Smart Structures and Systems

  • 제32권2호
  • /
  • Pages.83-99
  • /
  • 2023
  • /
  • 1738-1584(pISSN)
  • /
  • 1738-1991(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Temperature distribution prediction in longitudinal ballastless slab track with various neural network methods

  • Hanlin Liu (Mining College, Guizhou University) ;
  • Wenhao Yuan (School of Civil Engineering & Traffic Engineering, Shenzhen University) ;
  • Rui Zhou (School of Civil Engineering & Traffic Engineering, Shenzhen University) ;
  • Yanliang Du (School of Civil Engineering & Traffic Engineering, Shenzhen University) ;
  • Jingmang Xu (MOE Key Laboratory of High-Speed, Railway Engineering, Southwest Jiaotong University) ;
  • Rong Chen (MOE Key Laboratory of High-Speed, Railway Engineering, Southwest Jiaotong University)
  • 투고 : 2023.04.10
  • 심사 : 2023.08.15
  • 발행 : 2023.08.25
⟨ 이전 논문 다음 논문 ⟩

초록

The temperature prediction approaches of three important locations in an operational longitudinal slab track-bridge structure by using three typical neural network methods based on the field measuring platform of four meteorological factors and internal temperature. The measurement experiment of four meteorological factors (e.g., ambient temperature, solar radiation, wind speed, and humidity) temperature in the three locations of the longitudinal slab and base plate of three important locations (e.g., mid-span, beam end, and Wide-Narrow Joint) were conducted, and then their characteristics were analyzed, respectively. Furthermore, temperature prediction effects of three locations under five various meteorological conditions are tested by using three neural network methods, respectively, including the Artificial Neural Network (ANN), the Long Short-Term Memory (LSTM), and the Convolutional Neural Network (CNN). More importantly, the predicted effects of solar radiation in four meteorological factors could be identified with three indicators (e.g., Root Means Square Error, Mean Absolute Error, Correlation Coefficient of R2). In addition, the LSTM method shows the best performance, while the CNN method has the best prediction effect by only considering a single meteorological factor.

키워드

과제정보

The authors gratefully acknowledge support from the National Key Technologies Research and Development Program "Transportation Infrastructure" "Reveal the list and take command" project (No.2022YFB2603301), National Natural Science Foundation (No. 52278311 and 52008264), the Shenzhen Science and Technology Program under the grant (Nos. GJHZ20220913143006012, GJHZ20200731095802007 and KQTD20180412181337494), Guizhou University talentproject [2022]68, in part by the Foundation of Key L aboratory of Large Structure Health Monitoring and Control in Hebei Province under Grant KLLSHMC2108,MOE Key Laboratory of High-Speed, Railway Engineering,Southwest Jiaotong University: 2021 Open Fund, the Ministry of Education. the Project of Science and t echnology research and development of China RailwayCo., Ltd (No. K2022G038) and the Guangdong Province Natural Science Foundation (No. 2023A1515030148 and 2022A1515010665).

