shock, 2022, 41(6): 197-205
[5] WANG D Y, LUO H Y, GRUNDER O, et al. Multi-step ahead wind speed forecasting using an improved wavelet neural network combining variational mode decomposition and phase space reconstruction[J]. Renewable Energy, 2017, 113: 1345-1358
[6] HAN T, JIANG D X. Rolling bearing fault diagnostic method based on VMD-AR model and random forest classifier[J]. Shock and Vibration, 2016(6): 5132046.
[7] SUN W, GAO Q. Short-term wind speed prediction based on variational mode decomposition and linear-nonlinear combination optimization model[J]. Energies, 2019, 12(12): 1-27
[8] LI J C, ZHU S W, WU Q Q. Monthly crude oil spot price forecasting using variational mode decomposition[J]. Energy Economics, 2019, 83: 240-253
[9] 李振璧, 张坤, 姜媛媛, 等. 基于变分模态分解与近似熵的输电线路两相接地故障诊断[J]. 科学技术与工程, 2018, 18(5): 70-75
LI Z B, ZHANG K, JIANG Y Y, et al. Two-phase grounding fault diagnosis of transmission lines based on variational mode decomposition and approximate entropy[J]. Science Technology and Engineering, 2018, 18(5): 70-75
[10] 邹瑛珂, 李祖明, 刘晓宏, 等. 基于VMD分解的MFCC+GFCC无人机噪音混合特征提取方法[J]. 中国测试, 2021, 47(11): 141-146
ZOU Y K, LI Z M, LIU X H, et al. Hybrid feature extraction method of MFCC + GFCC UAV noise based on VMD decomposition[J]. China Measurement & Test, 2021, 47(11): 141-146
[11] 张燕霞, 户文刚. 基于VMD-SVD和SVM的旋转机械故障诊断研究[J]. 机电工程, 2022, 39(3): 324-329
ZHANG Y X, HU W G. Fault diagnosis of rotating machinery based on VMD-SVD and SVM[J]. Mechanical & Electrical Engineering Magazine, 2022, 39(3): 324-329
[12] 杜佳耘, 雷勇, 李永凯, 等. 基于参数优化变分模态分解的混合储能功率分配策略[J]. 现代电力, 2021, 38(1): 51-59
DU J Y, LEI Y, LI Y K, et al. Hybrid energy storage strategy based on parameter optimized variational mode decomposition[J]. Modern Electric Power, 2021, 38(1): 51-59
[13] 卢鹏, 年圣全, 邹国良, 等. 基于变分模态分解和注意力机制的浪高预测[J]. 海洋测绘, 2021, 41(2): 34-39
LU P, NIAN S Q, ZOU G L, et al. Wave height prediction based on variational mode decomposition and attention mechanism[J]. Hydrographic Surveying and Charting, 2021, 41(2): 34-39
[14] BANDT C, POMPE B. Permutation entropy: A natural complexity measure for time series[J]. Physical Review Letters, The American Physiological Society, 2002, 88(17): 174102
[15] 郑近德, 程军圣, 杨宇. 多尺度排列熵及其在滚动轴承故障诊断中的应用[J]. 中国机械工程, 2013, 24(19): 2641-2646
ZHENG J D, CHENG J S, YANG Y. Multi-scale permutation entropy and its applications to rolling bearing fault diagnosis[J]. China Mechanical Engineering, 2013, 24(19): 2641-2646
[16] 姚文坡, 刘铁兵, 戴加飞, 等. 脑电信号的多尺度排列熵分析[J]. 物理学报, 2014, 63(7): 427-433
[17] 王伯昕, 杨海涛, 王清, 等. 基于补充改进集合经验模态分析法-多尺度排列熵分析桥梁振动信号优化滤波方法[J]. 吉林大学学报(工学版), 2020, 50(1): 216-226
WANG B X, YANG H T, WANG Q, et al. Bridge vibration signal optimization filtering method based on improved CEEMD-multi-scale permutation entropy analysis[J]. Journal of Jilin University(Engineering and Technology Edition), 2020, 50(1): 216-226
[18] 赵建岗, 宁静, 宁云志, 等. 基于多尺度排列熵和线性局部切空间排列的机械故障诊断特征提取[J]. 振动与冲击, 2021, 40(13): 136-145
ZHAO J G, NING J, NING Y Z, et al. Feature extraction of mechanical fault diagnosis based on MPE-LLTSA[J]. Journal of Vibration and Shock, 2021, 40(13): 136-145
[19] 王泽, 王红军. 基于多尺度排列熵的滚动轴承故障特征提取[J]. 组合机床与自动化加工技术, 2020(8): 30-34
WANG Z, WANG H J. Fault feature extraction of rolling bearings based on multi-scale entropy[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2020(8): 30-34
[20] 蔡波, 黄晋英, 杜金波, 等. 基于MEEMD多特征融合与LS-SVM的行星齿轮箱故障诊断[J]. 中国测试, 2021, 47(9): 126-132
CAI B, HUANG J Y, DU J B, et al. Planetary gearbox fault diagnosis based on MEEMD multi-feature fusion and LS-SVM[J]. China Measurement & Test, 2021, 47(9): 126-132