Cutting-Edge Hybrid Machine Learning Models for Forecasting the Acid Resistance of Cementitious Composites Incorporating Eggshell and Glass Powders

This research introduced advanced hybrid machine learning (ML) techniques to create an efficient model for estimating the compressive strength after acid attack (CSAA). The models were developed based on mixtures containing eggshell powder (ESP) and glass powder (GP). Support vector regression (SVR) was integrated with sophisticated metaheuristic optimization techniques, namely the particle swarm optimization (PSO), firefly algorithm (FFA), and gray wolf optimization (GWO), to develop advanced forecasting models for the CSAA of cementitious composites. Additionally, conventional ML models, including random forest (RF) and decision tree (DT), were utilized for comparison. All three hybrid models demonstrated strong predictive capabilities, with SVR-PSO proving to be the most reliable method, attaining the maximum coefficient of determination (R2) score of 0.984, surpassing SVR-GWO (0.981) and SVR-FFA (0.980). In contrast, the RF model recorded an R2 value of 0.974, while the DT model revealed a significantly reduced R2 of 0.649. The partial dependence analyses and SHapley Additive exPlanations and partial dependence plots analyses highlighted the substantial impact of various parameters, revealing that compressive strength (CS) was the most influential factor, followed by GP and ESP. CS and GP had positive effects, while ESP negatively impacted CSAA. A user-friendly interface was developed to efficiently predict CSAA.

Development of hybrid ML models for predicting CSAA in cementitious composites with ESP and GP.
SVR-PSO achieved the highest accuracy (R2 = 0.984), outperforming SVR-GWO (R2 = 0.981) and SVR-FFA (R2 = 0.980).
SHAP and partial dependence plots identified CS as the most influential factor, with GP having a positive and ESP a negative effect on CSAA.
A user-friendly GUI was developed for rapid prediction.

Development of hybrid ML models for predicting CSAA in cementitious composites with ESP and GP.
SVR-PSO achieved the highest accuracy (R2 = 0.984), outperforming SVR-GWO (R2 = 0.981) and SVR-FFA (R2 = 0.980).
SHAP and partial dependence plots identified CS as the most influential factor, with GP having a positive and ESP a negative effect on CSAA.
A user-friendly GUI was developed for rapid prediction.

本研究引入先进的混合机器学习（hybrid machine learning, ML）技术，以构建用于预测酸蚀后抗压强度（compressive strength after acid attack, CSAA）的高效模型。所开发的模型以添加蛋壳粉（eggshell powder, ESP）与玻璃粉（glass powder, GP）的胶凝复合材料为研究体系。将支持向量回归（support vector regression, SVR）与三类先进的元启发式优化技术——粒子群优化（particle swarm optimization, PSO）、萤火虫算法（firefly algorithm, FFA）及灰狼优化（gray wolf optimization, GWO）——相融合，构建用于预测胶凝复合材料CSAA的先进预测模型。此外，本研究还采用了常规机器学习模型，包括随机森林（random forest, RF）与决策树（decision tree, DT），用于对照分析。三款混合模型均展现出优异的预测性能，其中SVR-PSO的可靠性最优，其决定系数（coefficient of determination, R²）最高可达0.984，优于SVR-GWO（0.981）与SVR-FFA（0.980）。与之相对，随机森林模型的R²值为0.974，而决策树模型的R²值仅为0.649，性能大幅下滑。部分依赖分析与夏普利可加解释（SHapley Additive exPlanations, SHAP）及部分依赖图分析揭示了各参数的显著影响：抗压强度（compressive strength, CS）为最具影响力的因素，其次为GP与ESP。CS与GP对CSAA具有正向影响，而ESP则对CSAA产生负向影响。本研究还开发了一款易用的交互界面，可高效实现CSAA的预测。

构建基于ESP与GP的胶凝复合材料CSAA预测的混合机器学习模型。
SVR-PSO的预测精度最高（决定系数R²=0.984），优于SVR-GWO（R²=0.981）与SVR-FFA（R²=0.980）。
夏普利可加解释（SHAP）与部分依赖图分析表明，CS为最具影响力的参数，其中GP对CSAA具有正向影响，ESP则产生负向影响。
本研究开发了一款易用的图形用户界面（GUI），可实现CSAA的快速预测。

构建基于ESP与GP的胶凝复合材料CSAA预测的混合机器学习模型。
SVR-PSO的预测精度最高（决定系数R²=0.984），优于SVR-GWO（R²=0.981）与SVR-FFA（R²=0.980）。
夏普利可加解释（SHAP）与部分依赖图分析表明，CS为最具影响力的参数，其中GP对CSAA具有正向影响，ESP则产生负向影响。
本研究开发了一款易用的图形用户界面（GUI），可实现CSAA的快速预测。