基于BP算法的IFPN参数优化方法.pdfVIP

绗?8 鍗 绗?2 鏈 鎺 鍒 涓 鍐 绛 2013 骞 12 鏈 Vol. 28 No. 12 Control and Decision Dec. 2013 鏂囩珷缂栧彿: 1001-0920 (2013) 12-1779-07 鍩轰簬BP 绠楁硶鐨処FPN 鍙傛暟浼樺寲鏂规硶 1,2 1 1 1 1 閮戝瘒鍏 , 闆疯嫳鏉 , 鐜 鐫 , 鐜 姣 , 鐢虫檽鍕 (1. 绌哄啗宸ョ▼澶у闃茬┖鍙嶅瀛﹂櫌锛岃タ瀹?10051 锛?. 涓浗浜烘皯瑙ｆ斁鍐?8331 閮ㄩ槦锛岄檿瑗垮崕闃?10042) 鎽 瑕? 閽堝鐩磋妯＄硦Petri 缃?IFPN) 妯″瀷鑷涔犺兘鍔涘樊鐨勭己闄? 灏嗙缁忕綉缁滀腑鐨凚P 璇樊鍙嶄紶绠楁硶寮曞叆IFPN 妯″瀷 鐨勫弬鏁板浼樿繃绋? 鎻愬嚭涓€绉嶅熀浜庢鐨勫弬鏁颁紭鍖栨柟娉? 璇ョ畻娉曢€氳繃寤虹珛鍙樿縼鐐圭噧鍜岀洿瑙夋ā绯婃帹鐞嗙殑杩戜技杩炵画鍑芥暟, 鎽嗚劚 浜嗗弬鏁板缁忛獙鐨勪緷璧? 鏇村姞绗﹀悎瀹為檯绯荤粺鐨勯渶姹? 鍚屾椂浣垮緱IFPN 鍏锋湁杈冨己鐨勬硾鍖栬兘鍔涘拰鑷€傚簲鍔熻兘, 鎺ㄧ悊缁撴灉鏇村姞 鍑嗙‘鍙俊. 鏈€鍚庨€氳繃鍏稿瀷瀹炰緥楠岃瘉浜嗚鍙傛暟浼樺寲鏂规硶鐨勬湁鏁堟€у拰浼樿秺鎬? 鍏抽敭璇岤 鐩磋妯＄硦闆嗭紱鐩磋妯＄硦Petri 缃戯紱浜х敓寮忚鍒欙紱BP 绠楁硶 涓浘鍒嗙被鍙耳 TP18 鏂囩尞鏍囧織鐮? A Method for parameters optimization of IFPN based on BP algorithm 1,2 1 1 1 1 ZHENG Kou-quan , LEI Ying-jie , WANG Rui , WANG Yi , SHEN Xiao-yong (1. Air Defense and Antimissile Institute锛孉ir Force Engineering University 锛孹i鈥檃n 710051 锛孋hina 锛?. Unit of 68331, PLA 锛孒uayin 710042 锛孋hina 锛嶤orrespondent 锛歓HENG Kou-quan 锛孍-mail 锛歾hengkouquan0421@163.com) Abstract 锛氾細锛欼n order to improve the self-learning capability of intuitionistic fuzzy Petri nets(IFPN), a novel parameters optimization method is proposed, in which the back propagation algorithm of neural net is introduced to the parameters- optimized process of IFPN. By constructing the approximate continuous function of transition 铿乺ing and intuitionistic fuzzy reasoning, the method makes the parameters get rid of the dependence upon experience, which makes the parameters adjust the fact instance better. Meanwhile, the IFPN model can own