基于响应面法和遗传算法的混凝土配合比多目标优化设计

Multi-Objective Optimization Design of Concrete Mix Proportion Based on Response Surface Method and Genetic Algorithm

摘要:

为实现多目标优化混凝土配合比设计，本文通过单因素试验确定C40混凝土中矿粉掺量、粉煤灰掺量和水胶比的最佳掺量范围，采用响应面法构建二次多项式回归方程，系统研究不同矿粉掺量、粉煤灰掺量及水胶比对混凝土坍落度和抗压强度的影响规律，并进一步应用NSGA-II算法并结合TOPSIS综合评价法实现混凝土配合比多目标优化。结果表明，通过响应面法建立的回归模型的相关系数R2分别为0.9447和0.9604，预测精度良好。粉煤灰掺量对坍落度的影响显著，而抗压强度主要受水胶比影响。优化后得到最佳配合比方案: 矿粉掺量为8.66%，粉煤灰掺量为25%，水胶比为0.34，试验验证预测值与试验值之间的相对误差小于5%。本研究为混凝土配合比的优化设计提供了理论依据和参考。

Abstract:

To realize the multi-objective performance of concrete proportion design, this study employed single-factor experiments to establish the optimal ranges for slag content, fly ash content, and water/binder ratio in C40 ready-mixed concrete. Using the response surface methodology, quadratic regression models were developed to systematically analyze how these three factors influence concrete slump and compressive strength. The NSGA-II algorithm was further applied in combination with TOPSIS comprehensive evaluation method to achieve multi-objective optimization of the mix proportion. The results demonstrated that the regression model established by response surface method has high accuracy and reliability, with correlation coefficients R2 of 0.9447 and 0.9604. The influence of fly ash content on slump was significant, while the influence of water/binder ratio on compressive strength was significant. The optimal mix proportion was obtained after optimization: slag content of 8.66%, fly ash content of 25%, and water/binder ratio of 0.34. Experimental verification showed that the relative error between predicted and measured values was less than 5%. This study provides a theoretical basis and reference for the optimal design of concrete proportion.