丢失数据下的条件极大似然辨识-控制与决策.pdf

绗?9 鍗 绗? 鏈 鎺 鍒 涓 鍐 绛 2014 骞 2 鏈 Vol. 29 No. 2 Control and Decision Feb. 2014 鏂囩珷缂栧彿: 1001-0920 (2014) 02-0358-05 DOI: 10.13195/j.kzyjc.2012.1546 涓㈠け鏁版嵁涓嬬殑鏉′欢鏋佸ぇ浼肩劧杈ㄨ瘑 鐜嬪缓瀹 (鏅痉闀囬櫠鐡峰闄㈡満姊扮數瀛愬伐绋嬪闄紝姹熻タ鏅痉闀?33403) 鎽 瑕? 閽堝浠垮皠缁撴瀯褰㈠紡鍦ㄤ涪澶辨暟鎹笅鐨勬潯浠舵瀬澶т技鐒惰鲸璇嗛棶棰? 棣栧厛寮曞叆浜ゆ崲鐭╅樀灏嗗師闅忔満鐭㈤噺鍒嗚В鎴愯娴嬪拰 涓㈠け閮ㄥ垎; 鐒跺悗纭畾鍑鸿娴嬫暟鎹湪涓㈠け鏁版嵁涓嬬殑鏉′欢鍧囧€煎拰鏉′欢鏂瑰樊, 浠ユ寤虹珛鏉′欢浼肩劧鍑芥暟; 杩涜€屼粠鐞嗚涓婄粰鍑轰簡 鏉′欢鏋佸ぇ浼肩劧鍑芥暟鍏充簬鏈煡鍙傛暟鐭㈤噺銆佹湭鐭ョ櫧鍣０鏂瑰樊鍊煎拰涓㈠け鏁版嵁鐨勬眰瀵煎叕寮? 骞朵粠宸ョ▼涓婄粰鍑轰竴绉嶅彲鍒嗙鐨勪紭 鍖栫畻娉旣 鏈€鍚庨€氳繃浠跨湡绠椾緥楠岃瘉浜嗚杈ㄨ瘑鏂规硶鐨勬湁鏁堟€? 鍏抽敭璇岤 鏉′欢鏋佸ぇ浼肩劧锛涗涪澶辨暟鎹紱浜ゆ崲鐭╅樀锛涗紭鍖栫畻娉 涓浘鍒嗙被鍙耳 TP273 鏂囩尞鏍囧織鐮? A Conditional maximum likelihood identi铿乧ation under missing data WANG Jian-hong (School of Mechanical and Electronic Engineering锛孞ingdezhen Ceramic Institute 锛孞ingdezhen 333403 锛孋hina. E-mail 锛歸angjianhong@nuaa.edu.cn) Abstract: To the conditional maximum likelihood identi铿乧ation problem of an af铿乶e structure under missing data, a permutation matrix is used to divide a random vector into observed and missing parts. Then conditional mean and covariance under missing data are set up to obtain a conditional likelihood function. In the theory, expressions of the derivatives about the conditional maximum likelihood function on the unknown parameter vector, unknown white noise variance and missing data are derived. A separable optimum algorithm is given to be applied in engineering. Finally, simulation results show the effectiveness of the identi铿乧ation method. Key words: conditional maximum likelihood 锛沵issing data 锛沺ermutation matrix 锛沷ptimum algorithm 0 寮曞紩寮 瑷€瑷€瑷€ 鏁版嵁涓庝涪澶辨暟鎹粨鍚堜綔涓洪殢鏈虹煝閲忓厓绱? 鑰屾湭鐭ュ弬鏁 鏁版嵁涓㈠け鏄伐涓氳繃绋嬩腑鏅亶瀛樺湪鐨勭幇璞? 鍗充娇鏌 鐭㈤噺鍒嗗埆瀛樺湪浜庡叾浠栫煩闃靛拰鐭㈤噺涓? 灏嗘湭鐭ュ