基于数理统计多元回归模型的拱坝水平位移影响因素分析

Analysis of influencing factors of horizontal displacement of arch dam based on mathematical statistics multiple regression model

为了从海量大坝安全监测数据中揭示大坝变形行为与其影响因素之间的数理统计规律,建立了大坝水平位移多元回归统计模型,并采用最小二乘法获取了统计模型的参数估计值。结果表明:模型计算值与实测值吻合较好,复相关系数较大,剩余均方差较小;所建立的基于最小二乘参数估计数理统计多元回归的分析模型能够有效解释水压分量、温度分量和时效分量对水平位移的影响,为评价大坝运行性态和预测大坝水平位移发展规律提供了有效的分析手段和途径。

In order to reveal the mathematical statistical law between the dam deformation behavior and its influencing factors behind the randomness from the massive dam safety monitoring data,a multiple regression statistical model of dam horizontal displacement was established,and the estimated parameters of the statistical model were obtained by the least square method. The results showed that the calculated values of the model were in good agreement with the measured values,the multiple correlation coefficient was large,and the residual mean square deviation was small. The established mathematical statistics multiple regression analysis model based on least square parameter estimation could effectively explain the influence of water pressure component,temperature component and time effect component on horizontal displacement,and provide effective analysis means and ways for evaluating dam operation performance and predicting dam horizontal displacement development law.