高性能混凝土坍落度预测的遗传规划方法  

Application of genetic programming in slump prediction of high performance concrete

作　　者：宋玲玲[1] 赵胜利[1] 李泉辉[2] 张东原[3] 

机构地区：[1]河北农业大学城乡建设学院,河北保定071001 [2]河北农业大学机电学院,河北保定071001 [3]河北建设集团混凝土分公司,河北保定071000

出　　处：《河北农业大学学报》2010年第2期114-118,共5页Journal of Hebei Agricultural University

基　　金：河北省科技支撑计划(06547004D-7);河北农业大学非生命基金(FSY200711)

摘　　要：提出应用遗传规划理论(GP)对高性能混凝土坍落度进行预测。针对影响高性能混凝土坍落度的主要因素作为输入因子,坍落度值作为输出变量,应用改进的遗传规划方法模拟出输入-输出二者因果关系的显式数学解析式,建立了高性能混凝土坍落度预测的非线性数学模型。通过实测数据进行验证分析,并分别与线性回归和神经网络模型比较,表明GP模型具有更好的拟合精度和预测效果,为坍落度预测提供了新的方法。This study applies the genetic programming（GP） theory to predict the slump of high performance concrete.The main factors that influence the slump of high performance concrete are considered as input variables and the slump value is seen as output variable of the GP model respectively.A visible function expression that contains the complex relationship between input variables and output variable is given by applying the method of improved GP and thus a nonlinear mathematical model of high performance concrete slump is built.The performance of the proposed GP model is analysed and the result is compared with that of the linear regression and BP neural network model which show that the GP model has higher fitting precision with the experiment data and better prediction effect.Thus,this new method can be used to predict the slump of high performance concrete.

关 键 词：遗传规划 高性能混凝土 坍落度 预测 

分 类 号：TU528[建筑科学—建筑技术科学] TP18[自动化与计算机技术—控制理论与控制工程]