materials-logo

Journal Browser

Journal Browser

Advanced Experimental Technology, Theory and Numerical Methods in Concrete Materials

A special issue of Materials (ISSN 1996-1944). This special issue belongs to the section "Construction and Building Materials".

Deadline for manuscript submissions: 20 September 2026 | Viewed by 4075

Editors

School of Transportation and Civil Engineering, Nantong University, Nantong 226019, China
Interests: concrete mechanical properties; fracture mechanisms; numerical simulations
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
1. College of Civil Engineering, Tongji University, Shanghai 200092, China
2. School of Transportation and Civil Engineering, Nantong University, Nantong 226019, China
Interests: sustainable construction engineering; low-carbon cementitious composites
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
College of Ocean Science and Engineering, Shanghai Maritime University, Shanghai 200135, China.
Interests: concrete materials; numerical simulation; durability; multi-field coupling; hydraulic engineering
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor Assistant
School of Transportation and Civil Engineering, Nantong University, Nantong 226019, China
Interests: automated construction; concrete material; advanced experimental method; numerical simulation; intelligent management

Special Issue Information

Dear Colleagues,

We are excited to announce our forthcoming Special Issue, "Advanced Experimental Technology, Theory and Numerical Methods in Concrete Materials". In the current era of booming modern engineering technology, concrete materials are the linchpins in various fields, such as infrastructure construction, architecture, and related engineering domains. Gaining an in-depth understanding of their characteristics and behaviors, and devising innovative research methods, holds the key to unlocking the potential for sustainable development and technological breakthroughs within related industries. This Special Issue collates the latest research accomplishments, novel approaches, and forward-thinking perspectives from around the globe in this domain, thereby creating an authoritative and profound platform for academic exchange among researchers, engineers, and scholars.

This Special Issue is meticulously planned and structured to spotlight recent progress and innovation in the field of concrete materials. The featured articles are anticipated to span multiple dimensions, from the minutiae of experimental techniques to the grandiosity of theoretical frameworks and the sophistication of numerical methods. The overarching trend in this specialized area is veering towards a more integrated and comprehensive exploration, leveraging advanced technologies and interdisciplinary knowledge to enhance our understanding and manipulation of these materials.

For this Special Issue, we welcome original research articles and reviews. Research areas may encompass (but are not confined to) the following:

  • Experimental Technology

Pioneering techniques for gauging the mechanical properties of concrete materials at both the micro and macro levels. For instance, state-of-the-art in situ testing procedures can precisely capture the stress, strain, and deformation idiosyncrasies of materials within real-world engineering settings, furnishing more dependable parameter benchmarks for engineering blueprints.

  • Theoretical Research

By leveraging the theoretical scaffolds of continuum mechanics, fracture mechanics, and damage mechanics, profound investigations can be conducted into the constitutive relations of concrete materials to erect theoretical models capable of faithfully depicting the complex mechanical behaviors of materials, like nonlinearity, anisotropy, and rate dependence, thereby enhancing the precision and reliability of numerical simulations and engineering dissections.

  • Numerical Methods

Develop streamlined and accurate numerical algorithms for simulating the mechanical behaviors and engineering responses of concrete materials. For example, enhanced algorithms predicated on the finite element method, discrete element method, finite difference method, etc., can more adeptly handle complex conundrums such as the large deformation, fracture, and contact of materials, augmenting the computational efficiency and stability of numerical simulations.

We look forward to receiving your contributions.

Dr. Shuyang Yu
Dr. Yuan Gao
Dr. Wenbing Zhang
Guest Editors

Dr. Jiajie Li
Guest Editor Assistant

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Materials is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • concrete
  • mechanical properties
  • numerical methods
  • theoretical solutions
  • fracture mechanisms

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (10 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

