有限元模型修正中的BAYES方法的几点讨论

Discussion on the Bayes Estimator Used in Finite Element Model Updating

ＢＡＹＥＳ方法是有限元模型动力修正中常用的方法。本文从不同的途径推导了该统计估算公式，并讨论了它的有效性、无偏性、学习能力、自适应性和鲁棒性，以及和最小二乘法、卡尔门滤波器等算法的一些不同之处。该方法可以作为一个多目标、多设计变量的优化方法。

The Bayesian estimator has been frequently used in finite element model updating.This paper presents the different derivations of the Bayesian estimator,and the discussion on its efficiency,unbiasedness,learning ability,adaptive nature,robustness,and the differences between this estimator and other estimators,for instance,least square method,Kalman filter.The Bayesian estimator can be used as a multiple objective,multiple design variable optimization method.An example is given to demonstrate its robustness under sensitivity matrix ill conditioned.