頁籤選單縮合
題 名 | On-line Condition Monitoring of Electrical Power Transformers Using Intelligent Self-constructing Diagnosis System=應用智慧型自建構診斷系統於電力變壓器線上狀況監測 |
---|---|
作 者 | 黃燕昌; | 書刊名 | 電腦學刊 |
卷 期 | 13:3 2001.09[民90.09] |
頁 次 | 頁31-37 |
分類號 | 448.23 |
關鍵詞 | 智慧型診斷系統; 故障診斷; 電力變壓器; Intelligent diagnosis system; Fault diagnosis; Electrical power transformers; |
語 文 | 英文(English) |
中文摘要 | 本文提出一智慧型自建構診斷系統於電力變壓器線上狀況監測,用以改善電力變 壓器初期故障之診斷性能。所提方法之建模方式是以低階多項式函數逐一建構成高階多項式 函數,用以建立溶解於變壓器絕緣油中各種溶解氣體成分與其相對應之故障種類之對應關係 。此溶解氣體成分與相對之故障種類間存在一複雜且富有數值知識之對應關係。本診斷系統 實際測試於台電公司溶解氣體資料庫並與類神經網路及傳統方法比較,測試結果證明本診斷 系統同時具有優異之診斷性能與較短之系統建構時間。 |
英文摘要 | This paper presents an intelligent self-constructing diagnosis system (ISCDS) for on-line condition monitoring of electrical power transformers that enhances the diagnotic accuracy of the power transformer incipient fault. The ISCDS formulates the pattern recognition problem into a hierarchical architecture with several layers of functional nodes of simple low-order polynomials. The ISCDS treats the complicated and numerical-knowledge relationships of diverse dissolved gas contents in the transformer oil to their corresponding fault types. The proposed ISCDS has been tested on the Taipower company diagnostic records and compared with the artificial neural networks (ANNs) as well as the main conventional methods. The test results confirm that the ISCDS possesses far superior diagnosis accuracy and requires less effort to develop. |
本系統中英文摘要資訊取自各篇刊載內容。