Intelligent operation of heavy haul train with data imbalance: A machine learning method

Abstract Compared with high speed trains and metro subways, heavy haul train operations are more challenging for their complex dynamic characteristics and complicated running environments. When running on a continuous and steep descent, the air brake operation strategy has become the most important issue for the safety and efficiency of heavy haul train transportation. Due to the difficulty in modeling the train’s dynamics and pneumatic brake system precisely, this paper addresses the intelligent driving problem for heavy haul train based on the fusion of expert knowledge and machine learning methodologies. By considering the characteristics of manual driving on steep descent, the pneumatic brake operation problem is formulated as a multi-class classification model. To overcome the negative influences of data imbalances, EasyEnsemble for the multi-class with a KNN based Denoising (EMKD) algorithm is introduced to determine the feasible Air Pressure Reduction (APR) and the exact time for exerting and releasing the air brake. This approach utilizes the EasyEnsemble.M algorithm to moderate the class imbalanced datasets and takes advantage of the AdaBoost.M1 algorithm to ensemble weak classifiers. Specifically, the K-nearest neighbor based Denoising (KD) algorithm is elaborated to remove the possible noise data from the minority dataset. Additionally, expert knowledge is obtained by abstracting the experience of sophisticated drivers and technical specifications, which are employed as operating constraints to regulate the output of the EMKD algorithm. The operational safety in terms of the in-train forces and punctuality of the proposed algorithm are validated by a number of experiments under the real running circumstances of Shuohuang heavy haul railway.

[1]  Xiaohua Xia,et al.  Optimal Scheduling and Control of Heavy Haul Trains Equipped With Electronically Controlled Pneumatic Braking Systems , 2006, IEEE Transactions on Control Systems Technology.

[2]  Hong Shen,et al.  Imbalanced data classification based on hybrid resampling and twin support vector machine , 2017, Comput. Sci. Inf. Syst..

[3]  Francisco Charte,et al.  MLSMOTE: Approaching imbalanced multilabel learning through synthetic instance generation , 2015, Knowl. Based Syst..

[4]  Xiangtao Zhuan,et al.  Development of an Optimal Operation Approach in the MPC Framework for Heavy-Haul Trains , 2015, IEEE Transactions on Intelligent Transportation Systems.

[5]  Wei Wei,et al.  An air brake model for longitudinal train dynamics studies , 2017 .

[6]  Zhang Bo.  Simulation Study of Heavy Haul Train Operation on Datong-Qinhuangdao Railway , 2008 .

[7]  Dewang Chen,et al.  Soft computing methods applied to train station parking in urban rail transit , 2012, Appl. Soft Comput..

[8]  Saeed Mohammadi,et al.  The Effects of Train Brake Delay Time on In-Train Forces , 2010 .

[9]  Xuelong Li,et al.  Asymmetric bagging and random subspace for support vector machines-based relevance feedback in image retrieval , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Yanqing Zhang,et al.  SVMs Modeling for Highly Imbalanced Classification , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[11]  Dewang Chen,et al.  Smart train operation algorithms based on expert knowledge and ensemble CART for the electric locomotive , 2016, Knowl. Based Syst..

[12]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[13]  Artyom Plyaskin,et al.  The Heavy Haul Train Service on the Eastern Section of the Baikal-Amur Mainline , 2017 .

[14]  Phil G. Howlett,et al.  Local energy minimization in optimal train control , 2009, Autom..

[15]  Dewang Chen,et al.  Data-driven train operation models based on data mining and driving experience for the diesel-electric locomotive , 2016, Adv. Eng. Informatics.

[16]  Jing Wang,et al.  Decentralized control of heavy-haul trains with input constraints and communication delays , 2013 .

[17]  Dewang Chen,et al.  Intelligent Train Operation Algorithms for Subway by Expert System and Reinforcement Learning , 2014, IEEE Transactions on Intelligent Transportation Systems.

