Prolonged vibration can be uncomfortable for passengers utilizing urban rail transit systems. This study proposes an automatic speed control framework for urban railway trains to reduce vertical vibrations experienced by passengers. We suggest the concept of the “segmented comfort speed limit” to represent the vertical passing comfort of oncoming sections. This speed limit is calculated from 1/3 octave band acceleration and smoothed through lag-type speed control mode. The deep deterministic policy gradient algorithm with hindsight experience replay mechanism (HER-DDPG) is designed, to balance safety, comfort, and energy efficiency driving. Verify the speed control framework based on HER-DDPG through the rail data collected from Dalian Metro Line 12. Compared with the DDPG-based model, the vertical comfort is improved by 2.34%, and the longitudinal acceleration and total energy consumption are reduced by 45% and 8.1%. Compared with the real-world train control trajectory, HER-DDPG improves vertical comfort by 9.76% and reduces energy consumption by 12.4%. The results show that the proposed framework can effectively improve the ride experience of passengers.
PengYZhouJFanC, et al.A review of passenger ride comfort in railway: assessment and improvement method. Transp Safety Env2022; 4(2): 6606037. DOI: 10.1093/tse/tdac016.
2.
HodgeVJO'KeefeSWeeksM, et al.Wireless sensor networks for condition monitoring in the railway industry: a survey. IEEE Trans Inf Theor2015; 16(3): 1088–1106. DOI: 10.1109/TITS.2014.2366512.
3.
BarabinoBConiMOlivoA, et al.Standing passenger comfort: a new scale for evaluating the real-time driving style of bus transit services. IEEE Trans Inf Theor2019; 20(12): 4665–4678. DOI: 10.1109/TITS.2019.2921807.
4.
RoncoliCChandakasEKapariasI. Estimating on-board passenger comfort in public transport vehicles using incomplete automatic passenger counting data. Transp Res Part C Emerg2023; 146: 103963. DOI: 10.1016/j.trc.2022.103963.
AmielEAnastasopoulosMChevaleyreG, et al.On applying artificial intelligence techniques to maximise passengers comfort and infrastructure reliability in urban railway systems. IEEE proceedings of the 2023 8th international conference on models and technologies for intelligent transportation systems (MT-ITS), Nice, France, 11–16 June 2023, pp. 1–6. DOI: 10.1109/MT-ITS56129.2023.10241648.
7.
MeghoeALoenderslootRTingaT. Rail wear and remaining life prediction using meta-models. Int J Rail Transp2020; 8(1): 1–26. DOI: 10.1080/23248378.2019.1621780.
8.
HuangJKaewunruenS. Evaluation of railway passenger comfort with machine learning. IEEE Access2022; 10: 2372–2381. DOI: 10.1109/ACCESS.2021.3139465.
9.
JiangHLiXXinG, et al.Geometry mapping and additional stresses of ballast less track structure caused by subgrade differential settlement under self-weight loads in high-speed railways. Transp Geotech2019; 18: 103–110. DOI: 10.1016/j.trgeo.2018.10.007.
10.
Fernández-RodríguezAFernández-CardadorACucalaAP. Balancing energy consumption and risk of delay in high speed trains: a three-objective real-time eco-driving algorithm with fuzzy parameters. Transp Res Part C Emerg2018; 95: 652–678. DOI: 10.1016/j.trc.2018.08.009.
11.
CaoYMaLZhangY. Application of fuzzy predictive control technology in automatic train operation. Cluster Comput2019; 22(6): 14135–14144. DOI: 10.1007/s10586-018-2258-0.
12.
XuWXiaoB. Train control simulation based on CMAC-PID algorithm. IEEE proceedings of the 25th chinese control and decision conference (CCDC). Piscataway (NJ): IEEE, pp. 4476–4480. DOI: 10.1109/CCDC.2013.6561741.
13.
HuangFChengBTengN. A numerical model to predict three-dimensional interaction dynamic of low-medium-speed maglev vehicle–guideway bridge system. P I Mech Eng F-J Rai2021; 235(10): 1249–1267. DOI: 10.1177/0954409721996553.
14.
ZhouFTaoKYangY, et al.Multi train collaborative cruise control for passenger comfort. J Electron Meas Instrum2023; 37(2): 151–159. DOI: 10.13382/j.jemi.B2205989.
15.
YuJGuoXChenZ, et al.Path tracking control based on tube MPC and time delay motion prediction. IET Intell Transp Syst2020; 14: 1–12. DOI: 10.1049/iet-its.2019.0088.
16.
