自适应谱减声发射消噪及轴承故障诊断

doi:10.16180/j.cnki.issn1007-7820.2019.04.004

摘要/Abstract

摘要：

对轴承进行声发射信号分析时,环境噪声会使信号能量波动,从而导致后期故障诊断失误。引入谱减法可以对声发射信号进行预先消噪,增强声信号的稳定性。但是谱减法对非平稳信号的处理性能不足,需对其进行谱减系数修正,并利用遗传算法对谱减系数(m,λ)全局优化。实验结果表明,自适应谱减法能够得到更优质的谱减系数,并有效的消除相对小波包能量的异常波动。各种故障类型的能量特征经支持向量机训练后,准确率均能达到92%左右。

关键词: 故障诊断, 声发射, 谱减法, 遗传算法, 小波包变换, 支持向量机

Abstract:

When acoustic emission signals are analyzed for bearings, environmental noise causes signal energy to fluctuate, resulting in misdiagnosis of late failures. To solve the problem, a spectral subtraction method was introduced to pre-noise the acoustic emission signal to enhance the stability of signal. In view of the lack of processing performance of spectral subtraction for non-stationary signals, spectral subtraction coefficients were modified and genetic algorithm was used to optimize the spectral subtraction coefficients(m, λ) globally. Experiment showed that the adaptive spectral subtraction method could obtain better spectral subtraction coefficients, and the fluctuation of wavelet packet energy feature could be eliminated. After the SVM training for the energy features of various bearing faults, the accuracy rate could reach about 92%.

Key words: fault diagnosis, acoustic emission, spectral subtraction, genetic algorithm, wavelet packet transform, SVM

中图分类号:

TP368.1

朱望纯,程浩,高海英. 自适应谱减声发射消噪及轴承故障诊断[J]. 电子科技, 2019, 32(4): 16-20.

ZHU Wangchun,CHENG Hao,GAO Haiying. Adaptive Acoustic Emission Noise Elimination and Bearing Fault Diagnosis[J]. Electronic Science and Technology, 2019, 32(4): 16-20.

