基于BP神经网络模型的纤维编织网增强自应力混凝土膨胀量预测方法

Prediction method for expansion of textile reinforced self-stressing concrete based on BP neutral network theory

为预测纤维编织网增强自应力混凝土的膨胀量,基于BP神经网络建立模型,模拟其膨胀量与纤维编织网Tex含量、养护龄期之间的关系。通过48块纤维编织网增强自应力混凝土试件验证模型的准确性及适用性,BP神经网络预测结果与试验数据之间的误差小于1.78%,两者吻合较好,为定量描述纤维编织网增强自应力混凝土膨胀量提供一种新的方法。

Based on the basic theory of BP neutral network,the effects of Tex content of textile and curing time on the expansion of textile reinforced self-stressing concrete were simulated.It is proved to be a rather suitable and accurate model via 48 specimens.Through the comparison of experimental data and BP neural network prediction results,the value of the error is less than 1.78%.This method provides a new way to quantitatively describe the expansion of textile reinforced self-stressing concrete.