Query：
学者姓名：钟学琦
Refining：
Year
Type
Indexed by
Source
Complex
Co-Author
Language
Clean All
Abstract ：
Self-centering rocking bridge piers possess significant potential for improving post-earthquake resilience and reducing the post-earthquake repairs for bridges. However, due to the multi-parameter nature of such piers, challenges remain in designing the self-centering bridge piers and ensuring balanced performance across multiple piers. To addresses these gaps, this study proposes a general multi-objective seismic design optimization framework for self-centering rocking bridges. The framework includes input-output dataset preparation, XGBoost model training, Pareto front calculation, and optimal solution selection. The framework is illustrated on a selfcentering bridge equipped with hemisphere-based rocking hinges (HRH), an innovative device previously developed by the authors. Results show that using a machine learning method (XGBoost herein) to develop surrogate model as a substitution for the finite element model improves optimization efficiency by at least 73 %, without compromising accuracy. The optimized bridge with HRHs achieves balanced performance among piers, with a 63.4 % decrease in shear difference and a 11.4 % reduction in displacement difference compared to the benchmark bridge.
Keyword ：
Mechanical hinge Mechanical hinge Multi-criteria decision-making Multi-criteria decision-making Multi-objective optimization Multi-objective optimization Self-centering bridge Self-centering bridge XGBoost machine learning model XGBoost machine learning model
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhong, Xueqi , Gao, Haoyuan , Li, Jianzhong et al. Multi-objective seismic design optimization of self-centering bridges with novel mechanical hinges [J]. | ENGINEERING STRUCTURES , 2025 , 343 . |
| MLA | Zhong, Xueqi et al. "Multi-objective seismic design optimization of self-centering bridges with novel mechanical hinges" . | ENGINEERING STRUCTURES 343 (2025) . |
| APA | Zhong, Xueqi , Gao, Haoyuan , Li, Jianzhong , Chen, Xu . Multi-objective seismic design optimization of self-centering bridges with novel mechanical hinges . | ENGINEERING STRUCTURES , 2025 , 343 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
This paper presents the experimental investigation for a self-centering bridge column equipped with the hemisphere-based rocking hinge (HRH), an innovative device previously developed by the authors. The HRH is designed to minimize the local damage at the rocking interface and to facilitate the assembling between the precast column and footing. This study conducts cyclic quasi-static tests with five test scenarios on two 1:2.5scale specimens to investigate the effects of initial PT force and damper types on the hysteretic performance of the HRH column. Experimental results show that the HRH columns exhibit excellent low-damage characteristics, with minimal damage in the reinforced concrete column body and the rocking interface even at an 8.75 % lateral drift. These columns also demonstrate satisfactory self-centering, energy-dissipation, and lateral load-resistant capacities. Furthermore, the force-displacement analytical model of the HRH column is verified as able to effectively characterize the hysteretic behavior of HRH columns, offering a useful tool for the preliminary design of this type of novel column.
Keyword ：
Analytical model Analytical model Bridge column Bridge column Quasi-static test Quasi-static test Rocking hinge Rocking hinge Self-centering Self-centering
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhong, Xueqi , Chen, Xu , Shen, Yu et al. Low-damage self-centering rocking bridge columns using hemisphere-based rocking hinges: Quasi-static experimental investigation [J]. | ENGINEERING STRUCTURES , 2025 , 335 . |
| MLA | Zhong, Xueqi et al. "Low-damage self-centering rocking bridge columns using hemisphere-based rocking hinges: Quasi-static experimental investigation" . | ENGINEERING STRUCTURES 335 (2025) . |
| APA | Zhong, Xueqi , Chen, Xu , Shen, Yu , Li, Jianzhong , Bao, Zehua . Low-damage self-centering rocking bridge columns using hemisphere-based rocking hinges: Quasi-static experimental investigation . | ENGINEERING STRUCTURES , 2025 , 335 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Concrete-filled steel tube (CFST) columns are widely utilized in modern structural systems due to their excellent load-bearing capacity, ductility, and energy dissipation characteristics. However, accurately predicting their failure modes under axial compression remains a critical challenge, particularly due to the inherent class imbalance in experimental datasets. To address this issue, this study develops an efficient and interpretable machine learning (ML)-based classification framework for predicting the failure modes of rectangular CFST columns under axial compression. A comprehensive database comprising 597 experimental samples is first established by systematically compiling data from publicly available literature. To mitigate the adverse effects of data imbalance on classification accuracy, a hybrid data augmentation strategy (SMOTE-Tomek) is implemented during preprocessing. Six ML models are then systematically evaluated using multiple performance metrics to identify the optimal predictive model. The best-performing model is further analyzed using the SHapley Additive exPlanation (SHAP) approach to quantify the individual contributions of input features. Results demonstrate that the SMOTE-Tomek technique significantly enhances the prediction capability for minority classes, thereby improving the overall robustness of the classification framework. Among the evaluated models, the CatBoost algorithm outperforms others in accurately predicting the failure modes of CFST columns under axial compression. Furthermore, SHAP analysis identifies the height-to-width ratio (L/B) and the yield strength of steel tube (fy) as the two most influential features governing the failure mode classification of rectangular CFST columns.