图/表 6

表1

表2

图1

图2

图3

表3

参考文献 16

[1]	Huang J, Lee H R, Ahn J H . Detection of bearing/rail defects for linear motion stage using acoustic emission[J]. International Journal of Precision Engineering and Manufacturing, 2013,14(11):2043-2046 doi: 10.1007/s12541-013-0256-y
[2]	许小刚, 王松岭, 刘锦廉 . 基于小波包能量分析及改进支持向量机的风机机械故障诊断[J]. 动力工程学报, 2013,33(8):606-612. doi: 10.3969/j.issn.1674-7607.2013.08.006
	Xu Xiaogang, Wang Songling, Liu Jinlian . Mechanical fault diagnosis of fan based on wavelet packet energy analysis and improved support vector machine[J]. Journal of Chinese Society of Power Engineering, 2013,33(8):606-612. doi: 10.3969/j.issn.1674-7607.2013.08.006
[3]	朱先和, 杨世平 . 基于小波变换对信号噪声的处理研究[J]. 电子科技, 2016,29(6):128-131. doi: 10.16180/j.cnki.issn1007-7820.2016.06.037
	Zhu Xianhe, Yang Shiping . Signal de-noising research based on wavelet transform[J]. Electronic Science and Technology, 2016,29(6):128-131. doi: 10.16180/j.cnki.issn1007-7820.2016.06.037
[4]	聂杰文, 徐明强, 王树青 . 基于小波消噪和希尔伯特黄变换的损伤检测技术研究[J]. 中国海洋大学学报, 2016,46(4):142-148. doi: 10.16441/j.cnki.hdxb.20140144
	Nie Jiewen, Xu Mingqiang, Wang Shuqing . Research on structural damage detection based on wavelet De-Noising and Hilbert-Huang transform[J]. Periodical of Ocean University of China, 2016,46(4):142-148. doi: 10.16441/j.cnki.hdxb.20140144
[5]	刘东瀛, 邓艾东, 刘振元 , 等. 基于EMD与相关系数原理的故障声发射信号降噪研究[J]. 振动与冲击, 2017,36(19):71-77. doi: 10.13465/j.cnki.jvs.2017.19.011
	Liu Dongying, Deng Aidong, Liu Zhenyuan , et al. De-noising method for fault acoustic emission signals based on the EMD and correlation coefficient[J]. Journal of Vibration and Shock, 2017,36(19):71-77. doi: 10.13465/j.cnki.jvs.2017.19.011
[6]	张瑞, 邓艾东, 司晓东 , 等. 一种新的声发射信号消噪及故障诊断方法[J]. 振动与冲击, 2018,37(4):75-81. doi: 10.13465/j.cnki.jvs.2018.04.012
	Zhang Rui, Deng Aidong, Si Xiaodong , et al. A new method for acoustic emission signal De-noised and fault diagnosis[J]. Journal of Vibration and Shock, 2018,37(4):75-81. doi: 10.13465/j.cnki.jvs.2018.04.012
[7]	张宇, 卢文秀, 褚福磊 . 基于声发射衰减特性的故障行星轮定位研究[J]. 振动与冲击, 2017,36(6):14-19. doi: 10.13465/j.cnki.jvs.2017.03.003
	Zhang Yu, Lu Wenxiu, Chu Fulei . Faulted planet gear positioning based on attenuation characteristics of AE signals[J]. Journal of Vibration and Shock, 2017,36(3):14-19. doi: 10.13465/j.cnki.jvs.2017.03.003
[8]	朱洁, 邓开发 . 基于改进小波包变换的音频指纹提取算法[J]. 电子科技, 2016,29(3):30-34. doi: 10.16180/j.cnki.issn1007-7820.2016.03.008
	Zhu Jie, Deng Kaifa. An approach to audio fingerprinting extraction based on improved wavelet packet[J]. Electronic Science and Technology, 2016,29(3):30-34. doi: 10.16180/j.cnki.issn1007-7820.2016.03.008
9	易子馗, 谭建平刘思思 . 基于改进谱减法和MFCC的电机异常噪声识别方法[J]. 微特电机, 2017,45(2):31-38. doi: 10.3969/j.issn.1004-7018.2017.02.008
	Yi Zikai, Tan Jianping, Liu Sisi . A window lift motor abnormal noise classification method based on improved spectral subtraction and MFCC[J]. Small & Special Electrical Machines, 2017,45(2):31-38. doi: 10.3969/j.issn.1004-7018.2017.02.008
[10]	Chen Z, Wang R, Yin F L . Speech dereverberation method based on spectral subtraction and spectral line enhancement[J]. Applied Acoustics, 2016,112(6):201-210. doi: 10.1016/j.apacoust.2016.05.017
[11]	崔璨, 袁英才 . 窗函数在信号处理中的应用[J]. 北京印刷学院学报, 2014,22(4):71-74. doi: 10.3969/j.issn.1004-8626.2014.04.029
	Cui Can, Yuan Yingcai . Application of window function in signal processing[J]. Journal of Beijing Institute of Graphic Communication, 2014,22(4):71-74. doi: 10.3969/j.issn.1004-8626.2014.04.029
[12]	齐立萍, 孙昊, 杨鹏 , 等. 基于参数自适应的改进谱减法[J]. 科学技术与工程, 2016,16(3):192-196.
	Qi Liping, Sun Hao, Yang Peng , et al. The spectral subtraction method based on adaptive parameters[J]. Science Technology and Engineering, 2016,16(3):192-196.
[13]	刘嘉敏, 彭玲, 刘军委 , 等. 遗传算法VMD参数优化与小波阈值轴承振动信号去噪分析[J]. 机械科学与技术, 2017,36(11):1-6. doi: 10.13433/j.cnki.1003-8728.2017.1110
	Liu Jiamin, Peng Ling, Liu Junwei , et al. Denoising analysis of bearing vibration signal based on genetic algorithm and wavelet threshold VMD[J]. Mechanical Science and Technology for Aerospace Engineering, 2017,36(11):1-6. doi: 10.13433/j.cnki.1003-8728.2017.1110
[14]	刘霞, 孙美岩, 薛海峰 , 等. 基于相关性小波奇异熵的滚动轴承故障特征提取[J]. 化工自动化及仪表, 2015(7):765-769.
	Liu Xia, Sun Meiyan, Xue Haifeng , et al. Rolling bearing fault feature extraction based on correlation of wavelet singular entropy[J].Control and Instruments in Chemical Industry, 2015(7):765-769.
[15]	付旻, 王炜, 王昊 , 等. 多分类支持向量机在公交换乘识别的应用[J]. 哈尔滨工业大学学报, 2018,50(3):1-8. doi: 10.11918/j.issn.0367-6234.201610057
	Fu Min, Wang Wei, Wang H , et al. Application of multi-class support vector machine in public transit transfer recognition[J]. Journal of Harbin Institute of Technology, 2018,50(3):1-8. doi: 10.11918/j.issn.0367-6234.201610057
[16]	曲健, 陈红岩, 刘文贞 , 等. 基于改进网格搜索法的支持向量机在气体定量分析中的应用[J]. 传感技术学报, 2015,28(5):78-82. doi: 10.3969/j.issn.1004-1699.2015.05.027
	Qu Jian, Chen Hongyan, Liu Wenzhen , et al. Application of support vector machine based on improved grid search in quantitative analysis of gas[J]. Chinese Journal of Sensors and Actuators, 2015,28(5):78-82. doi: 10.3969/j.issn.1004-1699.2015.05.027

