期刊
IEEE ACCESS
卷 7, 期 -, 页码 44761-44770出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2019.2906895
关键词
Railway relays; life prediction; complete ensemble empirical mode decomposition (CEEMD); improved variational mode decomposition (IVMD); radial basis function neural network (RBFNN)
资金
- Fundamental Research Funds for the Central Universities [2018YJS021]
- National Natural Science Foundation of China [U1734211, U1534208, 61806064, 61873201]
- National Key Research and Development Program [2016YFE0200900]
The railway relay plays an important role in railway systems. Its reliability has a significant effect on the safety of passengers and train operation, which can be reflected using degradation parameters. In this paper, a novel hybrid method based on the multi-layer decomposition and the radial basis function neural network (RBFNN) is proposed for life prediction of railway relays. As the degradation parameter series are usually nonlinear and non-stationary, it is vital to develop an essential method to preprocess the degradation series. In order to improve the prediction accuracy, a multi-layer decomposition method is developed first for data pre-processing, which blends complete ensemble empirical mode decomposition (CEEMD) and an improved variational mode decomposition (IVMD) with a stopping criterion for determining the decomposition modes number. It is noted that IVMD is then used to decompose the high-frequency intrinsic mode functions (IMFs) obtained using CEEMD to improve the prediction accuracy. Furthermore, RBFNN is applied to all the components for prediction. And the prediction results of all the components are reconstructed as the predicted degradation series. Finally, the effectiveness and robustness of the proposed novel hybrid prediction method are verified on one-step prediction and multi-step prediction by comparing other commonly used prediction methods. The experimental results indicate that the proposed hybrid prediction method performs best on the complex degradation parameters of safety relays.
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