【摘要】 如何对建(构)物进行变形监测和趋势预测?针对这一问题,测绘技术人员研究了多种预测模型,但由于造成建(构)物变形的原因比较复杂,故各种预测模型都有各自的优势和不足。本文经过对大量的变形监测数据进行多元回归分析研究,且通过变形数据的内因和外因之间的相关性,建立变形关系的数学模型。当处理两个变量之间关系时,可采用一元回归分析。当处理一个变量与多个因子之间的关系时,应采用多元回归分析。并通过在回归方程中逐个引入显著因子,剔除不显著因子,获得最佳回归方程(预报方程),本方法在实际应用中预测效果显著。更多还原

【Abstract】 How to do deformation monitoring and prediction for structure? Surveying and mapping engineers have developed many prediction models.Due to the complexity of structure deformation causes,different forecasting models have their own advantages and disadvantages respectively.In this paper the mathematical model of deformation relation is established through multiple linear regression analysis on deformation monitoring data,and the correlation between the internal and external factors of deformation data.The author uses simple regression analysis for the relationship between two variables.When handling the relationship between a variable and a number of factors,multiple regression analysis should be used.By introducing significant factor into regression equation and excluding insignificant factor,the best regression equation is established.The method has achieved good prediction results in practical application.更多还原