Research on Multi-Objective Real-Time Optimization of Automatic Train Operation (ATO) in Urban Rail Transit

doi:10.1007/s12204-018-1941-x

Abstract

Abstract: The determination and optimization of Automatic Train Operation (ATO) control strategy is one of the most critical technologies for urban rail train operation. The practical ATO optimal control strategy must consider many goals of the train operation, such as safety, accuracy, comfort, energy saving and so on. This paper designs a set of efficient and universal multi-objective control strategy. Firstly, based on the analysis of urban rail transit and its operating environment, the multi-objective optimization model considering all the indexes of train operation is established by using multi-objective optimization theory. Secondly, Non-dominated Sorting Genetic Algorithm II (NSGA-II) is used to solve the model, and the optimal speed curve of train running is generated. Finally, the intelligent controller is designed by the combination of fuzzy controller algorithm and the predictive control algorithm, which can control and optimize the train operation in real time. Then the robustness of the control system can ensure and the requirements for multi-objective in train operation can be satisfied.

Key words: urban rail transit| multi-objective| Automatic Train Operation (ATO)| Non-dominated Sorting Genetic Algorithm II (NSGA-II)| fuzzy predictive controller

摘要： The determination and optimization of Automatic Train Operation (ATO) control strategy is one of the most critical technologies for urban rail train operation. The practical ATO optimal control strategy must consider many goals of the train operation, such as safety, accuracy, comfort, energy saving and so on. This paper designs a set of efficient and universal multi-objective control strategy. Firstly, based on the analysis of urban rail transit and its operating environment, the multi-objective optimization model considering all the indexes of train operation is established by using multi-objective optimization theory. Secondly, Non-dominated Sorting Genetic Algorithm II (NSGA-II) is used to solve the model, and the optimal speed curve of train running is generated. Finally, the intelligent controller is designed by the combination of fuzzy controller algorithm and the predictive control algorithm, which can control and optimize the train operation in real time. Then the robustness of the control system can ensure and the requirements for multi-objective in train operation can be satisfied.

关键词: urban rail transit| multi-objective| Automatic Train Operation (ATO)| Non-dominated Sorting Genetic Algorithm II (NSGA-II)| fuzzy predictive controller

CLC Number:

U 661

HE Tong (何彤), XIONG Ruiqi (熊瑞琦). Research on Multi-Objective Real-Time Optimization of Automatic Train Operation (ATO) in Urban Rail Transit[J]. Journal of Shanghai Jiao Tong University (Science), 2018, 23(2): 327-335.

References

[1] LI C, WANG XM. An ATO control strategy based onparticle swarm optimization [J]. Journal of the ChinaRailway Society, 2017, 39(3): 53-58 (in Chinese). [2] YANG C X, LIU L, WANG C L. Optimization of highspeedtrain speed curve based on genetic algorithm [J].Railway Computer Application, 2012, 21(1): 9-12 (inChinese). [3] MENG J J, YIN M, QI W Z, et al. Optimization oftracing target curve of high speed train ATO basedon genetic algorithm [J]. Computer Engineering andApplications, 2016, 52(21): 247-251 (in Chinese). [4] LUO R S, WANG Y H, YU Z Y, et al. Adaptive stoppingcontrol of urban rail vehicle [J]. Journal of theChina Railway Society, 2012, 34 (4): 64-68 (in Chinese). [5] JIA L M, ZHANG X D, XIE Z T. Automatic traincontrol—an intelligent approach [C]//Proceedings ofIEEE on Tencon 93 Computer Communication. Beijing:IEEE, 1993, 4(4): 338-342. [6] KIM K, CHIEN S. Optimal train operation for minimumenergy consumption considering track alignment,speed limit, and schedule adherence [J]. Journal ofTransportation Engineering, 2011, 137(9): 665-674. [7] TANG H C, DICK C T, FENG X Y. A coordinatedtrain control algorithm to improve regenerative energyreceptivity in metro transit systems [C]//Proceedingsof Transportation Research Board 94th Annual Metting.Washington: Transportation Research Board,2015, 15(1): 13-18. [8] LEI D M, YAN X P. Multiple objective intelligent optimizationalgorithms and application [M]. Beijing: SciencePress, 2009 (in Chinese). [9] DEB K, PRATAP A, AGARWAL S, et al. A fastand elitsit multiobjective genetic algorithm: NSGA-II[J]. IEEE Transactions on Evolutionary Computation,2002, 6(2): 182-197. [10] GAO B, DONG H R, NING B. Speed control algorithmfor automatic train operation systems [J]. ComputatinalIntelligenceand Software Engineering, 2009,120(4): 1-4. [11] LARRANAGA M, ANSELMI J, AYESTA U, et al.Optimization techniques applied to railway systems[J]. Basque Center for Applied Mathematics, 2013,1(24): 27-45. [12] ZHAO N, ROBERTS C, HILLMANSEN S, et al. Amultiple train trajectory optimization to minimize energyconsumption and delay [J]. IEEE Transactions onIntelligent Transportation Systems, 2015, 16(5): 2363-2372. [13] ZHAO W T, GAO C H. A new control methd of automatictrain operation in urban rail transit basedon improved generalized predictive control theroy[C]//Proceedings of the 2013 Interational Conferenceon Electrical and Information Technologies for RailTransportation. Changchun: Interational Conferenceon Electrical and Information Technologies for RailTransportation, 2014, 56(287): 567-573. [14] LI G Y, YANG L J. Neural, fuzzy, predictive controland its realization [M]. Beijing: Electronic IndustryPress, 2013 (in Chinese). [15] LU Q H, FENG X Y, WANG Q Y. Energy-saving optimalcontrol of following trains based on genetic algorithm[J]. Journal of Southwest Jiaotong University,2012, 47(2): 265-270 (in Chinese). [16] YAO L. Research on optimization of automatic trainoperation system based on intelligent control algorithm[D]. Beijing, Beijing Jiaotong University, 2009(in Chinese).