2024, Vol. 5, Issue 1, Part A
Fault diagnosis method for track circuits using the UNet-LSTM network
Author(s): Nedret Altiok
Abstract: This review article explores an advanced fault diagnosis method for railway track circuits employing a hybrid deep learning model that combines the UNet convolutional neural network with Long Short-Term Memory (LSTM) networks. Aimed at significantly improving the accuracy and efficiency of fault detection and diagnosis in the critical components of railway infrastructure, this method utilizes the UNet architecture for its exceptional spatial feature extraction capabilities and integrates LSTM networks to adeptly handle temporal sequence data. This paper presents an in-depth analysis of the methodology, evaluates its performance against traditional fault diagnosis approaches, and discusses its implications for future railway system maintenance and safety.
Pages: 23-25 | Views: 372 | Downloads: 147
Download Full Article: Click Here
How to cite this article:
Nedret Altiok. Fault diagnosis method for track circuits using the UNet-LSTM network. Int J Electr Data Commun 2024;5(1):23-25.
