查詢結果分析
來源資料
相關文獻
- 應用進化模糊推論於油浸式變壓器故障偵測
- 進化規劃法在汽電共生機組最佳燃料調度的應用
- 時間電價下汽電共生系統最佳運轉策略
- A Modified Evolutionary Programming Approach for Distribution Loss Reduction by Feeder Switching
- 以新突變規則的進化規劃法作多目標最佳電力潮流
- 油浸式變壓器之過載能力估算
- Time Series Analysis for Power System Short Term Load Forecasting
- An Evolutionary Programming Approach to Thermal Unit Commitment
- A Time Series Approach to Short Term Load Forecasting Through Evolutionary Programming Structures
- Evolving ARMA Model for Short Term Load Forecasting
頁籤選單縮合
題 名 | 應用進化模糊推論於油浸式變壓器故障偵測=Oil-immersed Transformer Fault Detection Using Evolutionary Fuzzy Reasoning Technique |
---|---|
作 者 | 黃燕昌; 陳順焜; 楊宏澤; | 書刊名 | 正修學報 |
卷 期 | 13 2000.12[民89.12] |
頁 次 | 頁121-127 |
分類號 | 448.23 |
關鍵詞 | 油浸式變壓器; 溶解氣體分析法; 模糊診斷系統; 進化規劃法; Oil-immersed transformer; Dissolved gas analysis; Fuzzy diagnosis system; Evolutionary programming; |
語 文 | 中文(Chinese) |
中文摘要 | 為改善溶解氣體分析法對油浸式變壓器故障診斷之能力,本文提出利用進化模糊推論方法建構變壓器初期故障診斷系統。本文首先利用國際電工委員會╱國際電機電子工程師學會(IEC/IEEE)所頒佈的變壓器溶解氣體評斷準則,作為故障種類判斷法則建立的初期依據。然後根據實際電力變壓器溶解氣體資料以及對應的故障種類,透過進化模糊推論法則建構演算法調整「若-則」推論法則之條件判斷的歸屬函數與其所相對應之故障結果,建立模糊診斷系統架構。本診斷系統經實際測試於臺電公司之溶解氣體資料庫,並與現有的診斷系統與類神經網路方法比較,發現本診斷系統於設計過程與診斷準確性均具有較佳之性能。 |
英文摘要 | To improve the diagnosis accuracy of the conventional dissolved gas analysis (DGA) approaches, this paper presents an evolutionary programming (EP) based fuzzy diagnosis system to detect the incipient fault of the oil-immersed transformers. Using the IEC/IEEE DGA criteria as reference, a preliminary framework of the fuzzy diagnosis system is first built. According to previous dissolved gas test records and their actual fault types, the proposed technique is then used to automatically modify the fuzzy if-then rules and simultaneously adjust the corresponding membership functions. In comparison to results of the conventional DGA and the artificial neural networks (ANN) methods, the proposed method has been verified to possess superior performance both in developing the diagnosis system and in identifying the practical transformer fault cases. |
本系統中英文摘要資訊取自各篇刊載內容。