查詢結果分析
來源資料
頁籤選單縮合
題 名 | A Study of Power Transformer Fault Diagnosis Using Neural Network=應用類神經網路專家系統診斷電力變壓器故障之研究 |
---|---|
作 者 | 王念中; 郭宗益; | 書刊名 | 台電工程月刊 |
卷 期 | 616 1999.12[民88.12] |
頁 次 | 頁45-54 |
分類號 | 448.23 |
關鍵詞 | 油中氣體分析; 專家系統; 類神經網路; 變壓器故障診斷; 故障型別; 故障位置; Dissolved gas-in-oil analysis; DGA; Expert system; EPS; Artificial neural network; ANN; Transformer fault diagnosis; Fault types; Location of the fault; |
語 文 | 英文(English) |
中文摘要 | 本研究開發完成一個有關電力變壓器故障診斷的系統,該系統使用油中氣體分析 資料(DGA),而運作的基礎為「類神經網路(ANN)」和「專家系統(EPS)」。專家系統 所用的知識庫係取自IEEE 和IEC DGA標準,以及變壓器專家們的經驗;類神經網路的架 構及訓練資料組係經過細心挑選,以萃取已知的與未知的診斷相互內含。診斷系統 (ANNEPS)結合ANN和EPS之個別輸出而擁有較佳機制,以確保高的診斷精確度。系統 測試結果顯示不僅可診斷和預測故障型別,在某些案例中,亦可能預測故障位置。 |
英文摘要 | An artificial neural network and expert system based diagnosis system for transformer fault diagnosis using dissolved gas-in-oil analysis (DGA) has been developed. The knowledge base of its expert system (EPS)is derived from IEEE and IEC DGA standards and expert experiences. The topology and training date set of its artificial neural network (ANN) are carefully selected to extract known as well as unknown diagnosis correlation implicitly. The diagnosis system (ANNEPS) with the combination of the ANN and EPS outputs has an optimization mechanism to ensure high diagnosis accuracy. Test results show that it is possible not only to diagnosis and predict fault types, but also in certain cases, to predict the location of the fault. |
本系統中英文摘要資訊取自各篇刊載內容。