Fault diagnosis of diesel engine high pressure oil circuit based on CUM3-CNN

PDF(1869 KB)

Journal of Vibration and Shock ›› 2023, Vol. 42 ›› Issue (3) : 174-180.

CHANG Chun, MEI Jianmin, ZHAO Huimin, SHEN Hong, WANG Shuangpeng

Author information +

History +

Abstract

Aiming at the problems of strong noise interference, high subjective influence of artificial identification characteristics and low accuracy of automatic identification in diesel engine fault diagnosis，a diesel engine fault diagnosis method using convolutional neural network to identify the cumulant grayscale image of vibration signal was proposed. Firstly, using the innate characteristics of third-order cumulants to suppress Gaussian noise, the vibration signal of cylinder head was analyzed, and the grayscale image was generated as input of convolution neural network. Stochastic gradient descent with momentum algorithm and learning rate annealing method were used to train the convolutional neural network, and genetic algorithm was used to optimize training parameters, then the trained network was used to diagnose the faults of five working conditions of diesel engine high pressure oil circuit. The experimental results show that the grayscale images generated by third-order cumulants can suppress the noise effectively and display the characteristic information comprehensively. The method of learning rate annealing and genetic algorithm to improve the optimized convolutional neural network has good generalization ability, and has higher accuracy and anti-noise ability than the traditional method.

Key words

diesel engine / fault diagnosis / third-order cumulant / convolution neural network

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

CHANG Chun, MEI Jianmin, ZHAO Huimin, SHEN Hong, WANG Shuangpeng. Fault diagnosis of diesel engine high pressure oil circuit based on CUM3-CNN[J]. Journal of Vibration and Shock, 2023, 42(3): 174-180

References

[1] 蔡剑华,胡惟文,王先春.基于高阶统计量的滚动轴承故障诊断方法[J].振动.测试与诊断,2013,33(02):298-301+342-343.
CAI Jian-hua, HU Weiwen, WANG Xiaochun. Roller bearing fault diagnosis based on higher-order statistics[J]. Journal of Vibration, Measurement & Diagnosis, 2013,33(02):298- 301+342-343.
[2] 张贤达. 线代信号处理[M].清华大学出版社,2002:263-267.
ZHANG Xianda. Modern signal processing[M]. Tsinghua University Press, 2002:263-267.
[3] 沈虹,赵红东,梅检民,赵慧敏,张大鹏,任金成.基于角域四阶累积量切片谱的柴油机连杆轴承故障特征提取[J].振动与冲击,2014,33(11):90-94.
SHEN Hong, ZHAO Hongdong, MEI Jianmin, et al. Fault feature extraction of connecting rod bearings of a diesel engine based on angle domain fourth-order cumulant slice spectrum
[J]. Journal of Vibration and Shock,2014,33(11): 90-94.
[4] 任金成,肖云魁,张玲玲,沈虹,封慧娟.基于时频谱图和粗糙集的柴油机故障图像纹理特征自动提取[J].内燃机工程,2015,36(3):106-112.
REN Jincheng, XIAO Yunkui, ZHANG Lingling, et al. Automatic extraction of image texture feature of diesel engine fault based on cwt time-frequency image and variable precision rough set theory[J]. Chinese Internal Combustion Engine Engineering, 2015,36(3):106-112.
[5] 沈虹,赵红东,梅检民,曾锐利.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 Hongdong, MEI Jianmin, et al. Diesel engine fault diagnosis based on high-order cumulant image features[J]. Journal of Vibration and Shock,2015,34(11): 133-138.
[6] Good0fellow I., Bengio Y., Courville A.. Deep learning (Vol. 1)[M]. Cambridge:MIT press,2016:326-366.
[7] 吴春志,江鹏程,冯辅周,陈汤,陈祥龙.基于一维卷积神经网络的齿轮箱故障诊断[J].振动与冲击,2018,37(22):51-56.
WU Chunzhi, JIANG Pengcheng, FENG Fuzhou, et al. Faults diagnosis method for gearboxes based on a 1-D convolutional neural network[J]. Journal of Vibration and Shock, 2018,37(22): 51-56.
[8] 周奇才,刘星辰,赵炯,沈鹤鸿等.旋转机械一维深度卷积神经网络故障诊断研究[J].振动与冲击,2018,37(23):31-37.
ZHOU Qicai, LIU Xingchen, ZHAO Jiong, et al. Fault diagnosis for rotating machinery based on 1D depth convolutional neural network[J]. Journal of Vibration, 2018,37(23):31-37.
[9] 李恒,张氢,秦仙蓉,孙远韬.基于短时傅里叶变换和卷积神经网络的轴承故障诊断方法[J].振动与冲击,2018,37(19):124-131.
LI Heng, ZHANG Qin, QIN Xianrong, et al. Fault diagnosis method for rolling bearings based on short-time Fourier transform and convolution neural network[J]. Journal of Vibration, 2018,37(19):124-131.
[10] 袁建虎,韩涛,唐建,安立周.基于小波时频图和CNN的滚动轴承智能故障诊断方法[J].机械设计与研究,2017,33(02):93-97.
YUAN Jianhu, HAN Tao, TANG Jian, et al. An approach to intelligent fault diagnosis of rolling bearing using wavelet time-frequency representations and CNN[J]. Machine Design and Research, 2017,33(02):93-97.
[11] 陈仁祥,黄鑫,杨黎霞,汤宝平,余腾伟,周君.基于卷积神经网络和离散小波变换的滚动轴承故障诊断[J].振动工程学报,2018,31(05):883-891.
CHEN Renxiang, HUANG Xin, YANG Lixia, et al. Rolling bearing fault identification based on convolution neural network and discrete wavelet transform[J]. Journal of Vibration Engineering, 2018,31(05):883-891.
[12] 卓德兵,曹晖.基于小波时频图与轻量级卷积神经网络的螺栓连接损伤识别[J].工程力学,2021,(09):228-238.
ZHUO Debing, CAO Hui. Damage identification of bolt connections based on wavelet time-frequency diagrams and lightweight convolutional neural networks[J]. Engineering Mechanics, 2021,(09):228-238.
[13] 张宪超. 深度学习(上)[M].科学出版社,2019,127-128.
ZHANG Xian-chao, Deep Learning(Vol. 1)[M]. Science Press, 2019:127-128.
[14] Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: a simple way to prevent neural networks from overfitting[J].Journal of Machine Learning Research, 2014, 15(1):1929-1958.