Kalman Filter Model Based on AR(n) Model
Fumin Lu · Shuxue de shijian yu renshi · 2007
Considering deformation monitor points in different places,influence of all kinds of environmental factors is different,the author preset some AR(n) model,by means of calculation, AR(n) model whose residual standard deviation is small is chosen as the primary model,parameters of the primary model are looked as the status vector with dynamic noises to build Kalman Filter Model.The example verifes that the method can raise the fitting and forecast accuracy of the model.