Abstract: The uneven distribution of the temperature field in the track structure, caused by various meteorological factors such as extremely low temperatures and snowfall, leads to significant temperature loads and is the primary cause of damage to China Railway Track System (CRTS) III ballastless tracks in cold regions during service. In this study, to predict the temperature of the track structure accurately, we analyzed meteorological data collected from Shenyang, China, and identified the factors that had the most effect on the track temperature field. We propose a temporal convolutional network (TCN)-based temperature field prediction model for ballastless tracks (TCN-Track model), which enhances the ability to extract and fuse local and global features from complex long-term meteorological data. The results indicate that the proposed TCN-Track model performs well in predicting track temperature fields from meteorological data, with a mean absolute error (MAE) ranging from 0.26 to 0.39, a root mean square error (RMSE) ranging from 0.32 to 0.50, and correlation coefficient (R) values ranging from 0.888 to 0.985. Compared with a long short-term memory (LSTM) model, the MAE of the TCN-Track model is reduced by 89.17% and the RMSE by 88.51%. This method offers a new solution for accurately predicting the temperature field of ballastless tracks in cold regions, aiding in predicting and preventing track damage caused by low temperatures.

基于TCN-Track模型的寒区CRTS III无砟轨道温度场预测研究

[1]AnjaliT, ChandiniK, AnoopK, et al., 2019. Temperature prediction using machine learning approaches. The 2nd International Conference on Intelligent Computing, Instrumentation and Control Technologies, p.1264-1268.

[2]ArasuAI, ModaniM, VadlamaniNR, 2022. Application of machine learning techniques in temperature forecast. The 21st IEEE International Conference on Machine Learning and Applications, p.513-518.

[3]BaiSJ, KolterJZ, KoltunV, 2018. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv:1803.01271.

[4]BerwangerC, SymkoY, 1976. Finite-element solutions for thermal stresses in steel-concrete composite bridges. Experimental Mechanics, 16(5):168-175.

[5]ChenW, LiSQ, WangWD, et al., 2024. Analysis on crack propagation of CRTS III slab ballastless track under temperature loads and freeze–thaw deterioration. Theoretical and Applied Fracture Mechanics, 129:104206.

[6]ChongW, TramontiniR, Pivoto SpechtL, 2009. Application of the Laplace transform and its numerical inversion to temperature profile of a two-layer pavement under site conditions. Numerical Heat Transfer, Part A: Applications, 5(11):1004-1018.

[7]DuW, RenJJ, ZhangKY, et al., 2023. Two-stage identification of interlayer contact loss for CRTS III prefabricated slab track based on multi-index fusion. Journal of Zhejiang University-SCIENCE A, 24(6):497-515.

[8]EsperJ, TorbensonM, BüntgenU, 2024. 2023 Summer warmth unparalleled over the past 2,000 years. Nature, 631(8019):94-97.

[9]GhimireS, Nguyen-HuyT, Al-MusaylhMS, et al., 2023. Integrated multi-head self-attention transformer model for electricity demand prediction incorporating local climate variables. Energy and AI, 14:100302.

[10]HewageP, BeheraA, TrovatiM, et al., 2020. Temporal convolutional neural (TCN) network for an effective weather forecasting using time-series data from the local weather station. Soft Computing, 24(21):16453-16482.

[11]HongS, ParkC, ChoS, 2021. A rail-temperature-prediction model based on machine learning: warning of train-speed restrictions using weather forecasting. Sensors, 21(13):4606.

[12]HongSU, KimHU, LimNH, et al., 2019. A rail-temperature-prediction model considering meteorological conditions and the position of the sun. International Journal of Precision Engineering and Manufacturing, 20(3):337-346.

[13]JinC, 2020. Research on temperature and stress evolution of CRTS III ballastless track slab. Master Thesis, East China Jiaotong University, Nanchang, China(in Chinese).

[14]KanjanunK, YanB, YaoSA, et al., 2021. GRNN prediction model for temperature-induced deformation of CRTS II unballasted slab track. Applied Science and Engineering Progress, 15(4):5662.

[15]LeaC, FlynnMD, VidalR, et al., 2017. Temporal convolutional networks for action segmentation and detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, p.1003-1012.

[16]LiuHM, LuHY, HeYL, et al., 2018. Neural network based temperature field mapping model for CRTS II type ballastless track. IOP Conference Series: Materials Science and Engineering, 435:012042.

[17]LiuJ, ZhangT, HanGJ, et al., 2018. TD-LSTM: temporal dependence-based LSTM networks for marine temperature prediction. Sensors, 18(11):3797.

[18]LiuR, SongL, CaoJW, et al., 2023. Early warping deformation of high-speed railway CRTS III track slabs. Engineering Structures, 294:116651.

[19]LiuS, ChenXH, YangJ, et al., 2020. Numerical study and in-situ measurement of temperature features of asphalt supporting layer in slab track system. Construction and Building Materials, 233:117343.

[20]LouP, ShiT, 2023. Thermal arching and interfacial damage evolution of CRTS-II slab track under solar radiation in alpine and Plateau regions. Alexandria Engineering Journal, 74:301-315.

