Xi Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xi Huang has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
Huang Huang
School of Civil Engineering, Henan University of Technology, Zhengzhou, Henan, China
5 shared publicationsZhishen Wu
Key Laboratory of C & PC Structures Ministry of Education, National and Local Unified Engineering Research Center for Basalt Fiber Production and Application Technology, Southeast University, Nanjing, Jiangsu, China
4 shared publicationsLongxiang Wang
Key Laboratory of C & PC Structures Ministry of Education, National and Local Unified Engineering Research Center for Basalt Fiber Production and Application Technology, Southeast University, Nanjing, Jiangsu, China
2 shared publications- Mao Kurumatani
Department of Urban and Civil Engineering, Ibaraki University, Hitachi, Japan
2 shared publications Mohamad Najib Alhebrawi
Ibaraki University, Department of Urban and Civil Engineering, Hitachi 316-8511, Japan
2 shared publications- Zhen Sun
School of Civil Engineering, Southeast University, Nanjing 211189, China
2 shared publications
Latest Publications
- 6 November 2026
- Published by Springer Nature in Materials and Structures
- Vol. 59 (10) , 450
Parametric modeling and reconstruction method for steel-bar rib geometry based on 3D scanning
- 6 November 2026
- Published by Springer Nature in Materials and Structures
- Vol. 59 (10) , 450
Parametric modeling and reconstruction method for steel-bar rib geometry based on 3D scanning
- 16 September 2026
- Published by Springer Nature in Journal of Nondestructive Evaluation
- Vol. 45 (4) , 130
Multitask Learning Approach for Bolt Torque Loss Detection Using Variable-Frequency Hammering Cepstral Coefficients
- 16 September 2026
- Published by Springer Nature in Journal of Nondestructive Evaluation
- Vol. 45 (4) , 130
Multitask Learning Approach for Bolt Torque Loss Detection Using Variable-Frequency Hammering Cepstral Coefficients
- 1 December 2025
- Published by Wiley in Structural Concrete
Three‐stage weight‐based aggregate generation framework for 3D concrete mesostructure modeling
Aggregates determine the durability, workability, and strength of concrete, influenced by their size, shape, and distribution. Existing 3D modeling methods oversimplify aggregate shapes to reduce computational complexity, sacrificing realism. Thus, this study proposes a three‐stage weight‐based framework to generate realistic 3D concrete mesostructures. First, an additively weighted Voronoi diagram creates aggregates with diverse realistic shapes, including nonconvex forms and smooth surfaces. Next, aggregates undergo shape filtering to exclude rarely occurring isotropic shapes based on aspect ratio statistics from cross‐sectional images. Finally, aggregates are packed according to a target grading curve and volume fraction. The proposed model is validated against real specimens by comparing filling ratios, particle size distributions, and aspect ratios. Relative errors in the filling ratio, particle count, and aspect ratio distribution are within 3%, confirming that the framework accurately replicates mesostructural features. The approach provides a reliable basis for finite element simulations and fracture analyses in concrete modeling.
- 1 December 2025
- Published by Wiley in Structural Concrete
Three‐stage weight‐based aggregate generation framework for 3D concrete mesostructure modeling
Aggregates determine the durability, workability, and strength of concrete, influenced by their size, shape, and distribution. Existing 3D modeling methods oversimplify aggregate shapes to reduce computational complexity, sacrificing realism. Thus, this study proposes a three‐stage weight‐based framework to generate realistic 3D concrete mesostructures. First, an additively weighted Voronoi diagram creates aggregates with diverse realistic shapes, including nonconvex forms and smooth surfaces. Next, aggregates undergo shape filtering to exclude rarely occurring isotropic shapes based on aspect ratio statistics from cross‐sectional images. Finally, aggregates are packed according to a target grading curve and volume fraction. The proposed model is validated against real specimens by comparing filling ratios, particle size distributions, and aspect ratios. Relative errors in the filling ratio, particle count, and aspect ratio distribution are within 3%, confirming that the framework accurately replicates mesostructural features. The approach provides a reliable basis for finite element simulations and fracture analyses in concrete modeling.
