Railway Track Circuit Fault Diagnosis Using Recurrent Neural Networks

Timely detection and identification of faults in railway track circuits are crucial for the safety and availability of railway networks. In this paper, the use of the long-short-term memory (LSTM) recurrent neural network is proposed to accomplish these tasks based on the commonly available measurement signals. By considering the signals from multiple track circuits in a geographic area, faults are diagnosed from their spatial and temporal dependences. A generative model is used to show that the LSTM network can learn these dependences directly from the data. The network correctly classifies 99.7% of the test input sequences, with no false positive fault detections. In addition, the t-Distributed Stochastic Neighbor Embedding (t-SNE) method is used to examine the resulting network, further showing that it has learned the relevant dependences in the data. Finally, we compare our LSTM network with a convolutional network trained on the same task. From this comparison, we conclude that the LSTM network architecture is better suited for the railway track circuit fault detection and identification tasks than the convolutional network.

[1]  Zhao Linhai,et al.  Fault diagnosis for track circuit using AOK-TFRs and AGA , 2012 .

[2]  B. De Schutter,et al.  Exploiting spatial and temporal dependencies to enhance fault diagnosis: Application to railway track circuits , 2015, 2015 European Control Conference (ECC).

[3]  Alexander Steinecker,et al.  Automated fault detection using deep belief networks for the quality inspection of electromotors , 2014 .

[4]  Mohammad Ali Sandidzadeh,et al.  Intelligent condition monitoring of railway signaling in train detection subsystems , 2013, J. Intell. Fuzzy Syst..

[5]  Shengen Yan,et al.  Deep Image: Scaling up Image Recognition , 2015, ArXiv.

[6]  Stavros Ntalampiras.  Fault Identification in Distributed Sensor Networks Based on Universal Probabilistic Modeling , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[7]  Amy Loutfi,et al.  A review of unsupervised feature learning and deep learning for time-series modeling , 2014, Pattern Recognit. Lett..

[8]  Thierry Denoeux,et al.  Partially supervised Independent Factor Analysis using soft labels elicited from multiple experts: application to railway track circuit diagnosis , 2012, Soft Comput..

[9]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[10]  Paul Weston,et al.  Fault detection and diagnosis for railway track circuits using neuro-fuzzy systems , 2008 .

[11]  Huibing Zhao,et al.  Fault Diagnosis in Railway Track Circuits Using Support Vector Machines , 2013, 2013 12th International Conference on Machine Learning and Applications.

[12]  Jye-Chyi Lu,et al.  Equipment fault detection using spatial signatures , 1997 .

[13]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[14]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[15]  Arun Somani,et al.  Distributed fault detection of wireless sensor networks , 2006, DIWANS '06.

[16]  Tara N. Sainath,et al.  Convolutional, Long Short-Term Memory, fully connected Deep Neural Networks , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[17]  Navdeep Jaitly,et al.  Towards End-To-End Speech Recognition with Recurrent Neural Networks , 2014, ICML.

[18]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .

[19]  P J Webros.  BACKPROPAGATION THROUGH TIME: WHAT IT DOES AND HOW TO DO IT , 1990 .

[20]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[21]  Li Deng,et al.  Ensemble deep learning for speech recognition , 2014, INTERSPEECH.

[22]  Dexian Huang,et al.  Data-driven soft sensor development based on deep learning technique , 2014 .

[23]  Kwon Soon Lee,et al.  Fault Detection and Isolation of Induction Motors Using Recurrent Neural Networks and Dynamic Bayesian Modeling , 2010, IEEE Transactions on Control Systems Technology.

[24]  Thierry Denoeux,et al.  Fault diagnosis in railway track circuits using Dempster-Shafer classifier fusion , 2010, Eng. Appl. Artif. Intell..

[25]  Oliver Obst,et al.  Distributed Fault Detection in Sensor Networks using a Recurrent Neural Network , 2009, Neural Processing Letters.

[26]  Michael J. Watts,et al.  IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS Publication Information , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[27]  Erich Elsen,et al.  Deep Speech: Scaling up end-to-end speech recognition , 2014, ArXiv.