Juewei Cai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Juewei Cai has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Changcheng Yang
Shanghai Research Institute of Building Sciences Co., Ltd., Shanghai 201108, China
1 shared publication - Chen Jin
Shanghai Urban Construction Design and Research Institute (Group) Co., Ltd., Shanghai 200125, China
1 shared publication - Fan Huang
Shanghai Research Institute of Building Sciences Co., Ltd., Shanghai 201108, China
1 shared publication - Hongbo Zhou
Shanghai Key Laboratory of Engineering Structure Safety, SRIBS, Shanghai 200032, China
1 shared publication - Hui Chen
School of Urban Rail Transportation, Shanghai University of Engineering Science, Shanghai 201620, China
1 shared publication - Mengyuan Zeng
College of Transportation, Tongii University, Shanghai, China
1 shared publication
Latest Publications
- Open Access
Diagnostic-Gap-Driven Class-Conditional Modality Regulation for Multimodal Building Defect Segmentation
RGB–IR multimodal inspection can combine visible surface information with thermal-response patterns for building-defect assessment, but joint learning may develop class-specific information unevenly across modality branches. This study proposes adaptive class-conditional modality regulation for RGB–IR façade-defect semantic segmentation. Matched unimodal models establish an empirical diagnostic reference for each modality–defect pair. During multimodal training, periodic diagnostic branch scores are compared with these references, and the resulting diagnostic gaps redistribute auxiliary supervision while leaving the fused inference pathway unchanged. On the held-out test subset of the Building Façade Defect Detection dataset, plain dual-branch fusion provided only a modest improvement over RGB alone, while calibration-set diagnostics showed larger gaps in the IR branch. Across five matched test runs, the proposed method increased mIoU from to and Boundary F1 from to , exceeding early fusion and the selected global balancing methods OGM-GE and AGM. Ablation results associate the largest component-wise difference with class-specific allocation. The method adds training-time computation but does not change the deployed network or its forward computation.Open AccessDiagnostic-Gap-Driven Class-Conditional Modality Regulation for Multimodal Building Defect Segmentation
RGB–IR multimodal inspection can combine visible surface information with thermal-response patterns for building-defect assessment, but joint learning may develop class-specific information unevenly across modality branches. This study proposes adaptive class-conditional modality regulation for RGB–IR façade-defect semantic segmentation. Matched unimodal models establish an empirical diagnostic reference for each modality–defect pair. During multimodal training, periodic diagnostic branch scores are compared with these references, and the resulting diagnostic gaps redistribute auxiliary supervision while leaving the fused inference pathway unchanged. On the held-out test subset of the Building Façade Defect Detection dataset, plain dual-branch fusion provided only a modest improvement over RGB alone, while calibration-set diagnostics showed larger gaps in the IR branch. Across five matched test runs, the proposed method increased mIoU from to and Boundary F1 from to , exceeding early fusion and the selected global balancing methods OGM-GE and AGM. Ablation results associate the largest component-wise difference with class-specific allocation. The method adds training-time computation but does not change the deployed network or its forward computation. - Open Access
Experimental and Numerical Investigation of Tension-Induced Stress in Cross-Tensioned Concrete Pavement
This study investigates tension-induced stress in Cross-tensioned Concrete Pavement (CTCP) during sequential tensioning. An integrated approach combining full-scale field testing and finite element analysis was employed. A field test was conducted to capture the stress distribution throughout the complete tensioning process, and a finite element model was subsequently developed and validated against measured strains. The results indicate that the maximum tensile stress (approximately 1.35 MPa) consistently occurs at the corner of the nearest anchorage zone, which can be completely offset by the compressive stress generated from subsequent tensioning operations. The concept of “prestress effect zone” is proposed to characterize the influence region of each tensioning sequence. In CTCP, the extent of this zone is expected to be influenced by the characteristics of the applied prestress force, including tendon angle, spacing, and magnitude. Based on the distinct tension-induced stress distribution characteristics along the slab, three zones are identified: tensile increase region, tensile stability region, and tensile decrease region, enabling clearer investigation of tension-induced stress. The observed superposition of tensile stresses during sequential tensioning operations highlights the importance of analyzing the development of tension-induced stress throughout the tensioning process, providing essential guidance for anchorage zone design and construction procedures.
Open AccessExperimental and Numerical Investigation of Tension-Induced Stress in Cross-Tensioned Concrete Pavement
This study investigates tension-induced stress in Cross-tensioned Concrete Pavement (CTCP) during sequential tensioning. An integrated approach combining full-scale field testing and finite element analysis was employed. A field test was conducted to capture the stress distribution throughout the complete tensioning process, and a finite element model was subsequently developed and validated against measured strains. The results indicate that the maximum tensile stress (approximately 1.35 MPa) consistently occurs at the corner of the nearest anchorage zone, which can be completely offset by the compressive stress generated from subsequent tensioning operations. The concept of “prestress effect zone” is proposed to characterize the influence region of each tensioning sequence. In CTCP, the extent of this zone is expected to be influenced by the characteristics of the applied prestress force, including tendon angle, spacing, and magnitude. Based on the distinct tension-induced stress distribution characteristics along the slab, three zones are identified: tensile increase region, tensile stability region, and tensile decrease region, enabling clearer investigation of tension-induced stress. The observed superposition of tensile stresses during sequential tensioning operations highlights the importance of analyzing the development of tension-induced stress throughout the tensioning process, providing essential guidance for anchorage zone design and construction procedures.