提出了一种基于残差的自适应多模型算法，其基本思想是通过残差的大小来分配多模型中单个模型在整体估计中的权重。
An adaptive multiple model algorithm based on residual is presented, its basic idea is to assign the probability of each model in overall estimation through the size of residual.
通过减变量残差图，不但可以容易地考察一个变量在模型中的作用，而且可以诊断样本点对模型和变量的影响大小。
It can not only be used to determine the importance of an explanatory variable in the regression model, but also to detect some cases with influence on the model and variables.
通过检测测量数据在残差子空间内的投影大小，可以检测系统是否出现故障。
Fault can be detected by detecting the projection of the measurement data in RS.
通过检测测量数据在残差子空间内的投影大小，可以检测系统是否出现故障。
Fault can be detected by detecting the projection of the measurement data in RS.
应用推荐