An ultrasonic-AI hybrid approach for predicting void defects in concrete-filled steel tubes via enhanced XGBoost with Bayesian optimization
This study proposes an Ultrasonic-AI Hybrid Approach for predicting void defects in concrete-filled steel tubes (CFST). Based on 3600 ultrasonic measurement samples, an Extreme Gradient Boosting (XGBoost) model was enhanced through oversampling and hyperparameter optimization via Bayesian optimizati...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-07-01
|
| Series: | Case Studies in Construction Materials |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214509525001573 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825199448733515776 |
|---|---|
| author | Shuai Wan Shipan Li Zheng Chen Yunchao Tang |
| author_facet | Shuai Wan Shipan Li Zheng Chen Yunchao Tang |
| author_sort | Shuai Wan |
| collection | DOAJ |
| description | This study proposes an Ultrasonic-AI Hybrid Approach for predicting void defects in concrete-filled steel tubes (CFST). Based on 3600 ultrasonic measurement samples, an Extreme Gradient Boosting (XGBoost) model was enhanced through oversampling and hyperparameter optimization via Bayesian optimization (BO-XGBoost). The BO-XGBoost model demonstrated superior performance compared to baseline models (Random Forest, AdaBoost, and Gradient Boosting Decision Tree), achieving an overall prediction accuracy of 0.92, precision and recall of 0.90, and an AUC of 0.98. SHAP (SHapley Additive exPlanations) analysis revealed that sound velocity, sound time, acoustic amplitude, concrete strength, and fly ash content were the most influential features for model predictions. This hybrid approach offers high efficiency and accuracy for void defect detection in CFST, providing a novel solution that leverages the strengths of both traditional ultrasonic methods and artificial intelligence algorithms. The method not only detects the presence of void defects but also quantifies their extent, advancing CFST inspection from qualitative analysis to quantitative assessment. |
| format | Article |
| id | doaj-art-c6efce6ddbfb4b54bc12d35f14a818ca |
| institution | Kabale University |
| issn | 2214-5095 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Case Studies in Construction Materials |
| spelling | doaj-art-c6efce6ddbfb4b54bc12d35f14a818ca2025-02-08T05:00:29ZengElsevierCase Studies in Construction Materials2214-50952025-07-0122e04359An ultrasonic-AI hybrid approach for predicting void defects in concrete-filled steel tubes via enhanced XGBoost with Bayesian optimizationShuai Wan0Shipan Li1Zheng Chen2Yunchao Tang3Guangdong Provincial Key Laboratory of Intelligent Disaster Prevention and Emergency Technologies for Urban Lifeline Engineering, Dongguan University of Technology, Dongguan, ChinaGuangdong Provincial Key Laboratory of Intelligent Disaster Prevention and Emergency Technologies for Urban Lifeline Engineering, Dongguan University of Technology, Dongguan, ChinaSchool of Civil Engineering and Architecture, State Key Laboratory of Featured Metal Materials and Life-cycle Safety for Composite Structures, Guangxi University, Nanning, ChinaGuangdong Provincial Key Laboratory of Intelligent Disaster Prevention and Emergency Technologies for Urban Lifeline Engineering, Dongguan University of Technology, Dongguan, China; School of Civil Engineering and Architecture, State Key Laboratory of Featured Metal Materials and Life-cycle Safety for Composite Structures, Guangxi University, Nanning, China; Corresponding author at: Guangdong Provincial Key Laboratory of Intelligent Disaster Prevention and Emergency Technologies for Urban Lifeline Engineering, Dongguan University of Technology, Dongguan, China.This study proposes an Ultrasonic-AI Hybrid Approach for predicting void defects in concrete-filled steel tubes (CFST). Based on 3600 ultrasonic measurement samples, an Extreme Gradient Boosting (XGBoost) model was enhanced through oversampling and hyperparameter optimization via Bayesian optimization (BO-XGBoost). The BO-XGBoost model demonstrated superior performance compared to baseline models (Random Forest, AdaBoost, and Gradient Boosting Decision Tree), achieving an overall prediction accuracy of 0.92, precision and recall of 0.90, and an AUC of 0.98. SHAP (SHapley Additive exPlanations) analysis revealed that sound velocity, sound time, acoustic amplitude, concrete strength, and fly ash content were the most influential features for model predictions. This hybrid approach offers high efficiency and accuracy for void defect detection in CFST, providing a novel solution that leverages the strengths of both traditional ultrasonic methods and artificial intelligence algorithms. The method not only detects the presence of void defects but also quantifies their extent, advancing CFST inspection from qualitative analysis to quantitative assessment.http://www.sciencedirect.com/science/article/pii/S2214509525001573CFSTVoid detectionXGBoostBayes optimization |
| spellingShingle | Shuai Wan Shipan Li Zheng Chen Yunchao Tang An ultrasonic-AI hybrid approach for predicting void defects in concrete-filled steel tubes via enhanced XGBoost with Bayesian optimization Case Studies in Construction Materials CFST Void detection XGBoost Bayes optimization |
| title | An ultrasonic-AI hybrid approach for predicting void defects in concrete-filled steel tubes via enhanced XGBoost with Bayesian optimization |
| title_full | An ultrasonic-AI hybrid approach for predicting void defects in concrete-filled steel tubes via enhanced XGBoost with Bayesian optimization |
| title_fullStr | An ultrasonic-AI hybrid approach for predicting void defects in concrete-filled steel tubes via enhanced XGBoost with Bayesian optimization |
| title_full_unstemmed | An ultrasonic-AI hybrid approach for predicting void defects in concrete-filled steel tubes via enhanced XGBoost with Bayesian optimization |
| title_short | An ultrasonic-AI hybrid approach for predicting void defects in concrete-filled steel tubes via enhanced XGBoost with Bayesian optimization |
| title_sort | ultrasonic ai hybrid approach for predicting void defects in concrete filled steel tubes via enhanced xgboost with bayesian optimization |
| topic | CFST Void detection XGBoost Bayes optimization |
| url | http://www.sciencedirect.com/science/article/pii/S2214509525001573 |
| work_keys_str_mv | AT shuaiwan anultrasonicaihybridapproachforpredictingvoiddefectsinconcretefilledsteeltubesviaenhancedxgboostwithbayesianoptimization AT shipanli anultrasonicaihybridapproachforpredictingvoiddefectsinconcretefilledsteeltubesviaenhancedxgboostwithbayesianoptimization AT zhengchen anultrasonicaihybridapproachforpredictingvoiddefectsinconcretefilledsteeltubesviaenhancedxgboostwithbayesianoptimization AT yunchaotang anultrasonicaihybridapproachforpredictingvoiddefectsinconcretefilledsteeltubesviaenhancedxgboostwithbayesianoptimization AT shuaiwan ultrasonicaihybridapproachforpredictingvoiddefectsinconcretefilledsteeltubesviaenhancedxgboostwithbayesianoptimization AT shipanli ultrasonicaihybridapproachforpredictingvoiddefectsinconcretefilledsteeltubesviaenhancedxgboostwithbayesianoptimization AT zhengchen ultrasonicaihybridapproachforpredictingvoiddefectsinconcretefilledsteeltubesviaenhancedxgboostwithbayesianoptimization AT yunchaotang ultrasonicaihybridapproachforpredictingvoiddefectsinconcretefilledsteeltubesviaenhancedxgboostwithbayesianoptimization |