Keyword ：
Axial compression Axial compression Class imbalance Class imbalance Concrete-filled steel tube column Concrete-filled steel tube column Failure mode prediction Failure mode prediction Machine learning Machine learning Shapley additive explanation Shapley additive explanation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhong, Xueqi , Yu, Qiyao , Liao, Feiyu . Hybrid resampling-enhanced machine learning for failure mode prediction of axially compressed rectangular CFST columns with imbalanced data [J]. | STRUCTURES , 2025 , 80 . |
| MLA | Zhong, Xueqi et al. "Hybrid resampling-enhanced machine learning for failure mode prediction of axially compressed rectangular CFST columns with imbalanced data" . | STRUCTURES 80 (2025) . |
| APA | Zhong, Xueqi , Yu, Qiyao , Liao, Feiyu . Hybrid resampling-enhanced machine learning for failure mode prediction of axially compressed rectangular CFST columns with imbalanced data . | STRUCTURES , 2025 , 80 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
This study develops an advanced probabilistic machine learning (ML) framework to predict failure modes and axial load-bearing capacity of rectangular concrete-filled steel tube (CFST) columns, addressing critical challenges of class imbalance and prediction uncertainty. Leveraging a comprehensive dataset of 597 experimental samples, a rigorous feature selection procedure is conducted to optimize the ML applications. Three ML models are developed and evaluated: a deterministic approach (Random Forest) and two probabilistic models (Gaussian Process and Natural Gradient Boosting, NGBoost). To address the issue of class imbalance in failure mode classification, a hybrid resampling strategy combining the Synthetic Minority Over-sampling Technique and Tomek Links method (SMOTE-Tomek) is implemented. Furthermore, A novel classification-regression cascaded framework is proposed, where failure modes are first classified, followed by category-specific regression for capacity prediction. Results demonstrate that SMOTE-Tomek significantly improves minority failure mode classification, increasing the average F1-scores by 8.1 % (for flexural failure) and 118.2 % (for combined failure). The cascaded framework outperforms direct regression in estimating capacity, achieving a 56 % higher coefficient of determination (R2) and 15-30 % lower error metrics on average. NGBoost excels in both probabilistic failure mode prediction and uncertainty-aware capacity estimation, enabling reliability-based design and riskinformed decision-making for CFST structures in engineering practice.
Keyword ：
Axial compression Axial compression Classification-regression Classification-regression Concrete-filled steel tube column Concrete-filled steel tube column Failure mode Failure mode Load-bearing capacity Load-bearing capacity Machine learning Machine learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhong, Xueqi , Lai, Dade , Yu, Qiyao et al. Probabilistic machine learning with a cascaded framework for robust failure mode classification and capacity estimation of rectangular concrete-filled steel tube columns under axial compression [J]. | ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE , 2025 , 162 . |
| MLA | Zhong, Xueqi et al. "Probabilistic machine learning with a cascaded framework for robust failure mode classification and capacity estimation of rectangular concrete-filled steel tube columns under axial compression" . | ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 162 (2025) . |
| APA | Zhong, Xueqi , Lai, Dade , Yu, Qiyao , Liao, Feiyu . Probabilistic machine learning with a cascaded framework for robust failure mode classification and capacity estimation of rectangular concrete-filled steel tube columns under axial compression . | ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE , 2025 , 162 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
This study examines the cyclic performance of circular concrete-filled steel tube (CFST) composite joints with circumferential gap imperfections, emphasizing the effects of varying gap ratios (0 % to 2.2 %), increased steel beam height (100 and 150 mm), and different steel tube thicknesses (3 and 4 mm). A combined experimental and numerical investigation was conducted on seven large-scale joint specimens to evaluate hysteretic response, energy dissipation capacity, failure mechanisms, stress distribution patterns, and interfacial behavior between steel tube and core concrete. The results demonstrate that the presence of circumferential gaps significantly compromises joint performance, reducing peak load capacity by up to 20 %, initial stiffness by approximately 10 %, and energy dissipation by over 10 %, while accelerating rigidity degradation. Circumferential gaps disrupt the stress transfer path from the steel tube to the core concrete, leading to severe stress concentration at the joint core and premature shear failure. Conversely, increasing the steel beam height enhances load-bearing capacity, improves energy dissipation, and delays stiffness degradation, particularly in defective joints. The increase in steel tube thickness offers moderate gains in shear resistance but limited improvements in global cyclic performance. A predictive model was developed to quantify the influence of circumferential gaps, showing good agreement with experimental tests. These findings underscore the critical role of steel-concrete interfacial integrity in CFST joint behavior and highlight effective structural strategies to mitigate the adverse effects of circumferential imperfections.
Keyword ：
CFST composite joints CFST composite joints Circumferential gaps Circumferential gaps Cyclic load Cyclic load Experimental tests Experimental tests Finite element analysis Finite element analysis
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liao, Feiyu , Cui, Yucheng , Zhong, Xueqi et al. Cyclic performance of CFST composite joints with circumferential gap imperfections [J]. | STRUCTURES , 2025 , 82 . |
| MLA | Liao, Feiyu et al. "Cyclic performance of CFST composite joints with circumferential gap imperfections" . | STRUCTURES 82 (2025) . |
| APA | Liao, Feiyu , Cui, Yucheng , Zhong, Xueqi , Lai, Dade , Yang, Dacheng . Cyclic performance of CFST composite joints with circumferential gap imperfections . | STRUCTURES , 2025 , 82 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
