基于GA-BP神经网络的再生保温混凝土强度预测

Prediction of recycled aggregate thermal insulation concrete strength based on GA-BP neural network

为更准确地预测再生保温混凝土28 d的抗压强度,在Matlab2014a平台上通过遗传算法对BP神经网络的初始权值及阈值进行改进,建立了基于BP神经网络和遗传算法的再生保温混凝土28 d抗压强度预测模型,并采用试验数据作为训练样本和预测样本对GA-BP神经网络及BP神经网络预测模型的性能进行了比较。结果表明:与BP神经网络相比,GA-BP神经网络预测的相对误差较小且相对误差的变化较稳定。

In order to predict the 28 days compressive strength of recycled thermal insulation concrete more accurately,the initial weights and thresholds of BP neural network are improved by genetic algorithm on Matlab 2014 a platform.A prediction model of 28 days compressive strength of recycled thermal insulation concrete based on BP neural network and genetic algorithm is established.The GA-BP neural network and BP neural network are trained and predicted by using experimental data as training samples and prediction samples.The performance of the prediction model is compared.The results show that compared with BP neural network,the relative error of GA-BP neural network prediction is smaller and the change of relative error is more stable.