Jinyang Cao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Jinyang Cao has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Huifu Jiang
Research Institute of Highway, Ministry of Transport, Beijing 100088, China
1 shared publication Jianping Li
Transportation Engineering Quality Supervision Bureau of Shaanxi Province, Xi’an, Shaanxi, 710075
1 shared publication- Linsen Du
Research Institute of Highway Ministry of Transport
1 shared publication - Mingyang Wang
Beijing Jingdong Century Trading Co., Ltd., Beijing 100176, China
1 shared publication Wanliang Tian
No. 1 Engineering Co., Ltd. of FHEC of CCCC., Changping District, Beijing, 102205
1 shared publication- Wei Zhou
Automobile Transportation Research Center, Research Institute of Highway Ministry of Transport, Beijing 100088, China
1 shared publication
Latest Publications
- Open Access
- 1 July 2026
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 3274 (1)
Fatigue performance analysis of weathering steel structure in Dabashan tunnel
This paper measures the fatigue of the structures of weathering steel in the tunnel of the Daba Mountains. The study centers on the issues of the initial crack size, and effect of stress ratio on the fatigue life. The ABAQUS-FRANC3D coupled computational framework is used. The crack tip stress intensity factor is sensitive to the stress applied and very insensitive to the initial size of the crack. Findings have shown that the stress ratio has a considerable effect on fatigue life. As the stress ratio rises by 0.1 to 0.7, the fatigue life increases by 1287.38 per cent. On the other hand, the effect of initial crack size is comparatively low. The fatigue life decreased by only 13.89% as the initial crack size increased from 0.075 mm to 0.5 mm. The crack tip stress intensity factor was sensitive to stress ratio; however, the initial crack size is comparatively insensitive. The stress intensity factor increases gradually as there is a rise in the length of the crack, which increases the driving force for crack propagation. The obtained results are useful insights into optimising the fatigue life of such structures made of weathering steel and enhancing the safety assessment methods for tunnel engineering.
- 1 July 2026
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 3274 (1)
Open AccessFatigue performance analysis of weathering steel structure in Dabashan tunnel
This paper measures the fatigue of the structures of weathering steel in the tunnel of the Daba Mountains. The study centers on the issues of the initial crack size, and effect of stress ratio on the fatigue life. The ABAQUS-FRANC3D coupled computational framework is used. The crack tip stress intensity factor is sensitive to the stress applied and very insensitive to the initial size of the crack. Findings have shown that the stress ratio has a considerable effect on fatigue life. As the stress ratio rises by 0.1 to 0.7, the fatigue life increases by 1287.38 per cent. On the other hand, the effect of initial crack size is comparatively low. The fatigue life decreased by only 13.89% as the initial crack size increased from 0.075 mm to 0.5 mm. The crack tip stress intensity factor was sensitive to stress ratio; however, the initial crack size is comparatively insensitive. The stress intensity factor increases gradually as there is a rise in the length of the crack, which increases the driving force for crack propagation. The obtained results are useful insights into optimising the fatigue life of such structures made of weathering steel and enhancing the safety assessment methods for tunnel engineering.
- Open Access
- 1 June 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (11) , 5501
GAT-Informer: A Spatiotemporal Graph Neural Network Model for Urban Passenger Flow Forecasting
Accurate bus passenger flow prediction is a critical prerequisite for optimizing resource allocation in intelligent bus systems and improving public transport service quality. However, due to dynamic fluctuations in passenger travel demand and the complex topological structure of bus networks, effectively capturing the inherent spatiotemporal dependencies of passenger flow remains a significant challenge. To address this issue, this paper proposes GAT-Informer, a hybrid deep learning model for short-term bus passenger flow prediction. Unlike conventional methods that mainly rely on fixed physical adjacency or single-view spatial correlations, the proposed model incorporates domain knowledge into graph construction through a four-dimensional associated-node mechanism. Specifically, four types of features, namely line connectivity, spatial proximity, OD correlation, and station functional similarity, are used to identify relevant associated nodes and construct a passenger flow interaction spatiotemporal graph that better reflects inter-station dependencies. Based on this graph, a Graph Attention Network (GAT) is introduced to adaptively learn spatial interaction features and differentiated influence weights among associated stations. The spatially enhanced features extracted by GAT are then fed into the Informer network, where probabilistic sparse self-attention and hierarchical timestamp encoding are employed to efficiently capture long-term temporal dependencies and periodic fluctuation patterns of passenger flow. Experimental results based on bus passenger flow data from Foshan City show that the proposed GAT-Informer model significantly outperforms benchmark models, including LSTM-Transformer, CNN-GRU, and STGCN, across different prediction horizons, validating its effectiveness and improved predictive performance in bus passenger flow prediction.
- 1 June 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (11) , 5501
Open AccessGAT-Informer: A Spatiotemporal Graph Neural Network Model for Urban Passenger Flow Forecasting
Accurate bus passenger flow prediction is a critical prerequisite for optimizing resource allocation in intelligent bus systems and improving public transport service quality. However, due to dynamic fluctuations in passenger travel demand and the complex topological structure of bus networks, effectively capturing the inherent spatiotemporal dependencies of passenger flow remains a significant challenge. To address this issue, this paper proposes GAT-Informer, a hybrid deep learning model for short-term bus passenger flow prediction. Unlike conventional methods that mainly rely on fixed physical adjacency or single-view spatial correlations, the proposed model incorporates domain knowledge into graph construction through a four-dimensional associated-node mechanism. Specifically, four types of features, namely line connectivity, spatial proximity, OD correlation, and station functional similarity, are used to identify relevant associated nodes and construct a passenger flow interaction spatiotemporal graph that better reflects inter-station dependencies. Based on this graph, a Graph Attention Network (GAT) is introduced to adaptively learn spatial interaction features and differentiated influence weights among associated stations. The spatially enhanced features extracted by GAT are then fed into the Informer network, where probabilistic sparse self-attention and hierarchical timestamp encoding are employed to efficiently capture long-term temporal dependencies and periodic fluctuation patterns of passenger flow. Experimental results based on bus passenger flow data from Foshan City show that the proposed GAT-Informer model significantly outperforms benchmark models, including LSTM-Transformer, CNN-GRU, and STGCN, across different prediction horizons, validating its effectiveness and improved predictive performance in bus passenger flow prediction.