查詢結果分析
來源資料
頁籤選單縮合
題 名 | 利用類神經網路估算已開發礦區之油氣生產量及蘊藏量之研究 |
---|---|
作 者 | 林再興; 王崇興; | 書刊名 | 石油鑽採工程 |
卷 期 | 40 1999.12[民88.12] |
頁 次 | 頁50-56 |
分類號 | 457.2 |
關鍵詞 | 蘊藏量; 衰減曲線; 類神經網路; 生產率; Reserves; Decline curve; Neural networks; Production rate; |
語 文 | 中文(Chinese) |
中文摘要 | 本研究目的是利用油氣生產資料以建立、訓練及驗證類神經網路, 而預測礦區未 來生產率,並估算剩餘蘊藏量。 本研究以台灣 T- 天然氣礦區為例,利用具有衰減的生產資料分別進行三種類神經網路之訓 練學習及驗證。每種類神經網路都包括輸入層、隱藏層及輸出層等三層。由於 T- 礦區曾受 到注氣井之影響,本研究利用產率因子之變化而將注氣井之影響消除或加入,由類神經網路 所計算 T- 天然氣礦區之剩餘蘊藏量為 19 億至 28 億立方公尺。 |
英文摘要 | The purposes of this study are to establish and train a neural network for a gas field in Taiwan, and then tp predict future production rate to estimate remaining reserves. The gas reserves estimated from neural network are compared with those from decline curve analysis. Production data of T-gas field are collected and used in this study to derive three neural network. Back propagation neural networks of three layers including on hidden layer are established in this study. Training and validating of these neural networks have been conducted. Analysis of production data shows that production rate of T-gas field was affected by injecting wells. After eliminating the effect of injecting wells, the remaining reserves from neural networks for T-gas field is estimated between 1.9 and 2.8 billion SCM (standard cubic meters). |
本系統中英文摘要資訊取自各篇刊載內容。