The turnout is usually classified as the infrastructure in the railway system, whose safety and reliability are directly related to the stable operation of the railway system by its vital role. In this paper, we use the switch machine power curve recorded in the centralized signaling monitoring (CSM) system to conduct fault diagnosis. First, we obtain the mean value and difference value through wavelet transform as the input of convolutional neural network (CNN), realizing the extraction of switch machine fault features, and then use the extracted fault features as the input of long and short time memory network (LSTM) to finally realize switch machine fault diagnosis. The data is divided into training set and test set for training and testing the model. After 50 iterations, the accuracy of switch machine fault diagnosis reached 96.7% through experimental simulation.
Research on Switch Machine Fault Diagnosis Based on Wavelet Transform and CNN-LSTM
Lect. Notes Electrical Eng.
International Conference on Electrical and Information Technologies for Rail Transportation ; 2023 ; Beijing, China October 19, 2023 - October 21, 2023
Proceedings of the 6th International Conference on Electrical Engineering and Information Technologies for Rail Transportation (EITRT) 2023 ; Chapter : 21 ; 193-202
2024-01-09
10 pages
Article/Chapter (Book)
Electronic Resource
English
Fault Diagnosis Method Based on Wavelet Transform
Springer Verlag | 2016
|Intelligent Building Fault Diagnosis Based on Wavelet Transform and Bayesian Network
Springer Verlag | 2019
|Fault Diagnosis Based on Optimized Wavelet Packet Transform and Time Domain Convolution Network
BASE | 2023
|Empirical Wavelet Transform and Power Spectral Entropy for Rotating Machinery Fault Diagnosis
British Library Conference Proceedings | 2020
|