基于DVMD和SSAE的柴油机混合故障诊断

PDF(2302 KB)

振动与冲击 ›› 2022, Vol. 41 ›› Issue (11) : 271-277.

论文

白雲杰1,2，贾希胜1,2，梁庆海1,2

作者信息 +

Hybrid fault diagnosis of Diesel engine based on DVMD and SSAE

BAI Yunjie1,2, JIA Xisheng1,2, LIANG Qinghai1,2

Author information +

文章历史 +

摘要

针对柴油机缸盖振动信号非平稳非线性的特点，本文提出一种基于散布熵改进的变分模态分解（DVMD）和堆叠稀疏自编码器（SSAE）相结合的柴油机混合故障诊断方法。利用散布熵确定变分模态分解的层数K，并根据散布熵转折点选取有效模态分量。分别对选取的各模态分量提取常用14个时域特征和小波包分解后的能量特征，构建混合多特征向量，输入基于堆叠稀疏自编码器和Softmax层构建的深度神经网络（DNN）中，实现了柴油机7种混合故障模式识别。与其他常见方法进行对比，结果表明本文所提出的方法能够有效提取故障特征，具有较高的诊断准确率。

Abstract

Aiming at the non-stationary and nonlinear characteristics of diesel engine cylinder head vibration signals, this paper proposes a diesel engine hybrid fault diagnosis method based on the combination of dispersion entropy-improved variational modal decomposition (DVMD) and stacked sparse autoencoder (SSAE). The dispersion entropy is used to determine the decomposition number K value of VMD, and the effective modal components are selected according to the turning point of the dispersion entropy. Extract 14 common time-domain features and energy features after wavelet packet decomposition from the selected modal components, construct a hybrid multi-feature vector, and input it into a deep neural network (DNN) based on stacked sparse autoencoders and Softmax layers. The recognition of 7 mixed failure modes of diesel engine is realized. Comparing with other common methods, the results show that the method proposed in this paper can effectively extract fault features and has a higher diagnostic accuracy.

导出引用

白雲杰1,2，贾希胜1,2，梁庆海1,2. 基于DVMD和SSAE的柴油机混合故障诊断[J]. 振动与冲击, 2022, 41(11): 271-277

BAI Yunjie1,2, JIA Xisheng1,2, LIANG Qinghai1,2. Hybrid fault diagnosis of Diesel engine based on DVMD and SSAE[J]. Journal of Vibration and Shock, 2022, 41(11): 271-277