- Top Cited Papers
- 25 October 2025
- Published by SAGE Publications in Structural Health Monitoring
Advanced prediction of pipeline vertical deformation and axial strain via multi-source data fusion and multi-task deep learning
Vertical deformation and axial strain are crucial indicators for evaluating pipeline performance. Accurate prediction of these indicators provides essential support for early warning and proactive maintenance. To achieve this, a multi-sensor monitoring system was constructed by combining an embedded static leveling instrument with a long-gauge fiber-optic grating sensor system to sequentially monitor vertical deformation and axial strain. A novel multi-task prediction model, HO-CNN-BiGRU-AM-HMTL, was proposed to capture the spatiotemporal correlations between deformation and strain. The sensitivity of the model’s hyperparameters was examined, and the effects of dataset size (DS) and prediction horizon on model performance were analyzed. The model’s performance was evaluated by comparing it with existing single-task learning (STL) and multi-task learning (MTL) models in terms of prediction accuracy and computational efficiency. The results indicated that hyperparameter tuning of the hippopotamus optimization module enhanced the model’s performance. The DS showed an initial improvement followed by a decline in performance, while the prediction horizon demonstrated a gradual decrease, then a sharp drop. Maintaining the DS between 4 and 5 months and the prediction horizon within 7 days is recommended. The HO-CNN-BiGRU-AM-HMTL model outperformed existing STL and MTL models in prediction accuracy, reducing computation time by 70.13%–88.48% compared to STL and improving it by 4.05%–40.54% over MTL. Although there was some computational overhead, the overall runtime of the model remained under 16 s, meeting the requirements for engineering applications. This study integrates pipeline engineering with deep learning techniques to enable advanced prediction of deformation and strain, providing crucial support for risk warning and proactive maintenance.
- 25 October 2025
- Published by SAGE Publications in Structural Health Monitoring
Top Cited PapersAdvanced prediction of pipeline vertical deformation and axial strain via multi-source data fusion and multi-task deep learning
Vertical deformation and axial strain are crucial indicators for evaluating pipeline performance. Accurate prediction of these indicators provides essential support for early warning and proactive maintenance. To achieve this, a multi-sensor monitoring system was constructed by combining an embedded static leveling instrument with a long-gauge fiber-optic grating sensor system to sequentially monitor vertical deformation and axial strain. A novel multi-task prediction model, HO-CNN-BiGRU-AM-HMTL, was proposed to capture the spatiotemporal correlations between deformation and strain. The sensitivity of the model’s hyperparameters was examined, and the effects of dataset size (DS) and prediction horizon on model performance were analyzed. The model’s performance was evaluated by comparing it with existing single-task learning (STL) and multi-task learning (MTL) models in terms of prediction accuracy and computational efficiency. The results indicated that hyperparameter tuning of the hippopotamus optimization module enhanced the model’s performance. The DS showed an initial improvement followed by a decline in performance, while the prediction horizon demonstrated a gradual decrease, then a sharp drop. Maintaining the DS between 4 and 5 months and the prediction horizon within 7 days is recommended. The HO-CNN-BiGRU-AM-HMTL model outperformed existing STL and MTL models in prediction accuracy, reducing computation time by 70.13%–88.48% compared to STL and improving it by 4.05%–40.54% over MTL. Although there was some computational overhead, the overall runtime of the model remained under 16 s, meeting the requirements for engineering applications. This study integrates pipeline engineering with deep learning techniques to enable advanced prediction of deformation and strain, providing crucial support for risk warning and proactive maintenance.
