高效、准确地故障诊断可以提高柴油机的安全性和可靠性。传统机械故障诊断方法中人工参与程度过高，为识别结果带来诸多不确定性。针对这一问题，论文提出一种基于多重注意力卷积神经网络 (Multiple Attention Convolutional Neural Networks, MACNN)的端到端的故障诊断方法。该方法采用多层卷积神经网络 (Convolutional Neural Networks, CNN) 结合卷积注意力模块 (Convolutional Block Attention Module, CBAM) 对原始时域数据进行特征提取，然后对多维卷积输出特征图进行重组以保留其序列信息，最后直接采用序列注意力机制完成序列特征的学习。经采用实测柴油机缸盖振动信号数据进行验证后表明：面对8分类柴油机故障数据集，MACNN能够达到97.88%的识别准确率，测试100个样本用时仅为0.35s。与现有多种传统故障诊断方法和端到端故障诊断方法相比，均具有更好的诊断效果。
Abstract
Efficient and accurate fault diagnosis can improve the safety and reliability of diesel engine. In the traditional mechanical fault diagnosis method, the degree of human participation is too high, which brings high uncertainty to results. To solve this problem, this paper proposes an end-to-end fault diagnosis method based on multiple attention convolutional neural networks (MACNN). In this method, multi-layer convolutional neural networks (CNN) and convolutional block attention module (CBAM) are used to extract features from the original time-domain data, and then the multi-dimensional feature map of convolutional output is recombined to retain its sequence information. Finally, the sequential attention mechanism is directly used to learn the sequence feature. The results show that MACNN can achieve recognition accuracy of 97.88% for eight-class fault data set of diesel engine, and the time taken to test 100 samples is only 0.35 seconds. Compared with other traditional fault diagnosis methods and end-to-end fault diagnosis methods, the proposed MACNN has better diagnosis effect.
关键词
多重注意力 /
卷积神经网络 /
故障诊断 /
端到端
{{custom_keyword}} /
Key words
multiple attention /
convolutional neural networks (CNN) /
fault diagnosis /
end to end
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] BI F, MA T, WANG X. Development of a novel knock characteristic detection method for gasoline engines based on wavelet-denoising and EMD decomposition[J]. Mechanical Systems and Signal Processing, 2019, 117: 517-536.
[2] HUANG N E, SHEN Z, LONG S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society of London. Series A: mathematical, physical and engineering sciences, 1998, 454(1971): 903-995.
[3] BI X, LIN J, TANG D, et al. VMD-KFCM Algorithm for the Fault Diagnosis of Diesel Engine Vibration Signals[J].Energies, 2020, 13(1): 228.
[4] BI X, LIN J, BI F, et al. Engine working state recognition based on optimized variational mode decomposition and expectation maximization algorithm[J]. IEEE Access, 2020, 8: 33545-33559.
[5] DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE transactions on signal processing, 2013, 62(3): 531-544.
[6] LU C, WANG Z, ZHOU B. Intelligent fault diagnosis of rolling bearing using hierarchical convolutional network based health state classification[J]. Advanced Engineering Informatics, 2017, 32: 139-151.
[7] WANG L, ZHAO X, WU J, et al. Motor fault diagnosis based on short-time Fourier transform and convolutional neural network[J]. Chinese Journal of Mechanical Engineering, 2017, 30(6): 1357-1368.
[8] XIA M , LI T , XU L, et al. Fault diagnosis for rotating machinery using multiple sensors and convolutional neural networks[J]. IEEE/ASME Transactions on Mechatronics, 2017, PP(99):1-1.
[9] 庄雨璇. 基于深度学习的旋转轴承端到端故障诊断研究[D].苏州大学, 2019.
[10] 张立鹏, 毕凤荣, 程建刚, 等. 基于注意力BiGRU的机械故障诊断方法研究[J]. 振动与冲击, 2021, 40(5): 113-118.
ZHANG Lipeng, BI Fengrong, CHENG Jiangang, et al. Mechanical fault diagnosis method based on attention BiGRU. JOURNAL OF VIBRATION AND SHOCK, 2021, 40(5): 113-118.
[11] ZHOU C , SUN C , LIU Z , et al. A C-LSTM neural network for text classification[J]. Computer Science, 2015, 1(4):39-44.
[12] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[13] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[14] IOFFE S, SZEGEDY C. Batch normalization: Accelerating deep network training by reducing internal covariate shift[J]. Communications of the ACM, 2015: 448–456.
[15] WOO S, PARK J, LEE J Y, et al. Cbam: convolutional block attention module[C]//Proceedings of the European conference on computer vision (ECCV). Munich, 2018: 3-19.
[16] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. California, 2017: 5998-6008.
[17] ZHOU P, SHI W, TIAN J, et al. Attention-based bidirectional long short-term memory networks for relation classification[C]//Proceedings of the 54th annual meeting of the association for computational linguistics (volume 2: Short papers). Berlin, 2016: 207-212.
[18] KINGMA D P, BA J. Adam: A method for stochastic optimization[J]. Computer Science，2017，9：1-15.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(1696 KB)
