Energy-Efficient Automatic Train Driving by Learning Driving Patterns

Railway is regarded as the most sustainable means of modern transportation. With the fast-growing of fleet size and the railway mileage, the energy consumption of trains is becoming a serious concern globally. The nature of railway offers a unique opportunity to optimize the energy efficiency of locomotives by taking advantage of the undulating terrains along a route. The derivation of an energy-optimal train driving solution, however, proves to be a significant challenge due to the high dimension, nonlinearity, complex constraints, and timevarying characteristic of the problem. An optimized solution can only be attained by considering both the complex environmental conditions of a given route and the inherent characteristics of a locomotive. To tackle the problem, this paper employs a high-order correlation learning method for online generation of the energy optimized train driving solutions. Based on the driving data of experienced human drivers, a hypergraph model is used to learn the optimal embedding from the specified features for the decision of a driving operation. First, we design a feature set capturing the driving status. Next all the training data are formulated as a hypergraph and an inductive learning process is conducted to obtain the embedding matrix. The hypergraph model can be used for real-time generation of driving operation. We also proposed a reinforcement updating scheme, which offers the capability of sustainable enhancement on the hypergraph model in industrial applications. The learned model can be used to determine an optimized driving operation in real-time tested on the Hardware-in-Loop platform. Validation experiments proved that the energy consumption of the proposed solution is around 10% lower than that of average human drivers.

[1]  Xuan Vu,et al.  Optimal train control: Analysis of a new local optimization principle , 2011, Proceedings of the 2011 American Control Conference.

[2]  Bijan Moaveni,et al.  Automatic Train Control based on the Multi-Agent Control of Cooperative Systems , 2010 .

[3]  Avrim Blum,et al.  Correlation Clustering , 2004, Machine Learning.

[4]  Dinggang Shen,et al.  View‐aligned hypergraph learning for Alzheimer's disease diagnosis with incomplete multi‐modality data , 2017, Medical Image Anal..

[5]  Xiang Li,et al.  A Survey on Energy-Efficient Train Operation for Urban Rail Transit , 2016, IEEE Transactions on Intelligent Transportation Systems.

[6]  Chen Yao,et al.  Neuro-adaptive and robust automatic train control subject to unknown dynamics , 2013, Proceedings of the 32nd Chinese Control Conference.

[7]  Mato Baotic,et al.  Optimal rail route energy management under constraints and fixed arrival time , 2009, 2009 European Control Conference (ECC).

[8]  John R. Anderson,et al.  MACHINE LEARNING An Artificial Intelligence Approach , 2009 .

[9]  Phil Howlett,et al.  Energy-efficient train control , 1994 .

[10]  Masafumi Miyatake,et al.  Optimization of Train Speed Profile for Minimum Energy Consumption , 2010 .

[11]  Chung Min Kwan,et al.  Evaluation of Evolutionary Algorithms for Multi-objective Train Schedule Optimization , 2004, Australian Conference on Artificial Intelligence.

[12]  M. Meyer,et al.  An algorithm for the optimal control of the driving of trains , 2000, Proceedings of the 39th IEEE Conference on Decision and Control (Cat. No.00CH37187).

[13]  Gang Hua,et al.  Hyperspectral Image Classification Through Bilayer Graph-Based Learning , 2014, IEEE Transactions on Image Processing.

[14]  John T. Betts,et al.  Practical Methods for Optimal Control and Estimation Using Nonlinear Programming , 2009 .

[15]  Qingshan Liu,et al.  Elastic Net Hypergraph Learning for Image Clustering and Semi-Supervised Classification , 2016, IEEE Transactions on Image Processing.

[16]  Hou Zhongsheng.  Study on Energy-saving Control for Train Based on Genetic Algorithm , 2007 .

[17]  Jin Huang,et al.  An Energy-Efficient Train Control Framework for Smart Railway Transportation , 2016, IEEE Transactions on Computers.

[18]  Clive Roberts,et al.  Single-Train Trajectory Optimization , 2013, IEEE Transactions on Intelligent Transportation Systems.

[19]  Francesco Corman,et al.  Closing the loop in real-time railway control: Framework design and impacts on operations , 2015 .

[20]  Boi Faltings,et al.  Hypergraph Learning with Hyperedge Expansion , 2012, ECML/PKDD.

[21]  Hyun Jun Park,et al.  An optimal automatic train operation (ATO) control using genetic algorithms (GA) , 1999, Proceedings of IEEE. IEEE Region 10 Conference. TENCON 99. 'Multimedia Technology for Asia-Pacific Information Infrastructure' (Cat. No.99CH37030).

[22]  Edwin R. Hancock,et al.  Joint hypergraph learning and sparse regression for feature selection , 2017, Pattern Recognit..

[23]  Yue Gao,et al.  3-D Object Retrieval and Recognition With Hypergraph Analysis , 2012, IEEE Transactions on Image Processing.

[24]  Chiara Macchiavello,et al.  Multipartite entanglement detection for hypergraph states , 2017, 1703.00429.

[25]  Weifeng Zhong,et al.  Energy-efficient train reference speed profile optimization using control parameterization method , 2016, CCC 2016.

[26]  Eugene Khmelnitsky,et al.  On an optimal control problem of train operation , 2000, IEEE Trans. Autom. Control..

[27]  Junwei Han,et al.  A Unified Metric Learning-Based Framework for Co-Saliency Detection , 2018, IEEE Transactions on Circuits and Systems for Video Technology.

[28]  Deyu Meng,et al.  Co-Saliency Detection via a Self-Paced Multiple-Instance Learning Framework , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.