17 pages, 3159 KB  
Article
Investigation of the Changes in Microstructure and Transport Properties of Leached Clay–Cement Pastes
by Kailai Zhang, Wenwei Li, Huamei Yang, Xinyu Li, Dan Tian and Fan Li
Materials 2026, 19(14), 2937; https://doi.org/10.3390/ma19142937 - 8 Jul 2026
Viewed by 196
Abstract
Clay–cement slurry, as a widely used anti-seepage material, is prone to calcium leaching and deterioration when exposed to environmental water. The influence of microstructural and mineralogical evolution on the transport properties of clay–cement samples under leaching conditions remains to be investigated. In this [...] Read more.
Clay–cement slurry, as a widely used anti-seepage material, is prone to calcium leaching and deterioration when exposed to environmental water. The influence of microstructural and mineralogical evolution on the transport properties of clay–cement samples under leaching conditions remains to be investigated. In this paper, accelerated calcium leaching tests were conducted on clay–cement pastes. A variety of techniques, including XRD, SEM, and NMR, were used to characterize the microstructural and mineralogical changes in the leached samples. The effect of accelerated leaching on transport behavior was studied by measuring changes in the water permeability and calculating diffusivity. XRD and SEM analyses show that after 28 days, the characteristic peaks of portlandite and ettringite almost disappear, while C-S-H gel undergoes decalcification and decomposition, leading to an increase in pore number and a notable rise in pore size (up to 1.90 μm). NMR results indicate that total porosity and peak pore size increase significantly, with the proportion of gel pores decreasing and that of small capillary pores (10–50 nm) rising from 10% to 22.1%. Moreover, the surface layer porosity (0–5 mm) increases from 31.33% to 50.65%, while the middle and lower layers show less degradation, indicating a progressive deterioration pattern. Regarding transport properties, the hydraulic conductivity increases from 4.7 × 10−10 cm/s to 2.14 × 10−8 cm/s (a two-order-of-magnitude increase), and the diffusion coefficient rises from 1.6 × 10−11 m2/s to 8.6 × 10−11 m2/s (a 5.3-fold increase). Both the diffusion coefficient and its increase factor gradually decrease from the surface to the interior, consistent with the evolution of porosity. Full article
Show Figures

Figure 1

23 pages, 10015 KB  
Article
Study on Mechanical Properties and Synergistic Mechanism of Concrete Reinforced with Hybrid Basalt Fibers of Different Lengths
by Yingying Tao, Chuan Zhao, Yanmei Zhang, Yanchang Zhu, Yongxiang Fang, Rui Zhang, Qikai Wang, Fuxing Wu and Qingzhe Yi
Materials 2026, 19(13), 2848; https://doi.org/10.3390/ma19132848 - 3 Jul 2026
Viewed by 166
Abstract
Basalt fiber (BF) is an effective reinforcement for improving concrete’s mechanical properties and crack resistance due to its high tensile strength and bridging ability. To investigate the influence of fiber length combinations on the mechanical performance of concrete, basalt fiber-reinforced concrete (BFRC) specimens [...] Read more.
Basalt fiber (BF) is an effective reinforcement for improving concrete’s mechanical properties and crack resistance due to its high tensile strength and bridging ability. To investigate the influence of fiber length combinations on the mechanical performance of concrete, basalt fiber-reinforced concrete (BFRC) specimens were prepared using single and hybrid blending methods. Compressive and splitting tensile tests, scanning electron microscopy, and numerical simulations were conducted to evaluate the effects of fiber content and length hybridization, and analyze the possible reinforcement mechanisms. Results showed that for single-blended BFRC with 18 mm BF, both compressive and tensile strengths peaked at a 0.2% dosage, then declined. Conversely, the strengths of hybrid BFRC continuously increased with fiber content, reaching 33.00 MPa and 2.38 MPa at a 0.3% dosage, significantly outperforming the single-length fiber systems. Microstructural observations and numerical analyses suggested that fibers with different lengths contributed to complementary reinforcement effects during the loading process. The improved performance was attributed to the combined effects of crack bridging and stress redistribution provided by fibers with different lengths. Full article
Show Figures

