The railway track circuit is critical for train detection and signaling safety. Conventional diagnosis methods, reliant on manual checks and threshold-based alarms, are inefficient and prone to errors. This paper presents a deep learning model for intelligent fault diagnosis in track circuits. Real-time voltage and current waveforms under various conditions—normal operation, shunt faults, broken rails, and insulation degradation—are collected to form a high-dimensional time-series dataset. A hybrid neural network combining 1D Convolutional Neural Networks and Long Short-Term Memory networks is designed to automatically extract spatiotemporal features from raw signals. The model performs end-to-end diagnosis, identifying both fault type and severity. Validated using field data from a heavy-haul railway, the model achieves an overall classification accuracy of 98.7%, surpassing traditional threshold and Support Vector Machine methods. Notably, it attains a 95.3% recall rate for early-stage insulation degradation, a fault notoriously difficult for conventional approaches to detect. An integrated attention mechanism enhances interpretability by highlighting signal segments most relevant to the fault. This research demonstrates that deep learning offers a viable pathway toward predictive and intelligent maintenance of track circuits, with significant potential to reduce unplanned downtime and strengthen the safety of railway signaling systems.

Ziran Ge. A Fault Diagnosis Model for Railway Track Circuits Using Deep Learning. International Journal of New Developments in Engineering and Society (2026), Vol. 10, Issue 1: 1-7. https://doi.org/10.25236/IJNDES.2026.100101.

[1] De Bruin T, Verbert K, Babuška R. Railway track circuit fault diagnosis using recurrent neural networks[J]. IEEE transactions on neural networks and learning systems, 2016, 28(3): 523-533.

[2] Zhang X, Ru Y. Fault prediction of railway track circuit based on machine learning[J]. International Journal of Sensor Networks, 2024, 45(4): 216-228.

[3] Sun S, Zhao H. Fault diagnosis in railway track circuits using support vector machines[C]//2013 12th International Conference on Machine Learning and Applications. IEEE, 2013, 2: 345-350.

[4] Yin J, Zhao W. Fault diagnosis network design for vehicle on-board equipments of high-speed railway: A deep learning approach[J]. Engineering Applications of Artificial Intelligence, 2016, 56: 250-259.

[5] Peng F, Liu T. Method for fault diagnosis of track circuits based on a time–frequency intelligent network[J]. Electronics, 2024, 13(5): 859.

[6] Oukhellou L, Debiolles A, Denœux T, et al. Fault diagnosis in railway track circuits using Dempster–Shafer classifier fusion[J]. Engineering Applications of Artificial Intelligence, 2010, 23(1): 117-128.

[7] Chen Y, Song B, Zeng Y, et al. Fault diagnosis based on deep learning for current-carrying ring of catenary system in sustainable railway transportation[J]. Applied Soft Computing, 2021, 100: 106907.

[8] Ge X, Wang P, Shi Y, et al. A Novel Fault Diagnosis Method for ZPW-2000A Track Circuit Applied to Small Samples[J]. IEEE Access, 2025.

[9] Tao W, Li X, Li Z. Track circuits fault diagnosis method based on the UNet‐LSTM network (ULN)[J]. Journal of Electrical and Computer Engineering, 2024, 2024(1): 1547428.

[10] Ke T, Zhang W, Zhang Z, et al. An Effective Deep SVM Approach for Fault Diagnosis of 25 Hz Track Circuit[C]//International Conference on Intelligent Computing. Singapore: Springer Nature Singapore, 2024: 137-147.

[11] Han X. Fault diagnosis model for railway signalling equipment using deep learning techniques[J]. International Journal of Sensor Networks, 2024, 45(1): 40-53.

[12] Shafique R, Siddiqui H U R, Rustam F, et al. A novel approach to railway track faults detection using acoustic analysis[J]. Sensors, 2021, 21(18): 6221.

[13] Orlov S, Piletskaya A, Kusakina N, et al. Machine learning of diagnostic neural network for railway track monitoring[M]//Cyber-Physical Systems: Intelligent Models and Algorithms. Cham: Springer International Publishing, 2022: 55-65.

[14] Rakshit S, Sandeep B S. Railway track fault detection using deep neural networks[C]//2022 IEEE 6th Conference on Information and Communication Technology (CICT). IEEE, 2022: 1-5.

[15] James A, Jie W, Xulei Y, et al. Tracknet-a deep learning based fault detection for railway track inspection[C]//2018 International Conference on Intelligent Rail Transportation (ICIRT). IEEE, 2018: 1-5.

[16] López F, Di Santi E, Lefebvre C, et al. Track Component Failure Detection Using Data Analytics over existing STDS Track Circuit data[J]. arXiv preprint arXiv:2508.11693, 2025.

[17] Hamadache M, Dutta S, Olaby O, et al. On the fault detection and diagnosis of railway switch and crossing systems: An overview[J]. Applied Sciences, 2019, 9(23): 5129.

[18] Fu J, Yuan X. Simulation-driven fault diagnosis for track circuits using multi-scale convolution and transformers under imbalanced data conditions[J]. International Journal of Simulation and Process Modelling, 2025, 22(1-2): 29-46.