참고문헌

  1. Cai, X.P., Luo, B.C., Zhong, Y.L., Zhang, Y.R. and Hou, B.W. (2019), "Arching mechanism of the slab joints in CRTSII slab track under high temperature conditions", Eng. Fail. Anal., 98, 95-108. https://doi.org/10.1016/j.engfailanal.2019.01.076
  2. Cossu, A., Carta, A., Lomonaco, V. and Bacciu, D. (2021), "Continual learning for recurrent neural networks: an empirical evaluation", Neural Netw., 143, 607-627. https://doi.org/10.1016/j.neunet.2021.07.021
  3. Dai, G. and Su, M. (2016), "Full-scale field experimental investigation on the interfacial shear capacity of continuous slab track structure", Arch. Civil Mech. Eng., 16(3), 485-493. https://doi.org/10.1016/j.acme.2016.03.005
  4. Dai, G., Tang, Y., Liang, J., Yang, L. and Chen, Y.F. (2018), "Temperature monitoring of high-speed railway bridges in mountainous areas", Struct. Eng. Int., 28(3), 288-295. https://doi.org/10.1080/10168664.2018.1464376
  5. Dai, B., Frusque, G., Li, Q. and Fink, O. (2022), "Acceleration-Guided Acoustic Signal Denoising Framework Based on Learnable Wavelet Transform Applied to Slab Track Condition Monitoring", IEEE Sens. J., 22(24), 24140-24149. https://doi.org/10.1109/JSEN.2022.3218182
  6. Guo, Y.Q., Li, Z.W., He, Y.L. and Lu, H.Y. (2018), "A novel method of fore-warning the positive temperature gradient of CRTS II ballastless track based on support vector machine", J. Railway Sci. Eng., 15(9), 2209-2216. [In Chinese]
  7. Guo, W., Wang, Y., Zhai, Z. and Du, Q. (2022), "Seismic control of high-speed railway bridge using S-shaped steel damping friction bearing", Smart Struct. Syst., Int. J., 30(5), 479-500. https://doi.org/10.12989/sss.2022.30.5.479
  8. Joseph Manoj, R., Anto Praveena, M.D. and Vijayakumar, K. (2019), "An ACO-ANN based feature selection algorithm for big data", Clust. Comput., 22(2), 3953-3960. https://doi.org/10.1007/s10586-018-2550-z
  9. Lee, S., Kim, H., Lieu, Q.X. and Lee, J. (2020), "CNN-based image recognition for topology optimization", Know Based Syst., 198, 105887. https://doi.org/10.1016/j.knosys.2020.105887
  10. Liu, S., Shi, C., Wang, T., Yang, J. and Chen, X. (2023), "Development of a new modified TSRST test to measure the thermal stress of asphalt supporting layer in the slab track system", Meas., 207, 112422. https://doi.org/10.1016/j.measurement.2022.112422
  11. Lou, P., Zhu, J., Dai, G. and Yan, B. (2018), "Experimental study on bridge-track system temperature actions for Chinese high-speed railway", Arch. Civil Mech. Eng., 18, 451-464. https://doi.org/10.1016/j.acme.2017.08.006
  12. Lu, D. and Wang, C. (2023), "Three-dimensional temperature field inversion calculation based on an artificial intelligence algorithm", Appl. Therm. Eng., 225, 120237. https://doi.org/10.1016/j.applthermaleng.2023.120237
  13. Ma, Z. and Gao, L. (2021), "Predicting mechanical state of high-speed railway elevated station track system using a hybrid prediction model", KSCE J. Civil Eng., 25(7), 2474-2486. https://doi.org/10.1007/s12205-021-1307-z
  14. Meenal, R. and Selvakumar, A.I. (2018), "Assessment of SVM, empirical and ANN based solar radiation prediction models with most influencing input parameters", Renew Energy, 121, 324-343. https://doi.org/10.1016/j.renene.2017.12.005
  15. Ren, J., Deng, S., Zhang, K., Du, W. and Wu, Q. (2021), "Design theories and maintenance technologies of slab tracks for high-speed railways in China: a review", Transport Safety Environ., 3(4), p. tdab024.
  16. Shi, T., Lou, P., Zheng, W. and Sheng, X. (2022), "A hybrid approach to predict vertical temperature gradient of ballastless track caused by solar radiation", Constr. Build. Mater., 352, 129063. https://doi.org/10.1016/j.conbuildmat.2022.129063
  17. Su, M., Dai, G., Marx, S., Liu, W. and Zhang, S. (2019), "A brief review of developments and challenges for high-speed rail bridges in China and Germany", Struct. Eng. Int., 29(1), 160-166. https://doi.org/10.1080/10168664.2018.1456892
  18. Su, M., Xie, H., Kang, C. and Li, S. (2021), "Determination of the interfacial properties of longitudinal continuous slab track via a field test and ANN-based approaches", Eng. Struct., 246, 113039. https://doi.org/10.1016/j.engstruct.2021.113039
