Xiangyu Chang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiangyu Chang has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
Jianxiao Mao
2 shared publications- Yuguang Fu
Nanyang Technological Univ
2 shared publications - Bao Hong Quan1 shared publication
Chengjia Han
1 shared publicationHao Wang
1 shared publicationHongyun Fan
1 shared publication
Latest Publications
- Open Access
- 1 January 2025
- Published by Wiley in Journal of Engineering
- Vol. 2025 (1)
Prediction of Surrounding Rock Deformation in a Highway Tunnel Using an LSTM‐RF Hybrid Model
Accurate tunnel deformation prediction is critical for mitigating construction risks and ensuring tunnel stability. This study introduces a novel hybrid model integrating long short‐term memory (LSTM) networks and random forest (RF) to enhance the precision of tunnel deformation predictions during construction. Bayesian optimization was utilized to fine‐tune model parameters, ensuring optimal performance. Validated with multidepth data from the Yangjiashan highway tunnel in China, the hybrid model demonstrates remarkable adaptability to complex geological conditions. The results show that the LSTM‐RF model achieves a mean square error (MSE) of 0.0025, a root‐mean‐square error (RMSE) of 0.0052, and a coefficient of determination ( R 2 ) of 0.9810, outperforming individual models and other hybrid frameworks in predicting deformation trends. By effectively capturing temporal dependencies and modeling nonlinear residuals, the hybrid model provides a robust and reliable solution for improving safety and efficiency in tunneling projects. These findings emphasize the potential of hybrid approaches for geotechnical engineering, particularly in predictive maintenance and infrastructure monitoring.
- 1 January 2025
- Published by Wiley in Journal of Engineering
- Vol. 2025 (1)
Open AccessPrediction of Surrounding Rock Deformation in a Highway Tunnel Using an LSTM‐RF Hybrid Model
Accurate tunnel deformation prediction is critical for mitigating construction risks and ensuring tunnel stability. This study introduces a novel hybrid model integrating long short‐term memory (LSTM) networks and random forest (RF) to enhance the precision of tunnel deformation predictions during construction. Bayesian optimization was utilized to fine‐tune model parameters, ensuring optimal performance. Validated with multidepth data from the Yangjiashan highway tunnel in China, the hybrid model demonstrates remarkable adaptability to complex geological conditions. The results show that the LSTM‐RF model achieves a mean square error (MSE) of 0.0025, a root‐mean‐square error (RMSE) of 0.0052, and a coefficient of determination ( R 2 ) of 0.9810, outperforming individual models and other hybrid frameworks in predicting deformation trends. By effectively capturing temporal dependencies and modeling nonlinear residuals, the hybrid model provides a robust and reliable solution for improving safety and efficiency in tunneling projects. These findings emphasize the potential of hybrid approaches for geotechnical engineering, particularly in predictive maintenance and infrastructure monitoring.
- Top Cited Papers
- 27 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (7) , 6449-6471
Digital Twins in Transportation Infrastructure: An Investigation of the Key Enabling Technologies, Applications, and Challenges
Transportation infrastructure constitutes a significant part of civil infrastructure, such as bridges, tunnels, and roads, enormously promoting economic development. Transportation infrastructure is subjected to a high volume of traffic, damage, and component deterioration, as well as disaster events during the service period. Monitoring and management of the transportation infrastructure is always a critical task. Recently, digital twin (DT) is an emerging topic for transportation infrastructure management, with the advancement of artificial intelligence, Internet of Things, big data, and other smart technologies. Herein, DT aims to build a virtual counterpart of the physical infrastructure that is continually updated with its performance, maintenance, and health status. However, research in DT for transportation infrastructure mainly focused on infrastructure management (e.g., traffic state prediction and passenger flow assessment) and ignored the health status of the infrastructure itself. Challenges and associated opportunities exist in the adoption of DT for transportation infrastructure, such as balancing model fidelity and computation efficiency. Thus, it is necessary to investigate the key enabling technologies of DT in transportation infrastructure and provide a comprehensive reference for ongoing and future research. In this paper, a systematic investigation to identify the development of DTs for transportation infrastructure is presented. The paper starts by explaining the definition of DT and highlighting the various characteristics of DT. Next, the key enabling technologies and applications of DT for transportation infrastructure are discussed. Finally, based on the current development status of DT, challenges and open research are discussed along with their potential solutions.
- 27 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (7) , 6449-6471
Top Cited PapersDigital Twins in Transportation Infrastructure: An Investigation of the Key Enabling Technologies, Applications, and Challenges
Transportation infrastructure constitutes a significant part of civil infrastructure, such as bridges, tunnels, and roads, enormously promoting economic development. Transportation infrastructure is subjected to a high volume of traffic, damage, and component deterioration, as well as disaster events during the service period. Monitoring and management of the transportation infrastructure is always a critical task. Recently, digital twin (DT) is an emerging topic for transportation infrastructure management, with the advancement of artificial intelligence, Internet of Things, big data, and other smart technologies. Herein, DT aims to build a virtual counterpart of the physical infrastructure that is continually updated with its performance, maintenance, and health status. However, research in DT for transportation infrastructure mainly focused on infrastructure management (e.g., traffic state prediction and passenger flow assessment) and ignored the health status of the infrastructure itself. Challenges and associated opportunities exist in the adoption of DT for transportation infrastructure, such as balancing model fidelity and computation efficiency. Thus, it is necessary to investigate the key enabling technologies of DT in transportation infrastructure and provide a comprehensive reference for ongoing and future research. In this paper, a systematic investigation to identify the development of DTs for transportation infrastructure is presented. The paper starts by explaining the definition of DT and highlighting the various characteristics of DT. Next, the key enabling technologies and applications of DT for transportation infrastructure are discussed. Finally, based on the current development status of DT, challenges and open research are discussed along with their potential solutions.