Deep Sparse Autoencoder for Feature Extraction and Diagnosis of Locomotive Adhesion Status

The model is difficult to establish because the principle of the locomotive adhesion process is complex. This paper presents a data-driven adhesion status fault diagnosis method based on deep learning theory. The adhesion coefficient and creep speed of a locomotive constitute the characteristic vector. The sparse autoencoder unsupervised learning network studies the input vector, and the single-layer network is superimposed to form a deep neural network. Finally, a small amount of labeled data is used to fine-tune training the entire deep neural network, and the locomotive adhesion state fault diagnosis model is established. Experimental results show that the proposed method can achieve a 99.3% locomotive adhesion state diagnosis accuracy and satisfy actual engineering monitoring requirements.

[1]  Diego Cabrera,et al.  Fault Diagnosis for Rotating Machinery Using Vibration Measurement Deep Statistical Feature Learning , 2016, Sensors.

[2]  Maksym Spiryagin,et al.  Theoretical investigation of the effect of rail cleaning by wheels on locomotive tractive effort , 2016 .

[3]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[4]  Gerard Ledwich,et al.  Wheel slip control based on traction force estimaton of electric locomotives , 2016, 2016 Australasian Universities Power Engineering Conference (AUPEC).

[5]  Claude Delpha,et al.  An optimal fault detection threshold for early detection using Kullback-Leibler Divergence for unknown distribution data , 2016, Signal Process..

[6]  Wei Zhang,et al.  A New Deep Learning Model for Fault Diagnosis with Good Anti-Noise and Domain Adaptation Ability on Raw Vibration Signals , 2017, Sensors.

[7]  Gang Li,et al.  Fault Diagnosis and Application to Modern Systems , 2017, J. Control. Sci. Eng..

[8]  Yibin Li,et al.  Facial Expression Recognition with Fusion Features Extracted from Salient Facial Areas , 2017, Sensors.

[9]  Antonio Jesús Guerra Fernández,et al.  A Novel Electrohydraulic Brake System With Tire–Road Friction Estimation and Continuous Brake Pressure Control , 2016, IEEE Transactions on Industrial Electronics.

[10]  Xiao He,et al.  Cloud-Based Fault Tolerant Control for a DC Motor System , 2017, J. Control. Sci. Eng..

[11]  Pingyu Jiang,et al.  A deep learning approach for relationship extraction from interaction context in social manufacturing paradigm , 2016, Knowl. Based Syst..

[12]  Doina Caragea,et al.  Ensemble-based semi-supervised learning approaches for imbalanced splice site datasets , 2014, 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[13]  Lorenzo Rosasco,et al.  Unsupervised learning of invariant representations , 2016, Theor. Comput. Sci..

[14]  Zhenfeng Shao,et al.  High-resolution remote-sensing imagery retrieval using sparse features by auto-encoder , 2015 .

[15]  Xiaoyun Feng,et al.  Optimized Adhesion Control of Locomotive Airbrake Based on GSA-RNN , 2015, 2015 7th International Conference on Intelligent Human-Machine Systems and Cybernetics.

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

[17]  Naif Alajlan,et al.  Deep learning approach for active classification of electrocardiogram signals , 2016, Inf. Sci..

[18]  Jianzhong Wu,et al.  Stacked Sparse Autoencoder (SSAE) for Nuclei Detection on Breast Cancer Histopathology Images , 2016, IEEE Transactions on Medical Imaging.

[19]  Jian-Huang Lai,et al.  Deep Representations Based on Sparse Auto-Encoder Networks for Face Spoofing Detection , 2016, CCBR.

[20]  Namig J. Guliyev,et al.  A Single Hidden Layer Feedforward Network with Only One Neuron in the Hidden Layer Can Approximate Any Univariate Function , 2015, Neural Computation.

[21]  Jianli Yang,et al.  A novel method of diagnosing premature ventricular contraction based on sparse auto-encoder and softmax regression. , 2015, Bio-medical materials and engineering.

[22]  Jing He,et al.  Automatic Recognition of adhesion States using an Extreme Learning Machine , 2017, Int. J. Robotics Autom..

[23]  Jing He,et al.  Online Estimation of the Adhesion Coefficient and Its Derivative Based on the Cascading SMC Observer , 2017, J. Sensors.

[24]  Haytham Elghazel,et al.  Unsupervised feature selection with ensemble learning , 2013, Machine Learning.

[25]  Huanxin Zou,et al.  Synthetic Aperture Radar Target Recognition with Feature Fusion Based on a Stacked Autoencoder , 2017, Sensors.

[26]  S. N. Deepa,et al.  Comparative analysis on hidden neurons estimation in multi layer perceptron neural networks for wind speed forecasting , 2017, Artificial Intelligence Review.

[27]  Qing Wu,et al.  Rail Cleaning Process and its Influence on Locomotive Performance , 2017 .

[28]  Yong Wang,et al.  Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction , 2017, Sensors.

[29]  Yike Guo,et al.  Automatic Sleep Stage Scoring Using Time-Frequency Analysis and Stacked Sparse Autoencoders , 2015, Annals of Biomedical Engineering.

[30]  Jia Liu,et al.  Maxout neurons for deep convolutional and LSTM neural networks in speech recognition , 2016, Speech Commun..