基于多项式回归分析的核电站汽轮机基础沉降预测方法

Settlement Prediction Method for Turbine Foundation in Nuclear Power Station Based on Polynomial Regression Analysis

基于5阶多项式回归分析法建立汽机平台沉降预测模型,并应用该模型对岭澳二期核电厂汽轮机平台沉降监测数据进行了预测,结果表明,最大预测相对误差为10%,平均相对误差为4.7%,具有较好的实用性。

Based on five order polynomial regression, the prediction model was used to predict the subsidence of turbines plant. The results showed that the maximum relative error was 10% and the average relative error was 4.7%, indicating that this method was of good performance.