摘 要：提出一種基于PCA-神經(jīng)網(wǎng)絡(luò)的電力電子整流裝置故障診斷方法。首先對(duì)故障信號(hào)用主元分析法（PCA）提取特征向量，然后用神經(jīng)網(wǎng)絡(luò)進(jìn)行訓(xùn)練和測(cè)試。通過(guò)三相可控整流電路晶閘管斷路故障診斷實(shí)驗(yàn)結(jié)果表明，該方法能夠簡(jiǎn)化神經(jīng)網(wǎng)絡(luò)的結(jié)構(gòu)，提高網(wǎng)絡(luò)的訓(xùn)練速度，并獲得了很好的診斷效果。 關(guān)鍵詞：故障診斷;神經(jīng)網(wǎng)絡(luò);主元分析 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 （PCA） 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 前言 　　隨著電力電子技術(shù)的迅猛發(fā)展，實(shí)現(xiàn)能量變換的電力電子整流裝置，由于其效率高、控制靈活方便、易實(shí)現(xiàn)等優(yōu)點(diǎn)[1]，使其的應(yīng)用日益廣泛，同時(shí)電力電子整流裝置的故障問(wèn)題也越來(lái)越突出，因此在電力電子整流裝置中應(yīng)用自動(dòng)故障診斷技術(shù)，是有其現(xiàn)實(shí)意義和經(jīng)濟(jì)意義的，開展相關(guān)的理論和方法研究尤為重要。本文提出了一種基于主成分分析和神經(jīng)網(wǎng)絡(luò)相結(jié)合的電力電子整流裝置故障診斷方法，該方法結(jié)合兩種理論各自的優(yōu)點(diǎn)，首先對(duì)不同類型的故障信號(hào)進(jìn)行主成分變換，提取故障特征向量送入到神經(jīng)網(wǎng)絡(luò)中進(jìn)行分類決策。 詳情請(qǐng)點(diǎn)擊：基于PCA-NN的電力電子整流裝置故障診斷