To investigate the interfacial bond performance of highland barley straw ash (HBSA)-modified magnesium oxychloride cement mortar (MOCM) with ordinary concrete, the influence of three variables, HBSA dosage, interfacial agent, and thickness of MOCM, on the interfacial bond strength in five environments, namely, indoor environment, immersion, salt brine, freezing and thawing, and salt-freezing coupling, was analyzed. A hybrid GA-SVR model was developed through genetic algorithm optimization of support vector regression. The inputs of the prediction model were erosion environment, erosion age, interfacial agent, HBSA dosage, and MOCM thickness, and the output was interfacial bond strength. The 1 960 sets of experimental data were utilized as the database for the hybrid prediction model, including 1 372 sets of data (70%) for the training set, 294 sets of data (15%) for the validation set, and 294 sets of data (15%) for the testing set. The results showed that the MOCM-OPCC specimen with HBSA addition, painted interfacial agent, and MOCM layer thickness of 18 mm had the highest bond strength, which reached 1.56 MPa after curing to 28 d and still maintained high interfacial bond performance after erosion. The hybrid optimization model, GA-SVR, can significantly improve the prediction accuracy of the SVR model and exhibits obvious advantages in predicting the interfacial bonding performance between MOCM and OPCC. Compared with the SVR model, the MAE index error of the GA-SVR model was reduced by 28.57%, the RMSE index error by 20%, the R2 coefficient increased by 3.23%, and the SMAPE error by 5.34%.
| [1] |
Li K, Wang Y, Yao N, et al.Recent Progress of Magnesium Oxychloride Cement: Manufacture, Curing, Structure and Performance[J]. Construction and Building Materials, 2020, 255: 119 381.
|
| [2] |
Guo Y, Zhang Y, Soe K, et al.Recent Development in Magnesium Oxychloride Cement[J]. Structural Concrete, 2018, 19(5): 1 290-1 300.
|
| [3] |
Misra A K, Mathur RMagnesium Oxychloride Cement Concrete[J]. Bulletin of Materials Science, 2007, 30239-246.
|
| [4] |
Nobre J, Ahmed H, Bravo M, et al.Magnesia (MgO) Production and Characterization, and Its Influence on the Performance of Cementitious Materials: A Review[J]. Materials, 2020, 13(21): 4 752.
|
| [5] |
Singh A, Kumar R, Goel PFactors Influencing Strength of Magnesium Oxychloride Cement[J]. Construction and Building Materials, 2021, 303: 124 571.
|
| [6] |
Ahmad F, Rawat S, Zhang YMagnesium Oxychloride Cement: Development, Opportunities and Challenges[J]. Applied Sciences, 2024, 14(7):3 074.
|
| [7] |
Qing H, Wei xin Z, Xue ying X, et al.A Study on the Salt Attack Performance of Magnesium Oxychloride Cement in Different Salt Environments[J]. Construction and Building Materials, 2022, 320126 224.
|
| [8] |
Wu J, Chen F, Wang H, et al.Influence of Biomass Bottom Ash and Tannic Acid on Properties of Magnesium Oxychloride Cement[J]. Construction and Building Materials, 2025, 463140 090.
|
| [9] |
Sun X, Zhou W, Ye Q, et al.A Green Magnesium Oxychloride Cement Based Adhesive Synergistically Reinforced by Citric Acid and Polyvinyl Alcohol Fibers for Wood[J]. Construction and Building Materials, 2024, 426136 041.
|
| [10] |
Han Y, Kong XBiomimetic Organic-Inorganic Hybrid Magnesium Oxychloride Cement as Green Adhesive for Wood Industry[C]. 16th International Conference on Durability of Building Materials and Components, 2023100.
|
| [11] |
Zhou W, Ye Q, Shi S Q, et al.A Strong Magnesium Oxychloride Cement Wood Adhesive via Organic-Inorganic Hybrid[J]. Construction and Building Materials, 2021, 297123 776.
|
| [12] |
Han Y, Zhou W, Sun X, et al.Mussel-Inspired Magnesium Oxychloride Cement-Based Wood Adhesive Produced via the Synergy of Inorganic Fiber Enhancement and Multiple Reinforcement Network[J]. Construction and Building Materials, 2024, 439137 391.
|
| [13] |
Tanguler-Bayramtan M, Alam B, Sucu M, et al.Cement and Hydroxyethyl Methyl Cellulose Interaction: The Performance of Cement-Based Adhesives[J]. Materials and Structures, 2022, 55(3):91.
|
| [14] |
Wang R, Qin L, Gao XMechanical Strength and Water Resistance of Magnesium Oxysulfate Cement Based Lightweight Materials[J]. Cement and Concrete Composites, 2020, 109103 554.
|
| [15] |
Guo Y, Zhang Y X, Soe KEffect of Sodium Monofluorophosphate and Phosphates on Mechanical Properties and Water Resistance of Magnesium Oxychloride Cement[J]. Cement and Concrete Composites, 2022, 129104 472.
|
| [16] |
Mahesh BMachine Learning Algorithms-A Review[J]. International Journal of Science and Research (IJSR), 2020, 9(1):381-386.
