Xin Wang is a Research Professor and doctoral supervisor in the Department of Transportation Infrastructure Engineering at Tongji University. He has been awarded the Shanghai Overseas High-Level Talent Award (Youth). He obtained his Ph.D. in Civil and Environmental Engineering from Rutgers University (USA) in October 2024 and joined Tongji University in January 2025.
His research focuses on risk prediction and intelligent maintenance of rail transit infrastructure. By integrating artificial intelligence with civil engineering, his work centers on structural health monitoring, early-warning systems, and intelligent decision-making for railway and urban transit infrastructure. His goal is to enable infrastructure systems to “see risks, predict trends, and achieve optimal maintenance,” thereby promoting safer, more reliable, and more intelligent rail engineering.
He currently leads two funded research projects and has published 14 papers (11 SCI-indexed papers) as first or corresponding author in high-impact international and domestic journals, including Advanced Engineering Informatics, Applied Energy, Engineering Applications of Artificial Intelligence, and Journal of the China Railway Society.
Educational background
2019.6–2024.10 Rutgers University, USA | Ph.D. in Civil and Environmental Engineering
2016.9–2019.6 Southwest Jiaotong University | M.S. in Road and Railway Engineering
2012.9–2016.6 Southwest Jiaotong University | B.S. in Civil Engineering
Work experience
2025.1–2025.9 Research Assistant Professor, Tongji University
2025.9–Present Research Professor, Tongji University
Research interests
Risk prediction and intelligent maintenance of rail transit infrastructure
Data-driven modeling of railway infrastructure deterioration
Machine learning applications in railway engineering
Honors & Awards
2025 Shanghai Overseas High-Level Talent (Youth)
Publications
Journal Paper(Author order follows original; corresponding author marked by *)
23. Gao, T., Wang, Y.,Wang, X*(2026). Multi-objective optimization of rail welded joint grinding in railroad tracks via reinforcement learning. Engineering Applications of Artificial Intelligence, 164, 113386.
22. Zhou, J., Xue, M.,Wang, X.*, Zhai, G., Tian, C., & Wu, M. (2025). Online estimation and validation of wheel–rail braking adhesion based on negative gradient iteration. Vehicle System Dynamics, 1–25.
21.Wang, X.& Bai, Y. (2025). A multisource data fusion approach for predicting the deterioration of sign structures along highways. Journal of Infrastructure Systems
20.Wang, X., Dai, J., & Liu, X. (2025). A spatial-temporal neural network based on ResNet-Transformer for predicting railroad broken rails. Advanced Engineering Informatics, 65, 103126.
19. Wang J., Xu Y., &Wang X.*(2025) Research progress on interface damage of ballastless track structures in high-speed railways. Construction and Building Materials, 489,142258
18.Wang, X.& Bai, Y. (2025). Multisource data-driven approach for predicting the deterioration of high mast light poles along highways. Journal of Infrastructure Systems, 31(1), 04024036.
17.Wang, X., Liu, X., & Bai, Y. (2024). Prediction of the temperature of diesel engine oil in railroad locomotives using compressed information-based data fusion method with attention-enhanced CNN-LSTM. Applied Energy 367, 123357.
16. Yang C.,Wang, X. *, & Nassif, H. (2024). Impact of environmental conditions on predicting condition rating of concrete bridge decks. Transportation Research Record, 0(0).
15. Kang, D., Dai, J., Liu, X., Bian, Z., Zaman, A. &Wang, X.(2024). Estimating the occurrence of broken rails in commuter railroads with machine learning algorithms. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 09544097241280848.
14.Wang, X., Bai, Y., & Liu, X. (2023). Prediction of foot-by-foot railroad track geometry using a hybrid CNN-LSTM model. Advanced Engineering Informatics 58, 102235.
13.Wang, X., Liu, X., & Euston, T. L. (2023). Relationship between track geometry defect occurrence and substructure condition: A case study on one passenger railroad in the United States. Construction and Building Materials, 365, 130066.
12.Wang, X., Liu, X., & Bian, Z. (2022). A machine learning based methodology for broken rail prediction on freight railroads: A case study in the United States. Construction and Building Materials, 346, 128353.
11. Xu, G., Gutierrez, M., Arora, K., &Wang, X.(2022). Viscoplastic response of deep tunnels based on a fractional damage creep constitutive model. Acta Geotechnica. 17, 613–633
10. Xu, G., He, C. &Wang, X.(2020). Mechanical behavior of transversely isotropic rocks under uniaxial compression governed by micro-structure and micro-parameters. Bulletin of Engineering Geology and the Environment, 79, 1979–2004
9. Wang, Y., Wang, P.,Wang, X., & Liu, X. (2018). Position synchronization for track geometry inspection data via big-data fusion and incremental learning. Transportation Research Part C, 93: 544-565.
8.汪鑫,王平,陈嵘,高原&刘潇潇.(2020).基于多次波形匹配的高速铁路动检数据里程误差评估与修正.铁道学报(02),110-116.
7.王平,汪鑫,王源&张荣鹤.(2020).基于高铁轨道不平顺的车轮不圆顺识别模型.西南交通大学学报(04),681-687+678.
6.王平,高天赐,汪鑫,杨翠平&王源.(2020).基于拟合平纵断面的铁路特大桥梁线路平顺性评估.西南交通大学学报(02),231-237+272.
5.陈嵘,方嘉晟,汪鑫,徐井芒&崔大宾.(2019).车轮型面演变对高速道岔区轮轨接触行为影响分析.铁道学报(05),101-108.
4.汪鑫,高天赐,方嘉晟&王平.(2018).基于时间历程的高速铁路轨道不平顺异常值处理算法.铁道科学与工程学报(12),3029-3036.
3.汪鑫,王源,王平&王沂峰.(2018).高速铁路动检车检测数据里程误差评估与修正.铁道标准设计(07),46-51.
2.徐金辉,汪鑫,黄大维&王彪.(2018).CRTSⅡ型板式轨道参数对车辆频率响应的影响.铁道工程学报(01),62-69+94.
1.张荣鹤,王平,汪鑫&徐井芒.(2018).轨道不平顺作用下动车组安全运行速度限值研究.铁道标准设计(10),62-67+78.
Conference Presentations
4.Wang, X., Bai, Y.. A Data-Driven Approach for Predicting the Deterioration of Highway Ancillary Structures: Case Study on High Mast Light Pole. Transportation Research Board, 103rd Annual Meeting, Washington, DC. January 2024
3.Wang, X., Yang, C.. Impact of Environmental Conditions on Predicting Condition Rating of Concrete Bridge Decks. Transportation Research Board, 103rd Annual Meeting, Washington, DC. January 2024
2.Wang, X., & Zaman, A.. Machine Learning Based Broken Rail Prediction on Freight Railroads: Methodology and A Case Study in the United States. AREMA 2022 Annual Conference & Expo. Denver, August 2022.
1.Wang, X., Zaman, A., & Liu, X.. Artificial Intelligence Aided Broken Rail Prediction. FRA Track & Railroad Workplace Safety Symposium, St. Louis, April 2022.