[18]  MengChu Zhou,et al.  A Noise-Filtered Under-Sampling Scheme for Imbalanced Classification , 2017, IEEE Transactions on Cybernetics.

[19]  Lei Chen,et al.  A neural network driving curve generation method for the heavy-haul train , 2016 .

[20]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[21]  Taghi M. Khoshgoftaar,et al.  RUSBoost: A Hybrid Approach to Alleviating Class Imbalance , 2010, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[22]  Xiaohua Xia,et al.  Modeling and Control of Heavy-Haul Trains [Applications of Control] , 2011, IEEE Control Systems.

[23]  Ziyou Gao,et al.  Joint optimal train regulation and passenger flow control strategy for high-frequency metro lines , 2017 .

[24]  Edward Y. Chang,et al.  KBA: kernel boundary alignment considering imbalanced data distribution , 2005, IEEE Transactions on Knowledge and Data Engineering.

[25]  Francisco Herrera,et al.  SMOTE-IPF: Addressing the noisy and borderline examples problem in imbalanced classification by a re-sampling method with filtering , 2015, Inf. Sci..

[26]  R. Schapire.  The Strength of Weak Learnability , 1990, Machine Learning.

[27]  Liu Xiao,et al.  BPSO-Adaboost-KNN ensemble learning algorithm for multi-class imbalanced data classification , 2016 .

[28]  Ziyou Gao,et al.  Adaptive coordinated control of multiple high-speed trains with input saturation , 2016 .

[29]  Ziyou Gao,et al.  Optimal Guaranteed Cost Cruise Control for High-Speed Train Movement , 2016, IEEE Transactions on Intelligent Transportation Systems.

[30]  Tao Tang,et al.  Optimal operation of high-speed train based on fuzzy model predictive control , 2017 .

[31]  Richard Weber,et al.  Feature selection for high-dimensional class-imbalanced data sets using Support Vector Machines , 2014, Inf. Sci..

[32]  Frank L. Lewis,et al.  Distributed Fault-Tolerant Control of Virtually and Physically Interconnected Systems With Application to High-Speed Trains Under Traction/Braking Failures , 2016, IEEE Transactions on Intelligent Transportation Systems.

[33]  Francisco Herrera,et al.  A Review on Ensembles for the Class Imbalance Problem: Bagging-, Boosting-, and Hybrid-Based Approaches , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[34]  Xiaohua Xia,et al.  OPTIMAL CRUISE CONTROL OF HEAVY-HAUL TRAIN EQUIPPED WITH ELECTRONIC CONTROLLED PNEUMATIC BRAKE SYSTEMS , 2007 .

[35]  Albert Y. Zomaya,et al.  Particle Swarm Optimization based dictionary learning for remote sensing big data , 2015, Knowl. Based Syst..

[36]  Liu Xiao,et al.  Adapted ensemble classification algorithm based on multiple classifier system and feature selection for classifying multi-class imbalanced data , 2016 .

[37]  Huosheng Hu,et al.  Modelling and control design for an electro-pneumatic braking system in trains with multiple locomotives , 2012, Int. J. Model. Identif. Control..

[38]  Colin Cole,et al.  Current train control optimization methods with a view for application in heavy haul railways , 2012 .

[39]  Dewang Chen,et al.  Intelligent driving methods based on expert knowledge and online optimization for high-speed trains , 2017, Expert Syst. Appl..

[40]  Ito Wasito,et al.  Nearest neighbour approach in the least-squares data imputation algorithms , 2005, Inf. Sci..

[41]  Zhi-Hua Zhou,et al.  Exploratory Under-Sampling for Class-Imbalance Learning , 2006, Sixth International Conference on Data Mining (ICDM'06).

[42]  Tao Tang,et al.  Fuzzy Constrained Predictive Optimal Control of High Speed Train with Actuator Dynamics , 2016 .

[43]  Changyin Sun,et al.  Support vector machine-based optimized decision threshold adjustment strategy for classifying imbalanced data , 2015, Knowl. Based Syst..