基于人工神经网络的再生混凝土抗压强度预测

Prediction of Compressive Strength of Recycled Aggregate Concrete Based on Artificial Neural Network

针对掺入的再生骨料影响混凝土材料的抗压强度问题建立了实验数据库,利用多元线性回归及人工神经网络技术分别构建了再生混凝土抗压强度预测模型,并将预测模型的拟合结果与传统经验回归模型的拟合结果进行了对比。结果表明,人工神经网络模型具有较高的精度和拟合效果,对不可见的数据具有更好的泛化能力。研究结果可以为工程实践提供理论和技术支持。

Aiming at the influence of recycled aggregates on the compressive strength of concrete materials, an experimental database was established, and multiple linear regression and artificial neural network techniques were used to construct the compressive strength prediction models of recycled concrete respectively. The fitting results of the prediction model are compared with those of the traditional empirical regression model. The results show that the artificial neural network model has high accuracy and fitting effect, and the comprehensive performance of the artificial neural network model is the best. Through the verification of test data, it can be found that the artificial neural network model has better generalization ability to invisible data. The research results can provide theoretical and technical support for engineering practice.