Junwen Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Junwen Chen has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Kexiong Wu
School of Civil and Mapping Engineering, Guilin University of Technology, Guilin 541004, China
2 shared publications - Haodong Liu
School of Civil and Mapping Engineering, Guilin University of Technology, Guilin 541004, China
1 shared publication - Jin Yi
Guilin University of Technology
1 shared publication - Jinxuan Hu
School of civil engineering and architecture, Wuhan polytechnic University, Wuhan 430023, China
1 shared publication - Jiwang Zhang
Guangxi Key Laboratory of Green Building Materials and Construction Industrialization, Guilin University of Technology, Guilin 541004, China
1 shared publication - Lei Tang
Guangxi Airport Management Group, Nanning 530001, China
1 shared publication
Latest Publications
- Open Access
Interpretable Machine Learning Reveals Synergy-Gain Windows and Dual-Objective Mix-Proportion Boundaries for Compressive Strength and Peak Strain in Hybrid Steel–PVA Fiber-Reinforced Concrete
Hybrid steel–PVA fiber-reinforced concrete offers promise for enhancing both load-bearing capacity and deformation capacity. However, the coupled effects of fiber parameters and volume-fraction combinations on compressive strength (σc) and peak strain (εc) are still not fully understood. A unified, interpretable, and engineering-oriented quantitative framework is still lacking. This study compiled experimental data from 26 published literature, building a multi-source database consisting of 397 datasets for σc and 203 datasets for εc. Based on this database, a comprehensive analytical framework was proposed, including model prediction, SHAP-based interpretation, Monte Carlo marginalization, synergy-gain window determination, and dual-objective mix-proportion optimization. For σc prediction, LightGBM achieved the highest test-set R2 (0.9783), whereas CatBoost showed more robust error control (MAE = 2.7409 MPa). CatBoost was therefore selected as the base model for the subsequent interpretation analysis. For εc prediction, Bayesian-optimized CatBoost achieved the best test performance (R2 = 0.9659, MAE = 0.0218, RMSE = 0.0358), while the transfer-learning model reached a comparable accuracy level (R2 = 0.9650). SHAP analysis revealed that σc is mainly governed by matrix mix-proportion factors and steel fiber volume fraction, whereas εc is more sensitive to S/B and PVA-related variables. The mean synergy-gain maps generated via Monte Carlo marginalization and two-dimensional grid evaluation further showed clear differences between the two targets. Positive synergy in σc was highly localized. Its maximum mean synergy gain was 4.7949 MPa at (Steel, PVA) = (1.875%, 2.000%). By contrast, εc exhibited a wider positive-synergy region, with a peak value of 0.0141629 at (0.38%, 1.62%). Therefore, the engineering output of this study is not a single optimal mix point. Instead, it is a set of candidate windows for different performance targets, together with boundary-risk identification and priorities for experimental validation.
Open AccessInterpretable Machine Learning Reveals Synergy-Gain Windows and Dual-Objective Mix-Proportion Boundaries for Compressive Strength and Peak Strain in Hybrid Steel–PVA Fiber-Reinforced Concrete
Hybrid steel–PVA fiber-reinforced concrete offers promise for enhancing both load-bearing capacity and deformation capacity. However, the coupled effects of fiber parameters and volume-fraction combinations on compressive strength (σc) and peak strain (εc) are still not fully understood. A unified, interpretable, and engineering-oriented quantitative framework is still lacking. This study compiled experimental data from 26 published literature, building a multi-source database consisting of 397 datasets for σc and 203 datasets for εc. Based on this database, a comprehensive analytical framework was proposed, including model prediction, SHAP-based interpretation, Monte Carlo marginalization, synergy-gain window determination, and dual-objective mix-proportion optimization. For σc prediction, LightGBM achieved the highest test-set R2 (0.9783), whereas CatBoost showed more robust error control (MAE = 2.7409 MPa). CatBoost was therefore selected as the base model for the subsequent interpretation analysis. For εc prediction, Bayesian-optimized CatBoost achieved the best test performance (R2 = 0.9659, MAE = 0.0218, RMSE = 0.0358), while the transfer-learning model reached a comparable accuracy level (R2 = 0.9650). SHAP analysis revealed that σc is mainly governed by matrix mix-proportion factors and steel fiber volume fraction, whereas εc is more sensitive to S/B and PVA-related variables. The mean synergy-gain maps generated via Monte Carlo marginalization and two-dimensional grid evaluation further showed clear differences between the two targets. Positive synergy in σc was highly localized. Its maximum mean synergy gain was 4.7949 MPa at (Steel, PVA) = (1.875%, 2.000%). By contrast, εc exhibited a wider positive-synergy region, with a peak value of 0.0141629 at (0.38%, 1.62%). Therefore, the engineering output of this study is not a single optimal mix point. Instead, it is a set of candidate windows for different performance targets, together with boundary-risk identification and priorities for experimental validation.