- 16 July 2025
- Published by World Scientific Pub Co Pte Ltd
- p. 921-937
Adaptive Excitation Frequency Matching and Acoustic-Feature-Based Automatic Hammering Inspection System
- 16 July 2025
- Published by World Scientific Pub Co Pte Ltd
- p. 921-937
Adaptive Excitation Frequency Matching and Acoustic-Feature-Based Automatic Hammering Inspection System
- Top Cited Papers
- 16 April 2025
- Published by Springer Nature in Journal of Civil Structural Health Monitoring
- Vol. 15 (7) , 2433-2453
Pipeline deformation monitoring based on long-gauge FBG sensing system: missing data recovery and deformation calculation
- 16 April 2025
- Published by Springer Nature in Journal of Civil Structural Health Monitoring
- Vol. 15 (7) , 2433-2453
Top Cited PapersPipeline deformation monitoring based on long-gauge FBG sensing system: missing data recovery and deformation calculation
- 16 November 2023
- Published by World Scientific Pub Co Pte Ltd in International Journal of Structural Stability and Dynamics
- Vol. 23 (16n18)
Adaptive Excitation Frequency Matching and Acoustic-Feature-Based Automatic Hammering Inspection System
Hammering tests are employed for detecting surface and internal damage; however, their accuracy depends on the experience and expertise of inspectors. Because automation techniques can address the limitations of manual hammering tests, researchers have developed automatic hammering inspection systems to replace or assist conventional hammering inspection. Although several studies on automatic hammering inspection have been reported, several challenges hinder the practical application of their results. The relative hammering frequency and identification algorithms for complex and diverse damage are critical factors in implementing developed techniques. In a previous study, an automatic hammering inspection device for rapid and automated damage detection in practical applications was developed. This device can remotely adjust the hammering angle and force to increase detection accuracy and efficiency. Furthermore, an artificial-intelligence-enhanced damage identification method was developed to identify fine concrete cracks accurately using acoustic data. This study developed an automatic hammering inspection system with an adaptive matching function and automatic damage identification to increase the accuracy and efficiency of damage detection. First, by imitating human auditory judgment, an adaptive matching algorithm for the excitation frequencies of different damage types was developed to determine the optimal excitation frequency. Second, the relationships between acoustic features and damage information were analyzed. Finally, two concrete specimens with artificial damage were tested using the proposed system, with the relationships between the acoustic features in the time and frequency domains, as well as the damage location and depth, investigated experimentally. The results show that the proposed system can accurately identify surface and internal damage distributions up to a depth of 100[ ]mm at 20[ ]mm intervals.
- 16 November 2023
- Published by World Scientific Pub Co Pte Ltd in International Journal of Structural Stability and Dynamics
- Vol. 23 (16n18)
Adaptive Excitation Frequency Matching and Acoustic-Feature-Based Automatic Hammering Inspection System
Hammering tests are employed for detecting surface and internal damage; however, their accuracy depends on the experience and expertise of inspectors. Because automation techniques can address the limitations of manual hammering tests, researchers have developed automatic hammering inspection systems to replace or assist conventional hammering inspection. Although several studies on automatic hammering inspection have been reported, several challenges hinder the practical application of their results. The relative hammering frequency and identification algorithms for complex and diverse damage are critical factors in implementing developed techniques. In a previous study, an automatic hammering inspection device for rapid and automated damage detection in practical applications was developed. This device can remotely adjust the hammering angle and force to increase detection accuracy and efficiency. Furthermore, an artificial-intelligence-enhanced damage identification method was developed to identify fine concrete cracks accurately using acoustic data. This study developed an automatic hammering inspection system with an adaptive matching function and automatic damage identification to increase the accuracy and efficiency of damage detection. First, by imitating human auditory judgment, an adaptive matching algorithm for the excitation frequencies of different damage types was developed to determine the optimal excitation frequency. Second, the relationships between acoustic features and damage information were analyzed. Finally, two concrete specimens with artificial damage were tested using the proposed system, with the relationships between the acoustic features in the time and frequency domains, as well as the damage location and depth, investigated experimentally. The results show that the proposed system can accurately identify surface and internal damage distributions up to a depth of 100[ ]mm at 20[ ]mm intervals.
- 1 January 2023
- Published by Inderscience Publishers in International Journal of Sustainable Materials and Structural Systems
- Vol. 1 (1)
Development of an automated hammer testing system for concrete structures
- 1 January 2023
- Published by Inderscience Publishers in International Journal of Sustainable Materials and Structural Systems
- Vol. 1 (1)
Development of an automated hammer testing system for concrete structures