Graphical abstract

20 pages, 23493 KB  
Article
Mechanical Behavior and Damage Characteristics of Cemented Tailings Backfill Under Multiple Different Stress Disturbances
by Xiaofei Li, Yuanfan Liu, Jie Wang, Yan Li and Jianxin Fu
Materials 2026, 19(12), 2654; https://doi.org/10.3390/ma19122654 - 20 Jun 2026
Viewed by 220
Abstract
To investigate the impact of underground multiple stress disturbances on the long-term stability of cemented tailings backfill (CTB), this study conducted experiments under different disturbance levels (20–80% of static strength) and frequencies (1–4 times). By comprehensively utilizing mechanical testing, wave velocity monitoring, digital [...] Read more.
To investigate the impact of underground multiple stress disturbances on the long-term stability of cemented tailings backfill (CTB), this study conducted experiments under different disturbance levels (20–80% of static strength) and frequencies (1–4 times). By comprehensively utilizing mechanical testing, wave velocity monitoring, digital image correlation (DIC), and scanning electron microscopy (SEM), the “heterogeneous” evolution mechanism of macro-micro damage was revealed. The results indicate that disturbance level and frequency exert distinctly different driving effects on the deterioration of CTB, rather than a simple linear superposition. Specifically, low-frequency disturbance produces a compaction strengthening effect, microscopically promoting the generation of Ca(OH)2 and ettringite (increased Ca/Si ratio). In contrast, the combination of high disturbance and high frequency induces free water extrusion and inhibits hydration, leading to an advanced damage threshold based on energy evolution and the accelerated coalescence of microcracks, which favors the formation of C-S-H gel (decreased Ca/Si ratio). Within this heterogeneous mechanism, the disturbance level acts as the dominant controlling factor. This study clarifies the nonlinear mechanical and chemical evolution paths under composite disturbances, providing theoretical support for the dynamic stability control of backfill in deep multi-step mining. Full article
Show Figures

Figure 1

36 pages, 5761 KB  
Article
A Stacking Ensemble-Based Framework for Predicting the Compressive Strength of Microwave-Cured Geopolymers
by Sarah Nahd Kadhim, Ahmet Emin Kurtoğlu, Derya Bakbak, Abdulkadir Çevik and Ali İhsan Özçetin
Materials 2026, 19(12), 2474; https://doi.org/10.3390/ma19122474 - 9 Jun 2026
Viewed by 213
Abstract
Microwave curing offers energy-efficient geopolymer synthesis, yet optimizing compressive strength remains challenging due to complex variable interactions. This study develops an interpretable stacking ensemble surrogate model to predict the strength of microwave-cured geopolymers. A literature-derived dataset of 235 observations was systematically compiled from [...] Read more.
Microwave curing offers energy-efficient geopolymer synthesis, yet optimizing compressive strength remains challenging due to complex variable interactions. This study develops an interpretable stacking ensemble surrogate model to predict the strength of microwave-cured geopolymers. A literature-derived dataset of 235 observations was systematically compiled from literature (2010–2025), covering diverse aluminosilicate precursors, activator concentrations, and curing parameters. The framework integrates linear, kernel, and tree-based base models via a linear meta-learner to enhance generalization. Unlike conventional models, source-aware validation was implemented to ensure reliability across heterogeneous studies. The stacking ensemble significantly outperformed standalone models, achieving a coefficient of determination (R2) of 0.957 and a low RMSE of 5.64 MPa. Crucially, the model demonstrated high reliability through rigorous residual analysis and noise sensitivity stress tests, confirming stable performance across the entire strength range. Interpretability analyses using SHAP and partial dependence plots identified curing time, microwave power, and specimen size as dominant factors governing strength. These dependencies adhered to established geopolymerization kinetics, yielding physically reasonable response surfaces. This work demonstrates that stacking ensemble models serve as reliable statistical surrogate tools (not mechanistic simulators) for preliminary experimental screening within the investigated parameter space. The framework has not been validated against genuinely independent experimental campaigns or industrial-scale microwave curing conditions, and should be treated as a literature-based surrogate model rather than a deployment-validated predictive tool. Full article
Show Figures

