Abstract
A Bi-directional Long Short Term Memory (BiLSTM) based method is proposed to solve the problem of low accuracy of residual life prediction of DC railroad relays. First, a full-life testbed is built to extract the characteristic parameters that characterize the operating state of the DC railroad relay. Then, Maximal Information Coefficient (MIC) is used to correlate the feature parameters with the remaining electric life, and the optimal feature subset is selected by combining the random forest feature contribution analysis. Finally, the optimal feature subset is fed into the BiLSTM model for time series prediction. The case analysis shows that the model is better than Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM), and the effective prediction accuracy reaches 96.3%, which fully proves the feasibility of time-series prediction in the field of electrical appliances.
Sign-in/Register to access full text options 
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.
