CAJ | 학술논문

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.
제출응용유전규화이론(GP)대고성능혼응토담락도진행예측.침대영향고성능혼응토담락도적주요인소작위수입인자,담락도치작위수출변량,응용개진적유전규화방법모의출수입-수출이자인과관계적현식수학해석식,건립료고성능혼응토담락도예측적비선성수학모형.통과실측수거진행험증분석,병분별여선성회귀화신경망락모형비교,표명GP모형구유경호적의합정도화예측효과,위담락도예측제공료신적방법.
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.