参考文献

[1] 王国彪，何正嘉，陈雪峰，等.机械故障诊断基础研究“何去何从”[J].机械工程学报，2013，49(1)：63-72.
WANG Guobiao，HE Zhengjia，CHEN Xuefeng，et al.Basic research on machinery fault diagnosis—what is the prescri- ption[J]. Journal of Mechanical Engineering, 2013, 49(1)：63-72.
[2] J. Jiang, F. Gu, R. Gennish, D.J. Moore, G. Harris, A.D. Ball, Monitoring of diesel engine combustions based on the acoustic source characterisation of the exhaust system[J], Mech. Syst. Signal Process. 22 (2008) 1465–1480.
[3] J. Flett, G.M. Bone, Fault detection and diagnosis of diesel engine valve trains[J], Mech. Syst. Signal Process. 72-73 (2016) 316-327.
[4] T. Zheng, Y. Zhang, Y. Li, L. Shi, Real-time combustion torque estimation and dynamic misfire fault diagnosis in gasoline engine[J], Mech. Syst. Signal Process. 126 (2019) 521-535.
[5] 刘建敏，李晓磊，乔新勇，等．基于缸盖振动信号的柴油机多工况气缸压力识别方法研究[J]. 汽车工程，2015, 37(8): 875-880+979．
LIU Jianmin, LI Xiaolei, Qiao Xinyong, et al. A study on the cylinder pressure identification method for diesel engine undel multiple working conditions based on cylinder head vibration signals.[J] Automotive Engineering, 2015, 37(8): 875-880, +979．
[6] 刘敏，李志宁，张英堂，等．基于多尺度核独立成分分析的柴油机故障诊断[J]．振动、测试与诊断，2017，37(5)：892-897.
LIU Min, LI Zhining, ZHANG Yingtang, et al．Fault diag- nosis of diesel engine based on multi-scale kernel independent component analysis [J]. Journal of Vibration, Measurement and Diagnosis, 2017, 37(5): 892-897.
[7] 蒋佳炜，胡以怀，柯赟，等. 基于小波包特征提取和模糊熵特征选择的柴油机故障分析[J]. 振动与冲击，2020,39（04）：273-277+298.
JIANG Jiawei, HU Yihuai, KE Yun, et al. Fault diagnosis of diesel engines based on wavelet packet energy spectrum feature extraction and fuzzy entropy feature selection[J]. Journal of vibration and shock, 2020, 39（04）：273-277+298.
[8] 陈俊柏,刘勇智,陈勇,等.基于EMD和SVM的机载燃油泵故障诊断研究[J/OL].北京航空航天大学学报: 1-14[2021 -02-05].
CHEN Junbai, LIU Yongzhi, CHEN Yong, et al. Fault diagnosis of airborne fuel pump based on EMD and SVM[J/OL]. Journal of Beijing University of Aeronautics and Astronautics: 1-14[2021-02-05].
[9] 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 Junhong， LIU Yu， BI Fengrong， et al． Diesel-eng ine valve fault diagnosis based on LMD and SVM[J]. Trans actions of CSICE, 2012, 30( 5) : 469-473．
[10] Dragomiretskiy K, Zosso D. Variational Mode Decomp- osition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.
[11] SCHMID H J. Deep learning in neural networks: An overview[J]. Neural Networks, 2015 (61) :85-117．
[12] 李祖贺，樊养余，王凤琴. YUV空间中基于稀疏自动编码器的无监督特征学习[J].电子与信息学报,2016, 38(1): 29-37.
LI Zuhe, FAN Yangyu, WANG Fengqin. Unsupervised Feature Learning with Sparse Autoencoders in YUV Space[J]. Journal of Electronics & Information Technology, 2016, 38(1): 29-37.
[13] MA Y, LI H G. GRU-Auto-Encoder neural network based methods for diagnosing abnormal operating conditions of steam drums in coal gasification plants[J]. Computers & Chemical Engineering, 2020, 145(5): 107097.
[14] WANG Y L, YANG H B, YUAN X F, et al. Deep learning for fault-relevant feature extraction and fault classification with stacked supervised auto-encoder[J]. Journal of Process Control, 2020, 92(8): 79-89.
[15] Hestenes M R．Multiplier and gradient methods［J］．Journal of Optimization Theory and Applications，1969，4( 5) : 303-320．
[16] ROSTAGHI M, AZAMI H. Dispersion entropy: a measure for time-series analysis［J］. IEEE Signal Processing Letters，2016, 23(5): 610-614.
[17] 何玉灵，孙凯，王涛，等.基于变分模态分解与精细复合多尺度散布熵的发电机匝间短路故障诊断[J]．电力自动化设备, 2021, 41(3): 164-172.
HE Yuling, SUN Kai, WANG Tao, et, al. Fault diagnosis of generator interturn short circuit fault based on variational mode decomposition and refined composite multiscale dispersion entropy[J]. Electric Power Automation Equipment, 2021, 41(3): 164-172.
[18] 吴康福，李耀贵．基于混合特征和堆栈稀疏自编码器的齿轮箱故障诊断［J］．机床与液压，2020，48(11):200－206．
WU Kangfu， LI Yaogui．Fault Diagnosis of Gearbox Based on Hybrid Features and Stacked Sparse Auto-encoder[J]. Machine Tool ＆ Hydraulics, 2020, 48( 11) : 200－206．
[19] 曹浩，陈里里，司吉兵，等．奇异值分解和稀疏自编码器的轴承故障诊断［J］．计算机工程与应用，2019，55(20):257-262．
CAO Hao, CHEN Lili, SI Jibing, et al. Singular value decomposition and sparse automatic encoder for bearing fault diagnosis[J]. Computer Engineering an Applications, 2019, 55（20）：257-262.