基于人工神经网络和遗传算法的砖混再生粗骨料混凝土配合比优化设计  

Optimal design of the mix ratio of brick-concrete recycled coarse aggregate concrete based on artificial neural network and genetic algorithm

作　　者：李战国[1] 张浩[1] 李洪文 李悦[1] 金彩云[2] LI Zhanguo;ZHANG Hao;LI Hongwen;LI Yue;JIN Caiyun(The Key Laboratory of Urban Security and Disaster Engineering,MOE,Beijing Key Lab of Earthquake Engineering and Structural Retrofit,Beijing University of Technology,Beijing 100124,China;Department of Science,Beijing University of Technology,Beijing 100124,China)

机构地区：[1]北京工业大学城市与工程安全减灾教育部重点实验室,北京100124 [2]北京工业大学理学部,北京100124

出　　处：《混凝土》2023年第10期1-6,11,共7页Concrete

基　　金：国家自然科学基金(51808015)“基于遗传算法的泵送高强抗裂混凝土优化设计及其流动性数值分析”;建筑垃圾资源化利用综合技术研究开发项目(2020-K-079)。

摘　　要：基于抗压强度试验、人工神经网络(ANN)和遗传算法(GA)提出了一种砖混再生粗骨料混凝土的配合比优化设计方法。首先对36组不同配合比的砖混再生粗骨料混凝土进行抗压强度试验,在此基础上建立了ANN模型用于预测混凝土抗压强度,结果表明抗压强度的预测值接近试验值。基于上述研究结果,建立了砖混再生粗骨料混凝土抗压强度与配合比的函数关系。最后,以砖混再生粗骨料混凝土的最佳性价比为目标,利用遗传算法优化了砖混再生粗骨料混凝土常见强度等级的配合比。Based on compressive strength test,artificial neural network(ANN)and genetic algorithm(GA),a mix proportion optimization design method for brick-concrete recycled coarse aggregate concrete was proposed.Firstly,the compressive strength tests of 36 groups of brick-concrete recycled coarse aggregate concrete with different mix proportions were carried out.On this basis,the ANN model was established to predict the compressive strength of concrete.The results show that the predicted compressive strength is close to the experimental value.Based on the above research results,the functional relationship between compressive strength and mix ratio of recycled coarse aggregate concrete is established.Finally,aiming at the best performance-price ratio of recycled coarse aggregate concrete,genetic algorithm is used to optimize the mix proportion of common strength grades of recycled coarse aggregate concrete.

关 键 词：砖混再生混凝土 人工神经网络 遗传算法 配合比优化设计 

分 类 号：TU528.01[建筑科学—建筑技术科学]