期刊
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
卷 16, 期 10, 页码 6347-6358出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2020.2966326
关键词
Convolution; Feature extraction; Vibrations; Deconvolution; Fault diagnosis; Decoding; Kernel; Convolutional autoencoder (CAE); feature learning; gearbox fault diagnosis; residual learning
类别
资金
- National Natural Science Foundation of China [71777173]
- Fundamental Research Funds for the Central Universities
- Shanghai science and Technology Innovation Fund [19511106303, TII-19-3197]
Vibration signals are generally utilized for machinery fault diagnosis to perform timely maintenance and then reduce losses. Thus, the feature extraction on one-dimensional vibration signals often determines accuracy of those fault diagnosis models. These typical deep neural networks (DNNs), e.g., convolutional neural networks (CNNs), perform well in feature learning and have been applied in machine fault diagnosis. However, the supervised learning of CNN often requires a large amount of labeled images and thus limits its wide applications. In this article, a new DNN, one-dimensional residual convolutional autoencoder (1-DRCAE), is proposed for learning features from vibration signals directly in an unsupervised-learning way. First, 1-D convolutional autoencoder is proposed in 1-DRCAE for feature extraction. Second, a deconvolution operation is developed as decoder of 1-DRCAE to reconstruct the filtered signals. Third, residual learning is employed in 1-DRCAE to perform feature learning on 1-D vibration signals. The results show that 1-DRCAE has good signal denoising and feature extraction performance on vibration signals. It performs better on feature extraction than the typical DNNs, e.g., deep belief network, stacked autoencoders, and 1-D CNN.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据