[21]MirambellE, AguadoA, 1990. Temperature and stress distributions in concrete box girder bridges. Journal of Structural Engineering, 116(9):2388-2409.

[22]MOHURD (Ministry of Housing and Urban-Rural Development of the People’s Republic of China), 2012. Design Code for Heating Ventilation and Air Conditioning of Civil Buildings, GB 50736-2012. National Standards of the People’s Republic of China(in Chinese).

[23]NgamkhanongC, KaewunruenS, 2022. Prediction of thermal-induced buckling failures of ballasted railway tracks using artificial neural network (ANN). International Journal of Structural Stability and Dynamics, 22(5):2250049.

[24]OuZM, LiFJ, 2014. Analysis and prediction of the temperature field based on in-situ measured temperature for CRTS-II ballastless track. Energy Procedia, 61:1290-1293.

[25]OuZM, SunL, ChengQQ, 2015. Simplified calculation of temperature field in high-speed railway ballastless track structure. Journal of Zhejiang University (Engineering Science), 49(3):482-487 (in Chinese).

[26]RenJJ, DengSJ, ZhangKY, et al., 2021. Design theories and maintenance technologies of slab tracks for high-speed railways in China: a review. Transportation Safety and Environment, 3(4):tdab024.

[27]RenJJ, ZhangSY, XuXS, et al., 2022. Progress of research on service performance evolution and improvement technology of ballastless track in cold regions. Chinese Railways, (8):76-87 (in Chinese).

[28]RenJJ, QuCH, LiangJ, et al., 2024a. Experimental study on temperature field characteristics of CRTS III prefabricated slab track in cold regions. Archives of Civil and Mechanical Engineering, 24(3):152.

[29]RenJJ, DuJH, ZhangKY, et al., 2024b. Transfer relation between subgrade frost heave and slab track deformation and vehicle dynamic response in seasonally frozen ground. Journal of Zhejiang University-SCIENCE A, 25(2):130-146.

[30]SadhukhanB, ChakrabortyS, MukherjeeS, 2022. Investigating the relationship between earthquake occurrences and climate change using RNN-based deep learning approach. Arabian Journal of Geosciences, 15(1):31.

[31]ShrivastavaVK, ShrivastavaA, SharmaN, et al., 2023. Deep learning model for temperature prediction: an empirical study. Modeling Earth Systems and Environment, 9(2):2067-2080.

[32]SunZ, LouP, HuangXD, 2023. Temperature gradient of ballastless track in large daily temperature difference region and its influence on dynamic responses of vehicle-track-bridge system. Alexandria Engineering Journal, 85:114-131.

[33]WangD, 2010. Analytical Solutions for Temperature Profile Prediction in Multi-Layered Pavement Systems. PhD Thesis, University of Illinois at Urbana-Champaign, Champaign-Urbana, USA.

[34]WangJ, GaoL, ZhaoWQ, et al., 2022. Evolution mechanism of interlayer fatigue properties of CRTS III slab track. Construction and Building Materials, 360:129459.

[35]WangSR, GaoJZ, LinC, et al., 2023. Condition assessment of high-speed railway track structure based on sparse Bayesian extreme learning machine and Bayesian hypothesis testing. International Journal of Rail Transportation, 11(3):364-388.

[36]XieHR, XuLY, YanB, 2023. Mechanical properties of ballastless track considering freeze–thaw deterioration damage. Mathematics, 11(10):2289.

[37]XuB, DanHC, LiL, 2017. Temperature prediction model of asphalt pavement in cold regions based on an improved BP neural network. Applied Thermal Engineering, 120:568-580.

[38]YangRS, WanZB, LiuXY, et al., 2015. Temperature field test of CRTS I twin-block ballastless track in winter. Journal of Southwest Jiaotong University, 50(3):454-460.

[39]YangY, ZhouH, WuJR, et al., 2022. Robustified extreme learning machine regression with applications in outlier-blended wind-speed forecasting. Applied Soft Computing, 122:108814.

[40]YeWL, RenJJ, LiC, et al., 2024. Intelligent detection of surface defects in high‐speed railway ballastless track based on self‐attention and transfer learning. Structural Control and Health Monitoring, 2024:2967927.

[41]YuZW, XieY, TianXQ, 2019. Research on mechanical performance of CRTS III plate-type ballastless track structure under temperature load based on probability statistics. Advances in Civil Engineering, 2019:2975274.

[42]ZhangQQ, DaiGL, TangY, 2022. Thermal analysis and prediction methods for temperature distribution of slab track using meteorological data. Sensors, 22(17):6345.

[43]ZhaoLH, CheYN, 2022. Numerical simulation of temperature field of CRTS III ballastless track with tarmac in Harbin area. Highlights in Science, Engineering and Technology, 28:360-366.

[44]ZhouL, ZhangTQ, LuoYY, 2023. Insights of the vehicle-track-girder system dynamic response changes caused by the thermal deformation of CRTS III ballastless track in the natural environment. Construction and Building Materials, 400:132745.

[45]ZhouR, ZhangYY, XuHB, et al., 2024. Comparing various neural network methods for temperature prediction of CRTS II slab track on transition sections. Intelligent Transportation Infrastructure, 3:liae004.