混凝土钢筋锈蚀量预测的投影寻踪回归模型

Projection pursuit regression model for predict corrosive degree of concrete embeded rebar

造成钢筋锈蚀量预测值与实测值误差较大的原因在于以下两个方面:其一,由于混凝土开裂后钢筋锈蚀程度的离散性较大;其二,混凝土中的钢筋锈蚀机理非常复杂,影响因素繁多。为解决以上问题,将投影寻踪回归方法应用于锈蚀开裂后混凝土中钢筋锈蚀量的评估,建立了评估钢筋锈蚀量的投影寻踪回归模型,并通过实际工程检测结果验证了该方法的实际可行性,为钢筋锈蚀量的预测提供了一条新的方法。

There two difficult problems for assessing corrosive degree of concrete embeded rebar after corrosion crack：firstly,degree of concrete is large dispersion;secondly,it was influenced by the many uncertainties,and the mechanism of steel corrosion in concrete is very complex.After the main factors affecting,the corrosive degree of rebar is analyzed,a new model was established.The adaption of the model is discussed from the angles of projection pursuit regression model.The feasibility is verified according to the data from practical engineering investigation.It provides a new way to predict corrosive degree of concrete embeded rebar after corrosion crack.