基于FLR和ANFIS方法预测混凝土抗压强度研究  

Comparison study of predicting concrete compressive strength by FLR and ANFIS method

作　　者：林军 杨斌[1] 陈雁萍 LIN Jun;YANG Bin;CHEN Yanping(School of Architecture and Civil Engineering,Jiangsu Open University,Nanjing 211816,China;School of Transportation Engineering,Nanjing Tech University,Nanjing 211816,China)

机构地区：[1]江苏开放大学建筑工程学院,江苏南京211816 [2]南京工业大学交通运输工程学院,江苏南京211816

出　　处：《混凝土》2022年第5期11-15,共5页Concrete

基　　金：江苏省“双创博士”计划项目(202030537);江苏省高等学校自然科学研究面上项目(19KJB560011)。

摘　　要：由于水泥基材料的复杂特性,混凝土抗压强度影响因素众多,准确预测混凝土抗压强度是非常困难的。采用模糊线性回归(FLR)和自适应神经模糊推理系统(ANFIS)方法,以硅酸三钙,石膏类材料,比表面积和碱含量为预测模型变量,对混凝土抗压强度进行预测。研究结果表明,FLR方法的平均百分比误差水平最高,但其通过使用对称三角模糊数字来估计输出值,并确定了硅酸三钙是增加混凝土抗压强度的最重要因素。ANFIS方法成功地降低了预测水泥强度的不确定性水平,但是ANFIS是黑箱模型,预测数据缺乏可解释性。Accurate prediction of concrete compressive strength is very difficult due to the complex characteristics of cementitious materials and the various factors affecting the compressive strength of concrete.Fuzzy linear regression(FLR)and adaptive neuro-fuzzy inference system(ANFIS) methods were used to predict the compressive strength of concrete using tricalcium silicate,gypsum-like materials,specific surface area and alkali content as predictive model variables.The results showed that the FLR method had the highest mean percentage error level,but it estimated the output values by using symmetric triangular fuzzy numbers and identified tricalcium silicate as the most important factor in increasing the compressive strength.The ANFIS method successfully reduced the level of uncertainty in predicting cement strength,but ANFIS is a black box model and the predicted data lacked interpretability.

关 键 词：混凝土 抗压强度 模糊线性回归 自适应神经模糊系统 

分 类 号：TU528.01[建筑科学—建筑技术科学]