论文部分内容阅读
用灰色线性回归组合模型对建筑物变形数据的拟合和预测的残差平方和要比只用灰色模型拟合的平方和小得多,可见该模型的拟合精度大大优于原始灰色模型。灰色模型可以用来进行短期预测,并且具有所需原始信息量少、计算简单及预测精度较高等优点,而线性回归模型是传统的统计分析模型,它则需要大量的原始数据进行分析才能达到一定的精度。本文利用灰色模型和线性回归模型相结合对形变监测数据进行建模、分析和预测,并和仅用灰色模型对数据分析的结果进行比较,结果验证了该组合模型具有更高的精度,是一种可行有效的变形数据分析模型。
The sum of squared residuals of fitting and prediction of building deformation data with gray linear regression model is much less than the sum of squares of gray model fitting. It can be seen that the fitting accuracy of this model is much better than that of the original gray model. The gray model can be used for short-term prediction, and has the advantages of less original information, simple calculation and high prediction accuracy. However, the linear regression model is a traditional statistical analysis model, which requires a large amount of raw data to analyze in order to achieve certainty The accuracy. In this paper, the combination of gray model and linear regression model is used to model, analyze and forecast the deformation monitoring data. Compared with the gray model, the result of the data analysis shows that the model is more accurate A feasible and effective deformation data analysis model.