基于香农熵特征的发动机故障诊断方法

摘要
图/表
参考文献(16)
相关文章 (15)

全文: PDF (1164 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要本文通过分析活塞销在不同配合间隙下的运行轨迹，针对活塞销敲击响产生缸盖振动信号的有序性和在频率成分上的差异性，并考虑到实验数据的有限性，提出了用香农熵选取小波包子信号的特征提取方法和支持向量机的故障诊断方法。将振动信号进行小波包分解并求出各子信号的香农熵，根据香农熵的大小选取出合适的子信号进行分析研究，求出子信号的能量作为特征值，用支持向量机对活塞销不同程度的故障进行分类识别。诊断结果表明：用香农熵选取小波包子信号结合支持向量机的方法能够对活塞销不同程度的故障进行分类识别。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章

关键词 ：香农熵, 小波包, 支持向量机, 故障诊断

Abstract：Here, through analyzing operational trajectories of a piston pin under different fit clearances, aiming at the orderliness of cylinder cover vibration signals generated due to striking the piston pin and their difference in frequency components, considering the finiteness of test data, a method for choosing a wavelet packet’s sub-signals with Shannon entropy, extracting their features and then diagnosing faults with SVM was proposed.Firstly, a vibration signal of the piston pin was decomposed into several sub-signals with the wavelet packet transform and Shannon entropy of each sub-signal was calculated.According to Shannon entropy values, appropriate sub-signals were chosen and their energy was calculated and taken as their features.A support vector machine (SVM) was used to classify the piston pin’s different faults.The diagnosis test results showed that the proposed method can be used to identify and classify different faults of the piston pin.

Key words： Shannon entropy wavelet packet support vector machine fault diagnosis

收稿日期: 2017-11-29 出版日期: 2018-10-28

引用本文:

丁雷1，曾锐利2，沈虹2，赵慧敏2，曾荣1. 基于香农熵特征的发动机故障诊断方法[J]. 振动与冲击, 2018, 37(21): 233-239.
DING Lei 1 ZENG Ruili 2 SHEN Hong 2 ZHAO Huimin2 ZENG Rong 1. An engine fault diagnosis method based on Shannon entropy features. JOURNAL OF VIBRATION AND SHOCK, 2018, 37(21): 233-239.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2018/V37/I21/233

[1] 夏天,王新晴,肖云魁.基于高阶循环平稳的柴油发动机活塞销振动信号分析[J].中国机械工程,2010,21(12):1410-1413.
XIA Tian, WANG Xin-qing, XIAO Yun-kui. Analysis of Vibration Signals of Piston Pin in Diesel Engine Based on Higher Order Cyclostationarity[J]. Chinese Mechanical Engineering, 2010, 21(12):1410-1413.
[2] 肖云魁,李会梁,王保民.基于双谱的柴油发动机活塞销故障诊断[J].振动与冲击,2008,26(4):369-373.
XIAO Yun-kui, LI Hui-liang, WANG Bao-ming. Bispectrum Analysis of Fault Diagnostics of Piston-Pin of Diesel Engine[J]. Vibration and Shock, 2008,26(4):369-373.
[3] Yu L, Junhong Z, Fengrong B, et al. A fault diagnosis approach for diesel engine valve train based on improved ITD and SDAG-RVM[J]. Measurement Science & Technology, 2015, 26(2).
[4] Tamura M, Saito H, Murata Y, Kokubu K and Morimoto S 2011 Misfire detection on internal combustion engines using exhaust gas temperature with low sampling rate Appl. Therm. Eng. 31 4125–31.
[5] 白欣,黄博,王立臣.基于虚拟样机的发动机活塞销故障诊断研究[J].汽车技术,2005(4):20-23.
BAI Xin, HUANG Bo, Wang Li-chen. Study on Virtual-Prototype-Based Failure Diagnosis of Engine Piston Pin[J]. Automotive Technology, 2005(4):20-23.
[6] 刘发生.双谱柴油发动机活塞销故障诊断及应对措施探讨[J].科技风,2013(6):260-260.
LIU Fa-sheng. Discussion on Countermeasures about Fault Diagnosis of Piston Pin of Bispectral Diesel Engine and Countermeasures[J]. Technology Wind, 2013(6):260-260.
[7] 肖云魁,李世义,王建新,等.基于小波包—于小谱技术提取柴油发动机曲轴轴承故障特征[J].北京理工大学学报.2004,24(6):508-511.
XIAO Yun-kui, Li S Y, Wang J X. Fault Feature Extraction of Diesel Engine Crankshaft Bearing Based on Wavelet Packet-AR spectroscopy[J]. Journal of Beijing Institute of Technology, 2004,24(6):508-511.
[8] Ahmadi H, Tafreshi R, Sassani F, et al. On the Performance of Informative Wavelets for Classification and Diagnosis of Machine Faults[A]. In: Tang Y T, WAA 2001, LNCS 2251[C]. Germany: Springer-Verlag Berlin Heidelberg,2001,369-381.
[9] 丁恒远,肖云魁.汽车发动机活塞销异响分析[J].汽车运输,2000(7):31-35.
DING Heng-yuan, XIAO Yun-kui. Analysis of Automobile Engine Piston Pin Knocking[J]. Vehicle Transport. 2000(7):31-35.
[10] Antoni J, Daniere J, Guillet F. Effective Vibration Analysis of IC Engines Using Cyclostationarity. Part I: a Methodology for Condition Monitoring[J]. Journal of Sound and Vibration,2002,257(5):815-837.
[11] 李真.熵选择IMF分量的滚动轴承故障诊断方法[D].北京交通大学,2014.
LI Zhen. Fault Diagnosis Method of Rolling Bearing Based on Entropy selecting the IMF Component[D]. Beijing Jiaotong University, 2014.
[12] 胡志勇,牛家骅.基于时域能量划分和PSO-SVM的发动机故障诊断[J].汽车工程，2016,38(1):86-90.
HU Zhi-yong, LIU Jia-hua, Engine Fault Diagnosis Based on Time-domain Energy Division and PSO-SVM Algorithm[J]. Automobile Engineering, 2016, 38(1):86-90.
[13] 陈杰.基于支持向量机的柴油机故障诊断技术研究[D].武汉理工大学,2012.
Chen Jie. Research on Diesel Engine Fault Diagnosis Technology Based on Support Vector Machine[J]. Wuhan University of Technology, 2012.
[14] 张玲玲,肖静.基于MATLAB的机械故障诊断技术案例教程[M].高等教育出版社,2016,215-216.
ZhANG Ling-ling, XIAO Jin. Case Study of Mechanical Fault Diagnosis Technology Based on MATLAB[M]. Higher Education Press, 2016,215-216.
[15] 周斌,王保民,梅检民.基于小波包分解的柴油
机异响故障特征提取与诊断[J].军事交通学院学报,2009,11(2):30-34.
ZHOU Bin, WANG Bao-min, MEI Jian-min. Feature Extraction and Diagnosis on the Abnormal Sound Faults of Diesel Engine Based on the Wavelet Packet[J]. Journal of Military Transportation University, 2009,11(2):30-34.
[16] 徐玉秀,杨文平,吕轩,等.基于支持向量机的汽车发动机故障诊断研究[J].振动与冲击,2013,32(8):143-146.
XU Yu-xiu, YANG Wen-ping, LV Xuan. Research on Automotive Engine Fault Diagnosis Based on Support Vector Machine[J]. Vibration and Shock, 2013,32(8):143-146.