|
| [17] |
Liu L, Wang L Y, Wang H, et al.RF Optimizer Model for Predicting Compressive Strength of Recycled Concrete[J]. Journal of Wuhan University of Technology-Mater. Sci. Ed., 2025, 40(1): 215-223.
|
| [18] |
Huang J, Sun Y, Zhang J. Reduction of Computational Error by Optimizing SVR Kernel Coefficients to Simulate Concrete Compressive Strength through the Use of a Human Learning Optimization Algorithm[J]. Engineering with Computers, 2022: 1–18
|
| [19] |
Shi Y, Li J, Zhang Y, et al.Interpretable Machine Learning Method for Compressive Strength Prediction and Analysis of Pure Fly Ash-Based Geopolymer Concrete[J]. Journal of Wuhan University of Technology-Mater. Sci. Ed., 2025, 40(1): 65-78.
|
| [20] |
Kumar P S, Puja RExperimental Investigation and SVR Model to Predict the Mechanical Properties of RAC by Enhancing the Characteristic of RCA Using Surface Treatment Method along with Modified Mixing Approach[J]. Construction and Building Materials, 2023, 393132 032.
|
| [21] |
Luo X, Li Y, Liu Y, et al.Research on the Prediction of Mechanical Properties of Magnesium-Silicon-Based Cement and the Mechanism of Element Interaction Based on Machine Learning[J]. Construction and Building Materials, 2025, 463140 062.
|
| [22] |
Fan C C, Zheng Y X, Shaoqiang W, et al.Prediction of Bond Strength of Reinforced Concrete Structures Based on Feature Selection and GWO-SVR Model[J]. Construction and Building Materials, 2023, 400132 602.
|
| [23] |
Zhao G, Pan X, Yan H, et al.Predicting Engineering Properties of Controlled Low-Strength Material Made from Waste Soil Using Optimized SVR Models[J]. Case Studies in Construction Materials, 2024, 20e03 325.
|
| [24] |
Owusu-Danquah J S, Bseiso A, Allena S, et al.Artificial Neural Network Algorithms to Predict the Bond Strength of Reinforced Concrete: Coupled Effect of Corrosion, Concrete Cover, and Compressive Strength[J]. Construction and Building Materials, 2022, 350128 896.
|
| [25] |
Ministry of Construction of the People’s Republic of ChinaStandard for Technical Requirements and Test Method of Sand and Crushed Stone (or Gravel) for Ordinary Concrete, 2006JGJ 52-2006
|
| [26] |
Standardization Administration of ChinaStandard for Test Methods of Long-Term Performance and Durability of Ordinary Concrete, 2009GB/T 50082-2009
|
| [27] |
Ileberi E, Sun Y, Wang ZA Machine Learning Based Credit Card Fraud Detection Using the GA Algorithm for Feature Selection[J]. Journal of Big Data, 2022, 9(1): 24.
|
| [28] |
Scrucca LGA: A Package for Genetic Algorithms in R[J]. Journal of Statistical Software, 2013, 531-37.
|
| [29] |
Chatterjee S, Laudato M, Lynch L AGenetic Algorithms and Their Statistical Applications: An Introduction[J]. Computational Statistics & Data Analysis, 1996, 22(6): 633-651.
|
| [30] |
Zhang F, O’Donnell L JSupport Vector Regression. Machine Learning, 2020, London: Academic Press, 123-140.
|
| [31] |
Du K, Liu M, Zhou J, et al.Investigating the Slurry Fluidity and Strength Characteristics of Cemented Backfill and Strength Prediction Models by Developing Hybrid GA-SVR and PSO-SVR[J]. Mining, Metallurgy & Exploration, 2022, 39(2): 433-452.
|
| [32] |
Sun Y, Ding S, Zhang Z, et al.An Improved Grid Search Algorithm to Optimize SVR for Prediction[J]. Soft Computing, 2021, 25: 5 633-5 644.
|
| [33] |
Rainio O, Teuho J, Klén REvaluation Metrics and Statistical Tests for Machine Learning[J]. Scientific Reports, 2024, 14(1): 6 086.
|
| [34] |
Miller C, Portlock T, Nyaga D M, et al.A Review of Model Evaluation Metrics for Machine Learning in Genetics and Genomics[J]. Frontiers in Bioinformatics, 2024, 41 457 619.
|
| [35] |
Khalil N Z, Kong N, Fricke HThe Influence of GNP on the Mechanical and Thermomechanical Properties of Epoxy Adhesive: Pearson Correlation Matrix and Heatmap Application in Data Interpretation[J]. Polymer Composites, 2024, 45(10):8 997-9 018.
|
| [36] |
Wang H, Liang Q, Hancock J T, et al.Feature Selection Strategies: A Comparative Analysis of SHAP-Value and Importance-Based Methods [J]. Journal of Big Data, 2024, 11(1):44.
|
| [37] |
Mangalathu S, Hwang S H, Jeon J SFailure Mode and Effects Analysis of RC Members Based on Machine-Learning-Based SHapley Additive exPlanations (SHAP) Approach[J]. Engineering Structures, 2020, 19110 927.
|
Rights & permissions
Wuhan University of Technology and Springer-Verlag GmbH Germany, Part of Springer Nature
PDF
