基于内燃机振动信号的可视化识别诊断

Abstract
Figure/Table
References (19)
Related Citation (15)

Download: PDF (1471 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract In order to improve the accuracy and real-time of IC engine fault identification and diagnosis, and solve the difficulty of feature extraction for IC engine multi-component and non-stationary vibration signals effectively, a visual fault diagnosis method for IC engine vibration signals based on improved local binary pattern(ILBP) and two directional-two dimensional principal component analysis(TD-2DPCA) was proposed.Firstly，aiming at the problem of low time-frequency resolution and cross-interference in the analysis of IC engine vibration signals by the traditional method, the empirical wavelet transform(EWT) and synchro-squeezing wavelet transform(SST) were applied to the time-frequency representation of IC engine vibration signals.Secondly, the texture feature of the image was extracted by ILBP and TD-2DPCA was used to reduce the dimension of an ILBP texture image.The feature parameters of the image were obtained by vectorizing the coding matrix.Last, the feature vectors were trained and tested by support vector machine(SVM) and nearest neighbor classifier(NNC) respectively to realize the fault diagnosis of the IC engine.In the identification and diagnosis test of cylinder head vibration signals under 8 working conditions of the IC engine, higher classification accuracy was obtained.Through reasonable optimization of the parameters, the classification rate is guaranteed and the highest recognition rate reaches 96.67%.Compared with other methods, the effectiveness of this method in IC engine fault diagnosis was fully demonstrated.

Key words： IC engine fault diagnosis time-frequency analysis feature extraction recognition rate

Received: 22 May 2018 Published: 15 December 2019

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	CAI Yanping1
	2
	XU Guanghua1
	3
	ZHANG Heng2
	FAN Yu2
	LI Aihua2

Cite this article:

CAI Yanping1,2,XU Guanghua1, et al. Visual identification and diagnosis based on IC engine vibration signals[J]. JOURNAL OF VIBRATION AND SHOCK, 2019, 38(24): 150-157.

URL:

