高壓輸配電網路之故障偵測、辨識與定位之方法及系統

專利類型

發明

專利國別 (專利申請國家)

中華民國

專利申請案號

100123915

專利證號

I 425226

專利獲證名稱

高壓輸配電網路之故障偵測、辨識與定位之方法及系統

專利所屬機關 (申請機關)

國立臺灣大學

獲證日期

2014/02/01

技術說明

本發明實施例提供一種高壓輸配電網路之故障偵測、分類與定位之方法，此方法包括以下步驟。首先，將故障之一個週期內的電壓信號與電流信號進行多階層小波轉換，並據此產生複數個高頻信號。然後，對複數個高頻信號進行主成分分析，並據此產生至少一個信號特徵值。接著，使用支援向量機分類信號特徵值，以得到故障類型。再來，使用對應故障類型之可適性結構類神經網路偵測故障位置。據此，所述方法可完成故障偵測、分類與定位，且所述方法所花費的時間遠短於臨界故障清除時間。 An exemplary embodiment of the present disclosure illustrates a method for fault detection, classification and location in a high-voltage power transmission network. The method includes following steps. First, a multi-level wavelet transform is performed on a voltage signal and a current signal in a cycle of a fault, and a plurality of high frequency signals are generated accordingly. Then, a principal component analysis is performed on the high frequency signals, and at least one signal characteristic value is generated accordingly. Then, the signal characteristic value is classified by using a support vector machine to obtain a type of the fault. Then, an adaptive structural neural network corresponding to the type of the fault is used to estimate a location of the fault. Accordingly, the method accomplishes fault detection, fault classification, and fault location in a time significantly shorter than critical fault clearing time.

備註

連絡單位 (專責單位/部門名稱)

產學合作總中心

連絡電話

33669945

網址