飞机颤振模态参数辨识的期望最大化.pdfVIP

35 , (, 210016) []; ;; [ ], ,, : , , , [] TP273 [] A [] 1001- 4926( 2010) 02- 0035- 06 The App lication of Expectation M axm ization A lgorithm in A ircraft F lutter M odel Param eter Iden tification WANG Jian- hong,WANG ao- bo (N anjing University of A eronautics and A stronautics, Nanjing, Jiangsu, 210016, China) K ey w ord s: parameter identification; EM algorithm; flutter; aircraft A bstract: The traditional least- squares identification method gives biased parameter estmi ateswhen the observed input- output data are corrupted by noises. A generalEM algorithm is adopted for aircraft fluttermodelparameter identification under the noisy environ ment. The EM algorithm is an iterative algorithm based on the stochastic state spacemodel. It is used to compute themax mi um value for the likelihood function that consists of two steps: namely the E- andM - steps. No calculation of the second order derivatives or approxmi ated values is needed. This algorithm can increase the likelihood function converging to a stationary point. Before applying the algorithm, the innovation variance criterion is used to estmi ate the system s order in order to decrease the complexity. Finally the efficiency of thismethod is illustrated w ith a smi ulation example. , , ,, , , [ 1] (726- 729) , , , , , , [] 2010- 05- 09 [] 2010- 05- 22 []王建宏( 1980- ) 男 , 南京航空航天大学自动化学院讲师, 博士主要研究方向: 系统辨识和凸 化 2010年 6月 飞机颤振模态参数辨识的期望最大化 36 第 24卷 第2期 , , , , , , [ 1] (726- 729)