Figure 1

16 pages, 13866 KB  
Communication
Rheology and Shape Stability Control of 3D-Printed White Calcium Sulfoaluminate Cement Composites Containing Oyster Shell and Cuttlebone Powder
by Xingyu Qu, Qinyuan Wang, Jiafeng Kong, Junyu Wang, Jie Wang, Xingang Xu, Yan Zheng, Heyang Wu and Mingxu Chen
Materials 2026, 19(11), 2410; https://doi.org/10.3390/ma19112410 - 5 Jun 2026
Viewed by 309
Abstract
To optimize the shape stability of 3D-printed white calcium sulfoaluminate (WCSA) cement composites, oyster shell powder (OSP) and cuttlebone powder (CBP) were introduced as white admixtures to regulate rheological properties and printability. The setting behavior, rheological properties, and shape stability of the WCSA [...] Read more.
To optimize the shape stability of 3D-printed white calcium sulfoaluminate (WCSA) cement composites, oyster shell powder (OSP) and cuttlebone powder (CBP) were introduced as white admixtures to regulate rheological properties and printability. The setting behavior, rheological properties, and shape stability of the WCSA cement composites were evaluated by Vicat setting-time tests, rotational rheological measurements, three-stage thixotropic recovery tests, and structural deformation measurements, together with mechanical strength tests, XRD, and SEM analyses. The results showed that the incorporation of OSP and CBP shortened the setting time of WCSA cement composites. The initial and final setting times decreased from 41 min and 67 min to 17 min and 30 min in the WCSA cement composites with OSP, and from 42 min and 66 min to 20 min and 33 min in the WCSA cement composites with CBP, which improved printing operability. As the OSP and CBP content increases from 0% to 24%, the dynamic yield stress of WCSA cement composites increased from 48.83 Pa to 530.59 Pa and 60.30 Pa to 1085.80 Pa, respectively. The thixotropic recovery degree of WCSA cement composites increased from 57.89% to 86.46%, and 56.60% to 92.14%, respectively. As the OSP and CBP contents increase from 0% to 24%, the structural deformation decreased from 12.39% to 6.91% and 13.29% to 5.12% respectively, which improved buildability of the printed structures. In addition, although OSP and CBP reduced the mechanical strength of WCSA cement composites compared with the control group, the flexural and compressive strengths gradually recovered as the contents increased from 6% to 24% due to the enhanced filling effect and improved particle packing. This study provides a reference for the application of marine calcareous solid wastes in sustainable 3D-printed cementitious materials. Full article
Show Figures

Graphical abstract

21 pages, 15578 KB  
Article
Microscopic Characterization and Efficiency Coefficient Evaluation of Modified Recycled Concrete Micropowder in Cementitious Materials
by Qiuyi Li, Pengfei Zhang, Mingxu Chen, Liang Wang, Gongbing Yue, Jinghua Yan, Chenyang Xu and Yuanxin Guo
Materials 2026, 19(11), 2391; https://doi.org/10.3390/ma19112391 - 3 Jun 2026
Viewed by 294
Abstract
To advance the development of sustainable buildings, this study investigates recycled cement-based materials. The core component of this material is concrete-based recycled micropowder (CRM), which is shaped and reinforced from recycled construction waste. It is then activated through high-temperature calcination to produce modified [...] Read more.
To advance the development of sustainable buildings, this study investigates recycled cement-based materials. The core component of this material is concrete-based recycled micropowder (CRM), which is shaped and reinforced from recycled construction waste. It is then activated through high-temperature calcination to produce modified recycled micropowder (MRM), and the resulting changes in its properties are analyzed. X-ray diffraction, Brunauer–Emmett–Teller surface area, and hydration heat tests reveal that cementitious materials incorporating MRM800 contain more C-S-H and other hydration products, exhibit lower porosity, and demonstrate stronger hydration reactions. The results show that 800 °C is the optimal calcination temperature for CRM activation. For recycled silica-based mortar (RSM), the introduction of an efficiency coefficient (Kλ) allows for a quantitative, scientific, and intuitive evaluation of the contributions of three admixtures, aiding in the optimization of the mix ratio. RSM with MRM showed improved performance, with compressive strength ranging from 24.3 to 42.3 MPa. A 20% MRM addition effectively enhanced the mechanical properties of the mortar, while the mixture with 10% MRM and a 1:3 cement-to-sand ratio exhibited only 8.23% strength loss and 0.78% mass loss after 50 freeze–thaw cycles. MRM can improve the compactness of the cement matrix and thus optimize its freeze–thaw resistance, providing an eco-friendly technical solution for the engineering application of recycled mortar in cold regions. Full article
Show Figures