http://jvs.sjtu.edu.cn/EN/ OR http://jvs.sjtu.edu.cn/EN/Y2019/V38/I24/150

        [1] 牟伟杰, 石林锁, 等. 基于KVMD-PWVD与LNMF的内燃机振动谱图像识别诊断方法[J]. 振动与冲击, 2017, 36
(2): 45-51.
MU Wei-jie, SHI Lin-suo, et al. IC Engine Fault Diagnosis Method Based KVMD-PWVD and LNMF[J]. Journal of Vibration and Shock, 振动与冲击, 2017, 36(2): 45-51.
[2] 蔡艳平, 李艾华, 王涛, 等. 基于时频谱图与图像分割的柴油机故障诊断[J]. 内燃机学报, 2011, 29(2): 181-186.
CAI Yan-ping, LI Ai-hua, WANG Tao, et al. IC Diesel Engine Fault Diagnosis Based on Time-Frequency Spectrum Image and Image Segmentation [J]. Transactions of CSICE, 2011, 29(2): 181-186．
[3] 刘昱, 张俊红, 毕凤荣, 等. 基于Wigner分布和分形维数的柴油机故障诊断[J]. 振动、测试与诊断, 2016, 36 (2): 240-245.
LIU Yu, ZHANG Jun-hong, BI Feng-rong, et al. Study on fault diagnosis of diesel valve trains based on Wigner distribution and fractal dimension[J]. Journal of Vibration, Measurement & Diagnosis, 2016, 36(2):240-245.
[4] 岳应娟, 孙纲, 等. 内燃机KVMD-MHD振动谱图表征与TD-2DPCA编码特征诊断方法研究[J]. 振动工程学报, 2017, 30(4): 688-696.
      YUE Ying-juan, SUN Gang, et al. KVMD-MHD vibration spectrum representation of internal combustion engine and TD-2DPCA coding diagnosis method. [J]. Journal of Vibr-
ation Engineering, 2017, 30(4): 688-696.
[5] 沈虹, 赵红东, 梅检民, 等. 基于高阶累积量图像特征的柴油机故障诊断研究[J]. 振动与冲击, 2015, 34(11): 133-138.
SHEN Hong, ZHAO Hong-dong, MEI Jian-min, et al. Dies-el engine fault diagnosis based on high-order cumulant ima-ge features[J]. Journal of Vibration and Shock, 2015, 34(11): 133-138.
[6] GILLES J. Empirical Wavelet Transform [J]. IEEE Transa-ctions On Signal Processing, 2013, 61(16): 3999-4010.
[7] Anjiana Francis, C. Muruganantham. Empirical Wavelet   Transform and its Application [J]. International Journal of Electrical, Electronics and Communication Engineering, 2015, 1(1): 1-3.
[8] Anjana Francis, C.Muruganantham.An Adaptive Denoising Method using Empirical Wavelet Transform[J].International Journal of Computer Applications, 2015, 117(21):18-20.
[9] DAUBECHIES I, LU Jian-feng,WU HT.Syn-chrosqueezed Wavelet Transforms:an Empirical Mode Decomposition-like tool [J]. Applied and Computational Harmonic Analysis
, 2011, 30: 243-261.
[10] LI Chuan, LIANG Ming. Time-frequency Signal Analysis for Gearbox Fault Diagnosis Using a Generalized Synchro-squeezing Transform [J]. Mechanical Systems and Signal Processing, 2012, 26(1):205-217.
[11] 刘义亚, 李可, 陈鹏. 基于同步压缩小波变换的滚动轴承故障诊断[J]. 中国机械工程, 2018, 29(5):585-590.
      LIU Yi-ya, LI Ke, CHEN Peng. Fault diagnosis for Rolling bearings based on Synchrospueezing on Wavelet Transform [J].China Mechanical Engineering, 2018,29: 585-590.
[12] Ojala T, Pietikainen M, Harwood D. A comparative study of texture measures with classification based on featured distributions. Pattern Recognition, 1996, 29(1): 51-59.
[13] 岳应娟, 王旭, 等. 内燃机变分模态Rihaczek谱纹理特征识别诊断[J]. 仪器仪表学报, 2017,38(10): 2437-2445.
         YUE Ying-juan, WANG Xu, et al. Internal combustion engine fault diagnosis based on identification of variational modal Rihaczek spectrum texture characterization[J].Chinese Journal of Scientific Instrument, 2017,38(10): 2437-2445.
[14] AREZOU C, MEHRAN E. Face detection using fusion of LBP and AdaBoost [J]. Journal of Soft Computing and Applications, 2016(1): 1-10.
[15] 袁宝华, 王欢, 任明武. LBP与LNMF特征融合的人脸识别[J]. 计算机工程与应用, 2013, 49(5):166-169.
YUAN Bao-hua,WANG Huan, Ren Ming-wu. Fusing local binary pattern and LNMF of face recognition[J]. Computer Engineering and Application, 2013, 49(5): 166-169.
[16] JIAN Yang, ZHANG D, Frangi A F, et al. Two-Dimensio-nal PCA: a new approach to appearance-based face repres-entation and recognition[J]. Pattern Analysis and Machine Intelligence, 2004, 26(1): 131-137.
[17] 李巍华, 林龙, 单外平.基于广义S变换与双向2DPCA
的轴承故障诊断[J]. 振动、测试与诊断, 2015, 35(3): 499-506.
LI Wei-hua, LIN Long, SHAN Wai-ping. Bearing fault diagnosis based on generalized S-transform and two direc-tional 2DPCA[J]. Journal of Vibration, Measurement & Diagnosis, 2015, 35(3): 499-506.
[18] LI Z X,YAN X P,TIAN Z,et al.Blind vibration component separation and nonlinear feature extraction applied to the non-stationary vibration signals for gearbox muti-fault   diagnosis [J]. Measurement, 2013, 46(1): 259-271.
[19] 王成栋, 张优云, 夏勇. 模糊函数图像在柴油机气阀故障诊断中的应用研究[J]. 内燃机学报, 2004, 22(4): 162 - 168.
WANG Cheng-dong, ZHANG You-yun, XIA Yong. Study on the use of ambiguity function images in fault diagnosis for diesel valve train[J]. Transaction of CSICE, 2004, 22(4): 162-168.