基于正则化RBF神经网络的混凝土强度预测  

Prediction of concrete strength based on regular RBF neural network

作　　者：李钢[1] 吕国芳[1] 

机构地区：[1]河海大学能源与电气学院,江苏南京211100

出　　处：《电子设计工程》2014年第13期52-54,57,共4页Electronic Design Engineering

摘　　要：针对目前混凝土28天强度值的预测需时长、精度低的现状,建立了基于正则化RBF神经网络的混凝土强度预测模型,并运用MATLAB 7.13进行仿真实验。实验结果表明该模型综合考虑了影响混凝土强度的各种因素,能够实现非线性关系,具有较高的预测精度,并且训练速度快,可以节约大量的时间、人力、物力和财力,在混凝土强度预测领域具有广泛的应用前景。According to the current situation that forecasting the 28--day concrete strength is too long and in low accuracy, it has built the prediction model of concrete strength based on regular RBF neural network and has carried out the simulated experiment by MATLAB 7.13. The experimental results show that it considers various factors affecting the concrete strength, can realize nonlinear relations, has high precision of prediction and the training speed is fast. It can also save a lot of time, manpower, material and financial resources, has broad application prospects in the field of concrete strength prediction.

关 键 词：神经网络 混凝土强度 预测 仿真 

分 类 号：TN06[电子电信—物理电子学]