- Open Access
Effects of Ion on the Properties of Seawater Slurry and Development of Salt-Tolerant Polymer Seawater Slurry
To address the significant deterioration in the performance of traditional drilling slurries due to seawater intrusion, this study developed a novel salt-tolerant polymer slurry (MXC) utilizing grafting modification techniques. The performance of MXC was systematically evaluated and compared with two commercial slurries, PAC and Flowz, through simulated formation filtration experiments. The results indicate that the MXC slurry exhibited the lowest filtration loss and was capable of forming a thinner, denser filter cake, thereby providing optimal wall protection. Mechanistic analysis revealed that grafting modification optimized the hydrophobic interactions between polymer molecules, constructing a dynamic physical cross-linking network and a rigid double-helical structure within the solution. This significantly enhanced the system’s viscosity and resistance to ionic interference, ultimately resulting in the formation of a dense network structure during the filtration process. This study offers a novel material solution and theoretical foundation for the development of high-performance salt-tolerant slurries in marine engineering.
Open AccessEffects of Ion on the Properties of Seawater Slurry and Development of Salt-Tolerant Polymer Seawater Slurry
To address the significant deterioration in the performance of traditional drilling slurries due to seawater intrusion, this study developed a novel salt-tolerant polymer slurry (MXC) utilizing grafting modification techniques. The performance of MXC was systematically evaluated and compared with two commercial slurries, PAC and Flowz, through simulated formation filtration experiments. The results indicate that the MXC slurry exhibited the lowest filtration loss and was capable of forming a thinner, denser filter cake, thereby providing optimal wall protection. Mechanistic analysis revealed that grafting modification optimized the hydrophobic interactions between polymer molecules, constructing a dynamic physical cross-linking network and a rigid double-helical structure within the solution. This significantly enhanced the system’s viscosity and resistance to ionic interference, ultimately resulting in the formation of a dense network structure during the filtration process. This study offers a novel material solution and theoretical foundation for the development of high-performance salt-tolerant slurries in marine engineering.
- Open Access
Progress Analysis and Prospect on the Influence of Early-Age Carbonation Curing on Properties of Cement-Based Materials
As a cutting-edge technology in the field of cement-based materials, early carbonation curing enables industrial carbon sequestration and functional modification, and the optimization of process parameters is the key to advancing the development of this technology. This paper reviews the mechanism of action and influencing factors of early carbonation curing (including moisture content, carbon dioxide concentration, pre-hydration degree, etc.), its effects on the mechanical properties and durability of materials, as well as the resulting changes in microstructure. Meanwhile, this review also covers content such as the hydration–carbonation coupling mechanism, mentions the relevant conditions of carbonation products and microstructure, analyzes the performance enhancement of the interfacial transition zone (ITZ), and provides relevant support for the low-carbon development of cement-based materials by combining the application practice of prefabricated components and the comparison of technical routes. Although early carbonation can significantly improve material properties and optimize microstructure, current research still has shortcomings: the exploration of mineral carbonation–hydration activity, microstructure evolution law, and product combination mechanism is relatively insufficient, and the understanding of carbonation–hydration coupling kinetics is still not in-depth enough, all of which are areas requiring further research in the future.
Open AccessProgress Analysis and Prospect on the Influence of Early-Age Carbonation Curing on Properties of Cement-Based Materials
As a cutting-edge technology in the field of cement-based materials, early carbonation curing enables industrial carbon sequestration and functional modification, and the optimization of process parameters is the key to advancing the development of this technology. This paper reviews the mechanism of action and influencing factors of early carbonation curing (including moisture content, carbon dioxide concentration, pre-hydration degree, etc.), its effects on the mechanical properties and durability of materials, as well as the resulting changes in microstructure. Meanwhile, this review also covers content such as the hydration–carbonation coupling mechanism, mentions the relevant conditions of carbonation products and microstructure, analyzes the performance enhancement of the interfacial transition zone (ITZ), and provides relevant support for the low-carbon development of cement-based materials by combining the application practice of prefabricated components and the comparison of technical routes. Although early carbonation can significantly improve material properties and optimize microstructure, current research still has shortcomings: the exploration of mineral carbonation–hydration activity, microstructure evolution law, and product combination mechanism is relatively insufficient, and the understanding of carbonation–hydration coupling kinetics is still not in-depth enough, all of which are areas requiring further research in the future.