Abstract
Remaining useful life (RUL) prediction of key components is an important influencing factor in making accurate maintenance decisions for mechanical systems. With the rapid development of deep learning (DL) techniques, the research on RUL prediction based on the data-driven model is increasingly widespread. Compared with the conventional convolution neural networks (CNNs), the multi-scale CNNs can extract different-scale feature information, which exhibits a better performance in the RUL prediction. However, the existing multi-scale CNNs employ multiple convolution kernels with different sizes to construct the network framework. There are two main shortcomings of this approach: (1) the convolution operation based on multiple size convolution kernels requires enormous computation and has a low operational efficiency, which severely restricts its application in practical engineering. (2) The convolutional layer with a large size convolution kernel needs a mass of weight parameters, leading to a dramatic increase in the network training time and making it prone to overfitting in the case of small datasets. To address the above issues, a multi-scale dilated convolution network (MsDCN) is proposed for RUL prediction in this article. The MsDCN adopts a new multi-scale dilation convolution fusion unit (MsDCFU), in which the multi-scale network framework is composed of convolution operations with different dilated factors. This effectively expands the range of receptive field (RF) for the convolution kernel without an additional computational burden. Moreover, the MsDCFU employs the depthwise separable convolution (DSC) to further improve the operational efficiency of the prognostics model. Finally, the proposed method was validated with the accelerated degradation test data of rolling element bearings (REBs). The experimental results demonstrate that the proposed MSDCN has a higher RUL prediction accuracy compared to some typical CNNs and better operational efficiency than the existing multi-scale CNNs based on different convolution kernel sizes.
Highlights
With the development of industrial science and engineering maintenance, the level of automation and complexity of mechanical equipment (ME) has been increasing
Numerous multi-scale convolution neural networks (CNNs) models [12,16,19] have been proposed recently to extract different-scale feature information. Even though these models improve the learning ability of the network, the existing multi-scale networks’ frameworks are all based on different sizes of convolution kernels
It can be seen that the total model parameters of the proposed method were reduced by 96.1% and 36.6% compared to the multi-scale deep convolutional neural network (MS-DCNN) method and the MS-DRN
Summary
With the development of industrial science and engineering maintenance, the level of automation and complexity of mechanical equipment (ME) has been increasing. The above studies had a certain degree of successful RUL prediction, most of them need complicated signal processing techniques and some prior knowledge to extract feature information. These models are all shallow network architectures. Adopted a CNN-based network model with 13 convolution layers to predict REB RUL, in which the spectrum-principal-energy vector was used to extract signal eigenvectors to input the network. Numerous multi-scale CNN models [12,16,19] have been proposed recently to extract different-scale feature information Even though these models improve the learning ability of the network, the existing multi-scale networks’ frameworks are all based on different sizes of convolution kernels.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
