基于VMD和SVD的柴油机气门间隙异常特征提取研究

PDF(1179 KB)

振动与冲击 ›› 2020, Vol. 39 ›› Issue (16) : 23-30.

论文

江志农1，魏东海1，张进杰2，茆志伟2

作者信息 +

A study on valve clearance anomaly feature extraction of diesel engines based on VMD and SVD

JIANG Zhinong1，WEI Donghai1，ZHANG Jinjie2，MAO Zhiwei2

Author information +

文章历史 +

摘要

为有效地从柴油机缸盖表面振动信号中提取气门间隙故障特征，提出一种基于变分模态分解（VMD）和奇异值分解（SVD）的特征提取新方法。采用VMD算法对缸盖振动信号进行分解，利用所得的模态分量构建特征矩阵。接着应用SVD理论将特征矩阵转变为表征频率特性的奇异值序列，探讨了稳定工况下的奇异值序列与不同气门间隙状态之间的关系。由于转速、负荷等工况的改变对信号特征层的影响与故障所引起的信号特征的改变可能非常相似，因此将奇异值序列作为特征参数，输入到随机森林分类器中，构建分类模型，对柴油机变工况下的气门间隙故障进行诊断。实验结果表明：该方法能有效识别气门间隙故障，突出故障敏感特征；与传统基于Hankel矩阵和小波包系数矩阵的SVD特征提取方法相比，该方法所提特征参数在柴油机变工况条件下具有更高的识别率。

Abstract

A novel feature extraction method based on variational mode decomposition (VMD) and singular value decomposition (SVD) is proposed to effectively extract valve clearance fault characteristics from cylinder head surface vibration signals of diesel engine. The vibration signal of cylinder head was decomposed by VMD algorithm, and the modal component was used to construct the characteristic matrix. Then the SVD theory was applied to transform the eigenmatrix into a singular value sequence representing the frequency characteristics. Since the influence of changes in working conditions such as rotating speed and load on the signal characteristic layer might be very similar to the signal characteristic changes caused by faults, the sequence of singular values was taken as characteristic parameters and input into the random forest classifier to build a classification model for the diagnosis of valve clearance faults under variable working conditions of diesel engine. Experimental results show that this method can effectively identify valve clearance faults and highlight fault sensitive features. Compared with the traditional SVD feature extraction method based on Hankel matrix and wavelet packet coefficient matrix, the feature parameters proposed by this method have higher recognition rate under variable working conditions of diesel engine.

导出引用

江志农1，魏东海1，张进杰2，茆志伟2. 基于VMD和SVD的柴油机气门间隙异常特征提取研究[J]. 振动与冲击, 2020, 39(16): 23-30

JIANG Zhinong1，WEI Donghai1，ZHANG Jinjie2，MAO Zhiwei2. A study on valve clearance anomaly feature extraction of diesel engines based on VMD and SVD[J]. Journal of Vibration and Shock, 2020, 39(16): 23-30

