Junhao Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Junhao Xu has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Yingying Zhang
China University of Mining and Technology
4 shared publications - Yushuai Zhao
School of Information and Security, Yancheng Polytechnic College, Yancheng 224005, P. R. China
3 shared publications - Penghao Yu
China University of Mining and Technology
2 shared publications Baorui Sun
School of Mechanics and Civil Engineering, China University of Mining and Technology, Xuzhou, China
1 shared publicationLanlan Zhang
1 shared publication- Lanlan Zhang
State Key Laboratory of Respiratory Health and Multimorbidity, Department of Respiratory and Critical Care Medicine, West China Hospital, Sichuan University, Chengdu, China
1 shared publication
Latest Publications
- Open Access
- 17 October 2026
- Published by Elsevier in SSRN Electronic Journal
TunnelLuxNet: A unified and fast conditional CNN-Transformer framework for 3D illuminance field prediction in road tunnels
Comprehensive tunnel lighting assessment requires three-dimensional illuminance distributions across the roadway and surrounding surfaces. Physically based simulation resolves these distributions but becomes costly during repeated evaluations, while data-driven models commonly focus on individual planes. Here we present TunnelLuxNet, a conditional CNN–Transformer framework for rapid prediction of tunnel interior illuminance fields. A geometry-aware encoding maps connected surfaces to a common layout represented by multichannel spatial fields and a condition vector. Within this representation, convolutional processing captures local features, axial attention establishes longitudinal and cross-surface interactions, and conditional modulation incorporates geometric, material and luminaire conditions. Trained on 3,000 Radiance-generated configurations, TunnelLuxNet achieves mean MAE and RMSE of 0.097 and 0.404 lx for local fields and 1.290 and 2.286 lx under the densest tested installation, with close agreement against published measurements. Predicting approximately 1.8 million surface illuminance values for a long tunnel takes 22 s, compared with an estimated 6 h using Radiance. Extrapolation tests reveal greater sensitivity to cross-sectional geometry and luminaire aiming than to reflectance or alignment. Separately trained models for batwing and narrow-beam photometries demonstrate the workflow’s applicability to different luminaires. Ablation results highlight cross-surface information exchange as a key contribution to accuracy, suggesting its value for learning coupled physical fields in three-dimensional environments. TunnelLuxNet provides a reusable computational basis for comprehensive lighting assessment and extensive evaluation of design alternatives.
- 17 October 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessTunnelLuxNet: A unified and fast conditional CNN-Transformer framework for 3D illuminance field prediction in road tunnels
Comprehensive tunnel lighting assessment requires three-dimensional illuminance distributions across the roadway and surrounding surfaces. Physically based simulation resolves these distributions but becomes costly during repeated evaluations, while data-driven models commonly focus on individual planes. Here we present TunnelLuxNet, a conditional CNN–Transformer framework for rapid prediction of tunnel interior illuminance fields. A geometry-aware encoding maps connected surfaces to a common layout represented by multichannel spatial fields and a condition vector. Within this representation, convolutional processing captures local features, axial attention establishes longitudinal and cross-surface interactions, and conditional modulation incorporates geometric, material and luminaire conditions. Trained on 3,000 Radiance-generated configurations, TunnelLuxNet achieves mean MAE and RMSE of 0.097 and 0.404 lx for local fields and 1.290 and 2.286 lx under the densest tested installation, with close agreement against published measurements. Predicting approximately 1.8 million surface illuminance values for a long tunnel takes 22 s, compared with an estimated 6 h using Radiance. Extrapolation tests reveal greater sensitivity to cross-sectional geometry and luminaire aiming than to reflectance or alignment. Separately trained models for batwing and narrow-beam photometries demonstrate the workflow’s applicability to different luminaires. Ablation results highlight cross-surface information exchange as a key contribution to accuracy, suggesting its value for learning coupled physical fields in three-dimensional environments. TunnelLuxNet provides a reusable computational basis for comprehensive lighting assessment and extensive evaluation of design alternatives.
- Open Access
- 6 December 2023
- Published by Elsevier in KSCE Journal of Civil Engineering
- Vol. 28 (2) , 787-799
Shaking Table Test on Composite Isolation System of High-speed Railway Station with Integrated Station-Bridge Structure
- 6 December 2023
- Published by Elsevier in KSCE Journal of Civil Engineering
- Vol. 28 (2) , 787-799
Open AccessShaking Table Test on Composite Isolation System of High-speed Railway Station with Integrated Station-Bridge Structure
- 1 February 2022
- Published by Elsevier in Thin-Walled Structures
- Vol. 171
Experiment and simulation analysis on dynamic response of plane cable-membrane structure under impact load
- 1 February 2022
- Published by Elsevier in Thin-Walled Structures
- Vol. 171
Experiment and simulation analysis on dynamic response of plane cable-membrane structure under impact load
- 1 January 2022
- Published by Elsevier in Thin-Walled Structures
- Vol. 170
Analysis and design of fabric membrane structures: A systematic review on material and structural performance
- 1 January 2022
- Published by Elsevier in Thin-Walled Structures
- Vol. 170
Analysis and design of fabric membrane structures: A systematic review on material and structural performance
- 1 September 2021
- Published by Wiley in Polymer Composites
- Vol. 42 (11) , 6080-6093
Bond behavior of BFRP bars in concrete under lateral pressure
Basalt fiber reinforced polymer (BFRP) bars have been widely studied because of its advantages in corrosive environment. At present, the researches on the bond properties of basalt FRP bars mainly focus on the types of bars, bond length and environmental effects. In this paper, the bond properties of 12 mm diameter glass fiber reinforced bars with unilateral and bilateral compressive stresses of 0, 0.15, 0.3, 0.45, 0.6 and 0.75 were studied for revealing the effects of lateral stress. In addition, based on the analysis of the influence of compressive stress on the failure mode, a theoretical analysis model is established. Based on the fitting of ultimate bond strength and slip amount, the bond slip constitutive model of basalt fiber embedded in concrete is proposed, which can work under different compressive stress.
- 1 September 2021
- Published by Wiley in Polymer Composites
- Vol. 42 (11) , 6080-6093
Bond behavior of BFRP bars in concrete under lateral pressure
Basalt fiber reinforced polymer (BFRP) bars have been widely studied because of its advantages in corrosive environment. At present, the researches on the bond properties of basalt FRP bars mainly focus on the types of bars, bond length and environmental effects. In this paper, the bond properties of 12 mm diameter glass fiber reinforced bars with unilateral and bilateral compressive stresses of 0, 0.15, 0.3, 0.45, 0.6 and 0.75 were studied for revealing the effects of lateral stress. In addition, based on the analysis of the influence of compressive stress on the failure mode, a theoretical analysis model is established. Based on the fitting of ultimate bond strength and slip amount, the bond slip constitutive model of basalt fiber embedded in concrete is proposed, which can work under different compressive stress.