ChenYWuS. Framework of active obstacle avoidance for autonomous vehicle based on hybrid soft actor-critic algorithm. J Transport Eng Part A Syst2023; 149(4). DOI: 10.1061/JTEPBS.0000772.
17.
WuJZhouHLiuZ, et al.Ride comfort optimization via speed planning and preview semi-active suspension control for autonomous vehicles on uneven roads. IEEE Trans Veh Technol2020; 69(8): 8343–8355. DOI: 10.1109/TVT.2020.2996681.
18.
TanYZhangK. Real-time distributed cooperative adaptive cruise control model considering time delays and actuator lag. Transport Res Rec2022; 2676(11): 93–111. DOI: 10.1177/03611981221091762.
19.
WenYSunQZouY, et al.Study on the vibration suppression of a flexible carbody for urban railway vehicles with a magnetorheological elastomer-based dynamic vibration absorber. P I Mech Eng F-J Rai2020; 234(7): 749–764. DOI: 10.1177/0954409719865370.
20.
ZhuMWangYPuZ, et al.Safe, efficient, and comfortable velocity control based on reinforcement learning for autonomous driving. Transp Res Part C Emerg2020; 117: 102662. DOI: 10.1016/j.trc.2020.102662.
21.
ChenBZhangLChengG, et al.A novel approach for train tracking in virtual coupling based on soft actor-critic. Actuators2023; 12: 447. DOI: 10.3390/act12120447.
22.
LiuMLiYRongX, et al.Semi-active suspension control based on deep reinforcement learning. IEEE Access2020; 8: 9978–9986. DOI: 10.1109/ACCESS.2020.2964116.
23.
DuYChenJZhaoC, et al.Comfortable and energy-efficient speed control of autonomous vehicles on rough pavements using deep reinforcement learning. Transp Res Part C Emerg2022; 134: 103489. DOI: 10.1016/j.trc.2021.103489.
24.
DegrandeGSchillemansL. Free field vibrations during the passage of a Thalys high-speed train at variable speed. J Sound Vib2001; 247(1): 131–144. DOI: 10.1006/jsvi.2001.3718.
25.
FlorensaCHerdDGengX, et al.Automatic goal generation for reinforcement learning agents. PMLR proceedings of the 35th international conference on machine learning (ICML). New York (NY): PMLR Press, vol 80, pp. 1515–1528. https://proceedings.mlr.press/v80/florensa18a.html.
26.
RenZDongKZhouY, et al.Exploration via hindsight goal generation. In: NIPS'19 proceedings of the 33rd international conference on neural information processing systems (NeurIPS). New York (NY): Curran Associates Inc. Press.
27.
ISO 2631-1. Mechanical vibration and shock-evaluation of human exposure to whole-body vibration-Part 1: general requirements. Geneva: ISO, 1997.
28.
YeYZhangXSunJ. Automated vehicle’s behavior decision making using deep reinforcement learning and high-fidelity simulation environment. Transp Res Part C Emerg2019; 107: 155–170. DOI: 10.1016/j.trc.2019.08.011.
29.
KouroussisGConnollyDPVerlindenO. Railway-induced ground vibrations – a review of vehicle effects. Int J Rail Transp2014; 2(2): 69–110. DOI: 10.1080/23248378.2014.897791.
30.
ISO 2631-4. Mechanical vibration and shock - evaluation of human exposure to whole-body vibration - Part 4: guidelines for the evaluation of the effects of vibration and rotational motion on passenger and crew comfort. Fixed-guideway transport systems. Geneva: ISO, 2001.
31.
AndrychowiczMWolskiFRayA, et al.Hindsight experience replay. In: NIPS'17 Proceedings of the 31st international conference on neural information processing systems (NeurIPS). New York, NY: Curran Associates Inc. Press.
32.
YanSLiuCCaoJ. Comfort-based trajectory and velocity planning for automated vehicles considering road conditions. Int J Automot Technol2021; 22(4): 883–893. DOI: 10.1007/s12239-021-0080-9.
33.
WangLYeFWangY, et al.A Q-learning foresighted approach to ego-efficient lane changes of connected and automated vehicles on freeways. In: IEEE proceedings of the intelligent transportation systems conference (ITSC). Piscataway, NJ: IEEE. DOI: 10.1109/ITSC.2019.8917036.
34.
SunRChenYDubeyA, et al.Hybrid electric buses fuel consumption prediction based on real-world driving data. Transp. Res. B Transp. Environ2021; 91: 102637. DOI: 10.1016/j.trd.2020.102637.