参考文献

[1] Jiang Z N，Mao Z W，Wang Z J，et al. Fault diagnosis of internal combustion engine valve clearance using the impact commencement detection method [J]. Sensors，2017，17(12)：1-19.
[2] Grzegorz M，Szymański，Tomaszewski F. Diagnostics of automatic compensators of valve clearance in combustion engine with the use of vibration signal [J]. Mechanical Systems & Signal Processing，2015，68–69(7)：479-490.
[3] 刘昱，张俊红，毕凤荣，等. 基于LMD边际谱的柴油机气门故障诊断[J]. 内燃机工程，2014，35(6)：96-100.
Liu Y，Zhang Jun-hong，Bi Feng-rong，et al. Diesel engine valve fault diagnosis based on LMD marginal spectrum [J]. Chinese Internal Combustion Engine Engineering，2014，35(6)：96-100.
[4] 吕艳春，徐玉秀. 基于Laplace小波相关滤波法的柴油机气门间隙故障诊断[J]. 车用发动机，2008(3)：48-54.
Lv Yan-chun，Xu Yu-xiu. Fault diagnosis of valve clearance of diesel engine based on Laplace wavelet correlation filtering [J]. Vehicle Engine，2008(3)：48-54.
[5] Flett J，Bone G M. Fault detection and diagnosis of diesel engine valve trains [J]. Mechanical Systems and Signal Processing，2015，72-73：316-327.
[6] 司景萍，任庆霜，梁红波，等. 基于小波包分析的气门间隙异常故障诊断[J]. 振动与冲击，2011，30(12)：64-68.
Si Jing-ping，Ren Qing-shuang，Liang Hong-bo，et al. Valve clearance fault detection based on wavelet packet analysis [J]. Journal of Vibration & Shock，2011，30(12)：64-68.
[7] 沈志熙，黄席樾，马笑潇. 基于EMD和支持向量机的柴油机故障诊断[J]. 振动、测试与诊断，2010，30(1)：19-22.
Shen Zhi-xi，Huang Xi-yue，Ma Xiao-xiao. Fault diagnosis of diesel engine based on empirical mode decomposition and support vector machine [J]. Journal of Vibration Measurement & Diagnosis，2010，30(1)：19-22.
[8] 张俊红，刘昱，毕凤荣，等. 基于LMD和SVM的柴油机气门故障诊断[J]. 内燃机学报，2012，30(5)：469-473.
Zhang Jun-hong，Liu Yu，Bi Feng-rong，et al. Diesel engine valve fault diagnosis based on LMD and SVM [J]. Transactions of CSICE，2012，30(5)：469-473.
[9] Dragomiretskiy K，Zosso D. Variational mode decomposition [J]. IEEE Transactions on Signal Processing，2014，62(3)：531-544.
[10] Wang Y，Markert R，Xiang J，et al. Research on variational mode decomposition and its application in detecting rub-impact fault of the rotor system [J]. Mechanical Systems & Signal Processing，2015，60-61：243-251.
[11] Wang Z P，Jia L M，Qin Y. Adaptive diagnosis for rotating machineries using information geometrical Kernel-ELM based on VMD-SVD [J]. Entropy，2018，20(1)：73.
[12] Yang Y，Wang H，Cheng J，et al. A fault diagnosis approach for roller bearing based on VPMCD under variable speed condition [J]. Measurement，2013，46(8)：2306-2312.
[13] Soleimani A，Khadem S E. Early fault detection of rotating machinery through chaotic vibration feature extraction of experimental data sets [J]. Chaos，Solitons & Fractals，2015，78：61-75.
[14] Jacek U，Tomasz B，Marcin S，et al. Normalization of vibration signals generated under highly varying speed and load with application to signal separation [J]. Mechanical Systems & Signal Processing，2017，82：13-31.
[15] Chen K，Zhou X C，Fang J Q，et al. Study on frequency characteristics of rotor systems for fault detection using variational mode decomposition [J]. International Journal of Rotating Machinery，2017，2：1-11.
[16] 郑小霞，周国旺，任浩翰，等. 基于变分模态分解和排列熵的滚动轴承故障诊断[J]. 振动与冲击，2017，36(22)：22-28.
Zheng Xiao-xia，Zhou Guo-wang，Ren Hao-han，et al. A rolling bearing fault diagnosis method based on variational mode decomposition and permutation entropy [J]. Journal of Vibration & Shock，2017，36(22)：22-28.
[17] 岳应娟，王旭，蔡艳平. 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)：89-97.
Yue Ying-juan，Wang Xu，Cai Yan-ping. Internal combustion engine fault diagnosis based on identification of variational modal Rihaczek spectrum texture characterization [J]. Chinese Journal of Scientific Instrument，2017，38(10)：89-97.
[18] Zhou S L，Liao J，Shi X J. Kernel parameter selection of RBM-SVM and its application in fault diagnosis [J]. Journal of Electronic Measurement & Instrumentation，2014，9：69-74.
[19] 同济大学数学系. 工程数学:线性代数(第六版) [M]. 北京：高等教育出版社，2014.
[20] 李国宾，关德林，李廷举. 基于小波包变换和奇异值分解的柴油机振动信号特征提取研究[J]. 振动与冲击，2011，30(8)：149-152.
Li Guo-bin，Guan De-lin，Li Ting-ju. Feature extraction of diesel engine vibration signal based on waveletpacket transform and singularity value decomposition [J]. Journal of Vibration & Shock，2011，30(8)：149-152.
[21] 赵学智，叶邦彦，陈统坚. 基于小波-奇异值分解差分谱的弱故障特征提取办法[J]. 机械工程学报，2012，48(7)：37-47.
Zhao Xue-zhi，Ye Bang-yan，Chen Tong-jian. Extraction method of faint fault feature based on wavelet-SVD difference spectrum [J]. Journal of Mechanical Engineering，2012，48(7)：37-47.
[22] 戴华. 矩阵论[M]. 北京：科学出版社，2001.
[23] 姚金宝. 复杂工况下旋转机械故障特征提取方法研究[D]. 重庆：重庆大学，2017.