鎽� 瑕侊細鎻愬嚭涓€绋熀浜嶱CA-绁炵稉(j墨ng)缍�(w菐ng)绲�(lu貌)鐨勯浕鍔涢浕瀛愭暣娴佽缃晠闅滆ê鏂锋柟娉曘€傞鍏堝皪(du矛)鏁呴殰淇¤櫉(h脿o)鐢ㄤ富鍏冨垎鏋愭硶锛圥CA锛夋彁鍙栫壒寰佸悜閲�锛岀劧鍚庣敤绁炵稉(j墨ng)缍�(w菐ng)绲�(lu貌)閫�(j矛n)琛岃〒(x霉n)绶村拰娓�(c猫)瑭︺€傞€氶亷涓夌浉鍙帶鏁存祦闆昏矾鏅堕枠绠℃柗璺晠闅滆ê鏂峰(sh铆)椹�(y脿n)绲�(ji茅)鏋滆〃鏄�锛岃┎鏂规硶鑳藉绨�(ji菐n)鍖栫缍�(j墨ng)缍�(w菐ng)绲�(lu貌)鐨勭祼(ji茅)妲�(g貌u)锛屾彁楂樼恫(w菐ng)绲�(lu貌)鐨勮〒(x霉n)绶撮€熷害锛屽苟鐛插緱浜嗗緢濂界殑瑷烘柗鏁堟灉銆� 闂�(gu膩n)閸佃锛�鏁呴殰瑷烘柗;绁炵稉(j墨ng)缍�(w菐ng)绲�(lu貌);涓诲厓鍒嗘瀽 Abstract: ault diagnosis method for power electronics rectifier based on PCA-Neural Network was proposed. First extract the feature vector from the fault signal with the principal component analytic 锛圥CA锛� method, and then use neural network training and testing. Experimental result of thyristor open circuit fault diagnosis in power electronics rectifier showed that this method can simplify the structure of the neural network, improve the training speed of the network, have obtained very good diagnostic effect. Key words: Fault diagnosis;Neural Network; Principle Component Analysis 1 鍓嶈█ 銆€銆€闅ㄨ憲闆诲姏闆诲瓙鎶€琛�(sh霉)鐨勮繀鐚涚櫦(f膩)灞�锛屽(sh铆)鐝�(xi脿n)鑳介噺璁婃彌鐨勯浕鍔涢浕瀛愭暣娴佽缃紝鐢变簬鍏舵晥鐜囬珮銆佹帶鍒堕潏娲绘柟渚裤€佹槗瀵�(sh铆)鐝�(xi脿n)绛夊劒(y艒u)榛�(di菐n)[1]锛屼娇鍏剁殑鎳�(y墨ng)鐢ㄦ棩鐩婂唬娉涳紝鍚屾檪(sh铆)闆诲姏闆诲瓙鏁存祦瑁濈疆鐨勬晠闅滃晱椤屼篃瓒婁締瓒婄獊鍑�锛屽洜姝ゅ湪闆诲姏闆诲瓙鏁存祦瑁濈疆涓噳(y墨ng)鐢ㄨ嚜鍕�(d貌ng)鏁呴殰瑷烘柗鎶€琛�(sh霉)锛屾槸鏈夊叾鐝�(xi脿n)瀵�(sh铆)鎰忕京鍜岀稉(j墨ng)婵�(j矛)鎰忕京鐨�锛岄枊灞曠浉闂�(gu膩n)鐨勭悊璜栧拰鏂规硶鐮旂┒灏ょ偤閲嶈銆傛湰鏂囨彁鍑轰簡涓€绋熀浜庝富鎴愬垎鍒嗘瀽鍜岀缍�(j墨ng)缍�(w菐ng)绲�(lu貌)鐩哥祼(ji茅)鍚堢殑闆诲姏闆诲瓙鏁存祦瑁濈疆鏁呴殰瑷烘柗鏂规硶锛岃┎鏂规硶绲�(ji茅)鍚堝叐绋悊璜栧悇鑷殑鍎�(y艒u)榛�(di菐n)锛岄鍏堝皪(du矛)涓嶅悓椤炲瀷鐨勬晠闅滀俊铏�(h脿o)閫�(j矛n)琛屼富鎴愬垎璁婃彌锛屾彁鍙栨晠闅滅壒寰佸悜閲忛€佸叆鍒扮缍�(j墨ng)缍�(w菐ng)绲�(lu貌)涓€�(j矛n)琛屽垎椤炴焙绛�銆� 瑭虫儏璜�(q菒ng)榛�(di菐n)鎿婏細鍩轰簬PCA-NN鐨勯浕鍔涢浕瀛愭暣娴佽缃晠闅滆ê鏂