基于支持向量机的有机成膜涂层混凝土碳化深度预测模型

Carbonization Depth Prediction Model of Organic Film-forming Coating Concrete Based on Support Vector Machine

为研究有机成膜涂层混凝土碳化深度与其影响因素之间的高维非线性问题,采用以水灰比、用水量、水泥用量、涂层类别、老化时间、温度、相对湿度为影响因素进行的有机成膜涂层混凝土碳化试验测得的数据,运用支持向量机算法建立涂层混凝土碳化深度预测模型,将试验值与预测值对比,结果表明,该模型有较好的预测精度。并将预测结果与传统的BP神经网络预测模型对比,结果显示,支持向量机预测模型的误差更小,回归拟合效果更佳,可应用于有机成膜涂层混凝土碳化深度的预测。在此基础上,对影响因素进行敏感性分析,计算影响因素变化率与涂层混凝土碳化深度变化率之间的定量关系,从而找出影响因素敏感性程度排序,为有效防护涂层混凝土碳化提供一定参考。

In order to study the high-dimensional non-linear relationship between the carbonization depth of organic film-forming coating concrete and its influence factors,the carbonization depth prediction model of coating concrete is established by using support vector machine algorithm based on the experimental data of carbonation of coating concrete with water cement ratio,water consumption,cement consumption,coating category,aging time,temperature and relative humidity.Comparing the predicted value with the experimental value,it shows the model has better prediction accuracy.Comparing the prediction results with the prediction results of traditional BP neural network prediction model,the results show that the error of the support vector machine prediction model is smaller,and the regression fitting is better.It can be concluded that the model can be applied to predict the carbonation depth of organic filmforming coating concrete.On this basis,sensitivity analysis of the influence factors is conducted,and the quantitative relationship between the change rate of the influence factors and change rate of carbonization depth of coated concrete is calculated,based on which,the sensitivity ranking of influencing factors is found out.It provides some references for effectively preventing the carbonation of coating concrete.