基于SVM的钢纤维再生混凝土配合比优化  

Mix Proportion Optimization of Steel Fiber Recycled Concrete Based on SVM

作　　者：马骁含 徐超 Ma Xiaohan;Xu Chao

机构地区：[1]沈阳工业大学建筑与土木工程学院,辽宁沈阳110870

出　　处：《重庆建筑》2023年第10期61-64,共4页Chongqing Architecture

摘　　要：基于支持向量机(SVM)模型对钢纤维再生混凝土立方体的抗压强度进行了预测,得到了其与原材料配合比之间的非线性关系函数。将这个函数作为目标适应度函数,同时引入经济成本作为另一个目标适应度函数,依据规范和工程具体要求,建立了原材料配合比的相关约束条件,利用遗传算法进行了求解,实现了抗压强度和造价两目标优化,得出了最佳配合比集。结果表明:采用SVM模型预测混凝土立方体抗压强度的精度很高,相对误差在6%以内,并利用遗传算法求出了抗压强度和造价的Pareto最优解集。Based on the support vector machine(SVM)model,the compressive strength of steel fiber recycled concrete cubes was predicted,yielding the nonlinear relationship function between the mix ratio of raw materials and the strength.This function was used as the objective fitness function,with the economic cost introduced as another one,and according to the specifications and specific requirements of the project,relevant constraints of the mix ratio of raw materials were established,while the genetic algorithm was.used to solve the problem,realizing the two-objective optimization of compressive strength and cost and obtaining the optimal mix ratio set.The results showed that the SVM model has high accuracy in predicting the compressive strength of concrete cubes,with the relative error within 6%.The Pareto optimal solution set of the compressive strength and cost was also obtained by genetic algorithm.

关 键 词：支持向量机 多目标配合比优化 抗压强度 再生混凝土 

分 类 号：TU528[建筑科学—建筑技术科学]