Fault Diagnosis of Machines Using Deep Convolutional Beta-Variational Autoencoder

被引:17
作者
Dewangan G. [1 ]
Maurya S. [1 ]
机构
[1] Department of Electrical Engineering, Indian Institute of Technology Kanpur, Kanpur
来源
IEEE Transactions on Artificial Intelligence | 2022年 / 3卷 / 02期
关键词
Convolution neural network (CNN); fault diagnosis; variable-beta; variational autoencoder (VAE);
D O I
10.1109/TAI.2021.3110835
中图分类号
学科分类号
摘要
Industries are using fault diagnosis methods to prevent any downtime, which eventually led them to make profits and take necessary steps beforehand to avoid any mishaps. In recent years, deep learning methods have shown extraordinary performance in massive data applications with advancement in computing power. In this article, a novel intelligent fault diagnosis scheme based on deep convolutional variable-beta variational autoencoder (VAE) is proposed to extract discriminative features. A new min-max algorithm for data points reduction and a random sampling technique to get 2-D data has been proposed. The proposed fault diagnosis combines all intermediate steps (from preprocessing to classification) in a single framework, and an end-to-end training has been performed. The proposed training method with variable beta uses VAE as a feature extractor and classifier rather than just being a probabilistic generative model, which further improved the performance of the overall model. The proposed scheme reduces the needs of domain/expertise knowledge on time-series data. The proposed method has also been validated in the presence of noise. The proposed approach is validated through two case studies by utilizing rotating machinery datasets: First, on the case western reserve university vibration dataset (VD), and second, on the air compressor acoustic dataset (AD). Highest accuracies obtained are 99.93% and 99.91% on case western reserve university VD and air compressor AD, respectively, using the proposed scheme. Finally, a comparative study has been presented. © 2020 IEEE.
引用
收藏
页码:287 / 296
页数:9
相关论文
共 49 条
[1]  
Henriquez P., Alonso J.B., Ferrer M.A., Travieso C.M., Review of automatic fault diagnosis systems using audio and vibration signals, IEEE Trans. Syst. Man, Cybern.: Syst., 44, 5, pp. 642-652, (2014)
[2]  
Martin K.F., A review by discussion of condition monitoring and fault diagnosis in machine tools, Int. J. Mach. Tools Manuf., 34, 4, pp. 527-551, (1994)
[3]  
Maurya S., Singh V., Verma N.K., Condition monitoring of machines using fused features from EMD based local energy with DNN, IEEE Sensors J., 20, 15, pp. 8316-8327, (2020)
[4]  
Khan S.A., Kim J.M., Rotational speed invariant fault diagnosis in bearings using vibrational signal imaging and local binary patters, J. Acoust. Soc. Amer., 139, pp. EL100-EL104, (2016)
[5]  
Duan R., Wang F., Fault diagnosis of on-load tap-changer in converter transformer based on time-frequency vibration analysis, IEEE Trans. Ind. Electron., 63, 6, pp. 3815-3823, (2016)
[6]  
Verma N.K., Sevakula R.K., Dixit S., Salour A., Intelligent condition basedmonitoring using acoustic signals for air compressors, IEEE Trans. Rel., 65, 1, pp. 291-309, (2016)
[7]  
Verma N.K., Sevakula R.K., Thirukovalluru R., Pattern analysis framework with graphical indices for condition based monitoring, IEEE Trans. Rel., 66, 4, pp. 1085-1100, (2017)
[8]  
Maurya S., Singh V., Dixit S., Verma N.K., Salour A., Liu J., Fusion of low-level featureswith stacked autoencoder for condition based monitoring of machines, Proc. IEEE Int. Conf. Prognostics Health Manage., pp. 1-8, (2018)
[9]  
Dai X., Gao Z., From model, signal to knowledge: A datadriven perspective of fault detection and diagnosis, IEEE Trans. Ind. Inform., 9, 4, pp. 2226-2238, (2013)
[10]  
Chen J., Patton R., Robust Model-Based Fault Diagnosis for Dynamic Systems, 3, (2012)