Figure 1

32 pages, 11709 KB  
Article
Influence of Waste Tire Rubber Particle Size and Content on Mechanical Properties and Energy Dissipation of R-CTB
by Jie Wang, Yuanfan Liu, Kun Wang, Yan Li and Jianxin Fu
Materials 2026, 19(9), 1676; https://doi.org/10.3390/ma19091676 - 22 Apr 2026
Viewed by 448
Abstract
To achieve the resource utilization of waste tires and improve the mechanical performance of cemented tailings backfill, rubber–cemented tailings backfill (R-CTB) specimens were prepared with four rubber particle sizes (20-, 40-, 60-, and 80-mesh) and four contents (2%, 4%, 6%, and 8%). A [...] Read more.
To achieve the resource utilization of waste tires and improve the mechanical performance of cemented tailings backfill, rubber–cemented tailings backfill (R-CTB) specimens were prepared with four rubber particle sizes (20-, 40-, 60-, and 80-mesh) and four contents (2%, 4%, 6%, and 8%). A 0% rubber control group was introduced to address the lack of quantitative comparison. Uniaxial compression, digital image correlation (DIC), and scanning electron microscopy (SEM) were used to study mechanical behavior, energy evolution, and microstructural characteristics at 7 and 28 days. Results indicate that strength and elastic modulus first increase then decrease with particle size and decrease with content rise. Compared with the control group, R-CTB shows lower strength but significantly higher ductility and energy dissipation. Finer particles cause strain localization; higher content and finer size increase pores and weaken interfaces. Rubber incorporation transforms failure from brittle to ductile, providing a basis for engineering application. Full article
Show Figures

Figure 1

30 pages, 82741 KB  
Article
Feasibility, Mechanical Properties, and Environmental Impact of 3D-Printed Mortar Incorporating Recycled Fine Aggregates from Decoration and Renovation Waste
by Pu Yuan, Xinjie Wang, Jie Huang, Quanbin Shi and Minqi Hua
Materials 2026, 19(8), 1618; https://doi.org/10.3390/ma19081618 - 17 Apr 2026
Viewed by 544
Abstract
To address the accumulation of construction and demolition waste (W&D), this study recycled it into regenerated fine aggregate and prepared 3D-printed mortars with replacement ratios ranging from 0% to 100%. The mechanical properties of hardened specimens were tested, and the degradation mechanisms of [...] Read more.
To address the accumulation of construction and demolition waste (W&D), this study recycled it into regenerated fine aggregate and prepared 3D-printed mortars with replacement ratios ranging from 0% to 100%. The mechanical properties of hardened specimens were tested, and the degradation mechanisms of mechanical performance were investigated through SEM, MIP, and microhardness analysis. The carbon emissions of the materials were evaluated. The results indicated that while the 3D-printed mortar exhibited excellent buildability, its compressive strength, flexural strength, and interlayer bond strength gradually decreased with increasing replacement ratio. MIP results showed that as the replacement ratio of the W&D increased from 0% to 100%, the total porosity of the 3D-printed specimens significantly increased from 14.7433% to 27.5903%. SEM and microhardness images confirmed severe ITZ deterioration, and the average ITZ width increased from 31 to 79 μm. As the W&D replacement ratio increased from 0% to 100%, the total GWP decreased from 0.4043 to 0.3800 kg CO2-eq/kg mortar. Maximizing the utilization of W&D is key to achieving efficient utilization of solid waste. Considering printability, mechanical performance, interlayer behavior, microstructural characteristics, and environmental impact in a comprehensive manner, the 80% W&D replacement ratio can be regarded as a relatively balanced and promising selection. This work not only suggests the technical feasibility of recycling W&D in 3D printing mortar, but also proposes a sustainable pathway to reduce carbon emissions in construction. Full article
Show Figures

