【摘要】 变形序列一般可以分解为趋势项、周期项和随机项,因此在运用线性回归理论拟合序列时就要考虑是同时求解两者的参数还是分步求解参数,这样就产生了两种拟合方法。本文讨论了这两种拟合方法的参数求解方法,二者的根本区别在于统一求解参数仅使用一次最小二乘法,而分别求解趋势项和周期项参数要运用两次最小二乘法。通过工程实例,讨论并比较了这两种拟合方法的特点,可为类似工程提供参考。更多还原

【Abstract】 The deformation sequence can be decomposed into trend term,periodic term and random term,so it is necessary to consider whether to solve both parameters simultaneously or step by step when using linear regression theory to fit the sequence,thus two fitting methods are produced.This paper first discusses the parameter solving methods of the two fitting methods.The fundamental difference between the two methods is that only one least square method is used to solve the parameters uniformly,while the two least square methods are used to solve the parameters of trend term and period term respectively.Secondly,the characteristics of the two fitting methods are discussed and compared through an engineering example,which can provide a useful reference for similar projects.更多还原