Intelligent Fault Detection of High-Speed Railway Turnout Based on Hybrid Deep Learning

With the purpose of detecting the turnout fault without label data and fault data timely, this paper proposes a hybrid deep learning framework com-bining the DDAE (Deep Denoising Auto-encoder) and one-class SVM (Support Vector Machine) for turnout fault detection only using normal data. The proposed method achieves an accuracy of 98.67% on the real turn-out dataset for current curve, which suggests that this work realizes the purpose of detecting the fault with only normal data and provides a basis for the intelligent fault detection of turnouts.

[1]  Robert P. W. Duin,et al.  Support vector domain description , 1999, Pattern Recognit. Lett..

[2]  Xi Wang,et al.  Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification , 2015, ACM Multimedia.

[3]  Xun Gong,et al.  Traffic flow forecasting based on hybrid deep learning framework , 2017, 2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE).

[4]  Pushpak Bhattacharyya,et al.  A Hybrid Deep Learning Architecture for Sentiment Analysis , 2016, COLING.

[5]  Jinling Liang,et al.  Multistability of complex-valued neural networks with distributed delays , 2016, Neural Computing and Applications.

[6]  Rasa Remenyte-Prescott,et al.  A fault detection method for railway point systems , 2016 .

[7]  Zhang Yi,et al.  Explicit guiding auto-encoders for learning meaningful representation , 2017, Neural Computing and Applications.

[8]  Yongfeng Ju,et al.  Algorithm of Railway Turnout Fault Detection Based on PNN Neural Network , 2014, 2014 Seventh International Symposium on Computational Intelligence and Design.

[9]  Uday Kumar,et al.  SVM Based Diagnostics on Railway Turnouts , 2012 .

[10]  Meng Qi Zhang,et al.  Railway Turnout Fault Diagnosis Based on Support Vector Machine , 2014 .

[11]  Li Xia,et al.  Fault diagnosis of high-speed railway turnout based on support vector machine , 2016, 2016 IEEE International Conference on Industrial Technology (ICIT).

[12]  Mehmet Sevkli,et al.  A Simple State-Based Prognostic Model for Railway Turnout Systems , 2011, IEEE Transactions on Industrial Electronics.

[13]  Mengjie Zhang,et al.  An Experimental Study on Hyper-parameter Optimization for Stacked Auto-Encoders , 2018, 2018 IEEE Congress on Evolutionary Computation (CEC).

[14]  Kai Zhang.  The railway turnout fault diagnosis algorithm based on BP neural network , 2014, 2014 IEEE International Conference on Control Science and Systems Engineering.

[15]  José Sá da Costa,et al.  Application of a novel fuzzy classifier to fault detection and isolation of the DAMADICS benchmark problem , 2006 .