  19. Wang, W., Hu, W., Wang, W., Xu, X., Wang, M., Shi, Y., Qiu, S. and Tutumluer, E. (2021), "Automated crack severity level detection and classification for ballastless track slab using deep convolutional neural network", Autom. Constr., 124, 103484. https://doi.org/10.1016/j.autcon.2020.103484
  20. Xin, X., Ren, Z., Yin, Y. and Gao, J. (2022), "Intelligent identification of mortar void in ballastless slab track using the wheelset acceleration combined with CNN-SVM", J. Mech. Sci. Technol., 36(12), 5845-5857. https://doi.org/10.1007/s12206-022-1103-9
  21. Xu, Q., Sun, S., Xu, Y., Hu, C., Chen, W. and Xu, L. (2022), "Influence of temperature gradient of slab track on the dynamic responses of the train-CRTS III slab track on subgrade nonlinear coupled system", Sci. Rep., 12(1), 14638. https://doi.org/10.1038/s41598-022-18898-y
  22. Yang, R., Li, J., Kang, W., Liu, X. and Cao, S. (2017), "Temperature characteristics analysis of the ballastless track under continuous hot weather", J. Transp. Eng. A-SYST., 143(9), 04017048. https://doi.org/10.1061/JTEPBS.0000076
  23. Yu, Y., Tang, L., Ling, X., Cai, D., Ye, Y. and Geng, L. (2020), "Mitigation of temperature-induced curling of concrete roadbed along highspeed railway: in situ experiment and numerical simulation", KSCE J. Civil Eng., 24(4), 1195-1208. https://doi.org/10.1007/s12205-020-0671-4
  24. Zhang, J., Jiang, H., Ding, F., Zhang, P., Zhou, F., Li, T. and Duan, N. (2020a), "Effects of metal-ceramic anticorrosion coating on the performance of ballastless tracks at high temperature", Arch. Civil Mech. Eng., 2, 120. https://doi.org/10.1007/s43452-020-00123-0
  25. Zhang, R., Liu, Y. and Sun, H. (2020b), "Physics-informed multi-LSTM networks for metamodeling of nonlinear structures", Comput. Methods Appl. Mech. Eng., 369, 113226. https://doi.org/10.1016/j.cma.2020.113226
  26. Zhang, Q., Dai, G. and Tang, Y. (2022), "Thermal Analysis and Prediction Methods for Temperature Distribution of Slab Track Using Meteorological Data", Sens., 22(17), 6345. https://doi.org/10.3390/s22176345
  27. Zhao, L., Zhou, L., Yu, Z., Mahunon, A.D., Peng, X. and Zhang, Y. (2021), "Experimental study on CRTS II ballastless track-bridge structural system mechanical fatigue performance", Eng Struct., 244, 112784. https://doi.org/10.1016/j.engstruct.2021.112784
  28. Zhou, H., Deng, Z., Xia, Y. and Fu, M. (2016), "A new sampling method in particle filter based on Pearson correlation coefficient", Neurocomputing, 216, 208-215. https://doi.org/10.1016/j.neucom.2016.07.036
  29. Zhou, W.B., Zhang, Y., Jiang, L., Feng, Y., Liu, X. and Lai, Z. (2021), "Critical coupling span number in high-speed railway simply supported beam bridge", Smart Struct. Syst., Int. J., 28(1), 13-28. https://doi.org/10.12989/sss.2021.28.1.013
  30. Zhou, R., Zhu, X., Huang, J., Zhou, H., Liu, H., Ma, C. and Zhang, L. (2022a), "Structural damage analysis of CRTS II slab track with various interface models under temperature combinations", Eng. Fail. Anal., 134, 106029. https://doi.org/10.1016/j.engfailanal.2022.106029
  31. Zhou, R., Zhu, X., Ren, W.X., Zhou, Z., Yao, G., Ma, C. and Du, Y. (2022b), "Thermal evolution of CRTS II slab track under various environmental temperatures: Experimental study", Constr. Build. Mater., 325, 126699. https://doi.org/10.1016/j.conbuildmat.2022.126699
  32. Zhou, R., Yuan, W., Liu, W., Zhu, X., Yao, G., Li, F. and Zhang, L. (2023a), "Thermal performance of CRTS II slab track-bridge structure under extreme temperatures: Numerical simulation", Constr. Build Mater., 377, 131147. https://doi.org/10.1016/j.conbuildmat.2023.131147
  33. Zhou, R., Yue, H., Du, Y., Yao, G., Liu, W. and Ren, W. (2023b), "Experimental and numerical study on interfacial thermal behavior of CRTS II slab track under continuous high temperatures", Eng. Struct., 284, 115964. https://doi.org/10.1016/j.engstruct.2023.115964
  34. Zumin, O. and Fujian, L. (2014), "Analysis and prediction of the temperature field based on in-situ measured temperature for CRTS-II ballastless track", Energy Procedia, 61, 1290-1293. https://doi.org/10.1016/j.egypro.2014.11.1083