Graphical abstract

21 pages, 6200 KB  
Article
Prediction and Regulation of SCC’s Shrinkage Using the PSO-BPNN Model
by Tongyuan Ni, Lihua Shen, Shenghao Shen, Zaoyang Cai, Wen Chu, Chengshun Hu, Chenhui Jiang and Kai Jing
Materials 2026, 19(7), 1468; https://doi.org/10.3390/ma19071468 - 7 Apr 2026
Viewed by 500
Abstract
The shrinkage deformation is a significant risk to self-compacting concrete (SCC)-filled steel tube structures. It was essential to understand the concrete autogenous shrinkage strain before being regulated in order to determine compensation shrinkage measures. In this study, A PSO-BPNN model was constructed, which [...] Read more.
The shrinkage deformation is a significant risk to self-compacting concrete (SCC)-filled steel tube structures. It was essential to understand the concrete autogenous shrinkage strain before being regulated in order to determine compensation shrinkage measures. In this study, A PSO-BPNN model was constructed, which is based on the Particle Swarm Optimization-Back Propagation Neural Networks (PSO-BPNN), and the autogenous shrinkage strain of SCC was predicted based on PSO-BPNN before being regulated. Moreover, some experiments about compensating for shrinkage by expansion and by a combination of expansion and contraction were investigated. Based on this prediction, a series of experiments was conducted on the regulation of the shrinkage deformation of SCC for an actual bridge project. The results indicated that a good consistency of PSO-BPNN between predicted and measured values, demonstrating that PSO-BPNN is a model with high accuracy in predicting concrete autogenous shrinkage strain before regulation, and as a guidance for regulation to compensate for shrinkage. The prediction error was less than 10% for 28-day self-shrinkage, and the experimental workload was reduced. The PSO-BPNN is a convenient tool for predicting the shrinkage of SCC, enabling the determination of dosages of expansion agent and reducing shrinkage agent to achieve SCC’s shrinkage regulation. Full article
Show Figures

Figure 1

23 pages, 2486 KB  
Article
Research on the Prediction Method for Ultimate Bearing Capacity of Circular Concrete-Filled Steel Tubular Columns Based on Random Search-Optimized CatBoost Algorithm
by Zhenyu Wang, Yunqiang Wang, Xiangyu Xu, Zihan Zhang, Yaxing Wei and Dan Luo
Materials 2026, 19(7), 1360; https://doi.org/10.3390/ma19071360 - 30 Mar 2026
Viewed by 558
Abstract
With the development of various emerging structures, concrete-filled steel tubular (CFST) columns have become critical load-bearing components in key infrastructures such as subways and underground utility tunnels. Accurately predicting their ultimate bearing capacity (Nu) is essential for guaranteeing structural safety. [...] Read more.
With the development of various emerging structures, concrete-filled steel tubular (CFST) columns have become critical load-bearing components in key infrastructures such as subways and underground utility tunnels. Accurately predicting their ultimate bearing capacity (Nu) is essential for guaranteeing structural safety. To address the limitations of traditional empirical formulas and code-based calculation approaches, this paper proposes a prediction model for ultimate bearing capacity based on the CatBoost algorithm optimized by Random Search. Furthermore, the marginal contribution of each key feature to the prediction results is measured through interpretability analysis. First, a database containing 438 CFST column ultimate bearing capacity test cases was established, with key parameters such as geometric dimensions and material properties as input variables. Second, the predictive performance of six machine learning algorithms—CatBoost, LightGBM, Random Forest (RF), Gradient Boosting (GB), K-Nearest Neighbors (KNN), and XGBoost—was compared. A five-fold cross-validation integrated with a Random Search strategy was employed for joint hyperparameter optimization. The results show that the optimized CatBoost model significantly outperforms other algorithms and conventional design codes, achieving a coefficient of determination (R2) as high as 0.99 and a root mean square error (RMSE) of 174.29 kN. Furthermore, the SHAP (Shapley Additive exPlanations) method was used to perform global and local interpretability analyses of the prediction model. This not only quantified the individual contribution and interaction effects of each feature parameter on the bearing capacity but also revealed that geometric parameters are the primary influencing factor. This finding confirms a high degree of consistency between the prediction mechanism of the data-driven model and classical mechanical theories, effectively validating the model’s reliability. This study provides an efficient and reliable tool for the optimal design and rapid evaluation of CFST columns and establishes a new data-driven paradigm for the design and reinforcement of key components in underground structures. Full article
Show Figures

Figure 1

Back to TopTop