SNR_i	m_B	λ_B	ρ
-12 dB	2.52	3.25	0.872
-11 dB	2.49	3.27	0.871
-10 dB	2.53	3.25	0.875
-9 dB	2.47	3.23	0.874
?	?	?	?
0 dB	2.23	3.11	0.870
?	?	?	?
9dB	1.94	2.02	0.863
10dB	1.92	2.04	0.871

优化方法	SNR_i	m_B	λ_B	ρ
实验优化	-10 dB	2.5	3.0	0.827
	0 dB	2.5	3.0	0.813
	10 dB	2.0	2.0	0.836
遗传算法优化	-10 dB	2.53	3.25	0.875
	0 dB	2.23	3.11	0.870
	10 dB	1.94	2.04	0.871

轴承状态类型	正常	内圈故障	外圈故障
消噪前准确率	61.4%	57.6%	54.5%
消噪后准确率	93.5%	90.3%	91.8%

[1]	伍伟嘉,杨俭,袁天辰,邵志慧. 基于支持向量机的轨道结构病害识别研究[J]. 电子科技, 2022, 35(2): 27-33.
[2]	金霄,吴飞,鄢松,陆雯霞,张忠艺. 基于GAWK-means的地铁车站指纹定位方法[J]. 电子科技, 2022, 35(2): 34-39.
[3]	邵志慧,杨俭,袁天辰,伍伟嘉. 基于排列熵和支持向量机的轨枕病害诊断[J]. 电子科技, 2022, 35(2): 52-58.
[4]	冯先丁,魏镜弢,吴张永,钱杰,浦友尚. 基于PCA-PSO-SVM的球磨机负荷预测研究[J]. 电子科技, 2022, 35(1): 29-34.
[5]	修晓波,李伯全,周峰. 基于遗传算法的温度传感器布置优化[J]. 电子科技, 2021, 34(9): 17-23.
[6]	王阳,王亚刚. 基于阶跃响应和遗传算法优化高阶加时滞模型的辨识方法[J]. 电子科技, 2021, 34(9): 41-46.
[7]	张朋飞,魏存伟,刘先康,刘安然,杨欧,林永霖. 窄带舰船目标识别方法研究[J]. 电子科技, 2021, 34(6): 50-55.
[8]	刘姝,邵杰,张颐婷,张善章. 基于双谱和谱特征的心电信号分类方法[J]. 电子科技, 2021, 34(5): 42-46.
[9]	闫书豪,乔美英. 基于一维WConv-BiLSTM的轴承故障诊断算法[J]. 电子科技, 2021, 34(4): 75-82.
[10]	仝兆景,秦紫霓,赵运星,芦彤,郑权. 基于贝叶斯网络的变压器故障诊断研究[J]. 电子科技, 2021, 34(3): 43-47.
[11]	彭荣杰,彭亚雄,陆安江. 基于改进PCA+SVM的人脸识别系统[J]. 电子科技, 2021, 34(12): 56-61.
[12]	陈胜利,王新掌,许孝卓. 永磁同步电机失磁故障电磁仿真分析[J]. 电子科技, 2021, 34(10): 32-37.
[13]	巨志勇,翟春宇,张文馨. 基于SVM与区域生长的彩色商品标签图像分割方法[J]. 电子科技, 2021, 34(10): 69-74.
[14]	金鑫,冯毅,尤雪汐,王佳欣. 基于机器学习的信息安全设备调配保障技术研究[J]. 电子科技, 2020, 33(8): 80-86.
[15]	万东燕,许桢英,杨卿,吴梦琪. 基于PCA与SVM的焊缝缺陷信号分类方法[J]. 电子科技, 2020, 33(5): 9-14.