| 人工神经网络在低阻油层识别上的应用 |
| |
| 引用本文： | 杨庆军,邓春呈,杨永利,鲁国普.人工神经网络在低阻油层识别上的应用[J].特种油气藏,2001,8(2):8-10. |
| |
| 作者姓名： | 杨庆军 邓春呈 杨永利 鲁国普 |
| |
| 作者单位： | 1. 中国地质大学石油系,湖北武汉430074
2. 河南石油勘探局勘探开发研究院,河南,南阳,473132 |
| |
| 摘 要： | 低阻油层作为一种非常规储层，其含油性受多个因素影响。常规测井解释方法评价低阻油层有很大的困难。人工神经网络具有自适应、自学习、抗干扰能力较强的特点。本文利用BP模型，结合低阻油层的电性特征，成功地对河南油区下二门油田的低阻油气层进行了识别。
|
| 关 键 词： | 人工神经网络 BP模型 低阻油层 河南油区 下二门油田 油气勘探 |
| 文章编号： | 1006-6535(2001)02-0008-03 |
Application of nerve network on oil-bearing formation with low resistivity |
| |
| Yang Qingjun,Deng Chuncheng,Yang Yongli,Lu Guopu.Application of nerve network on oil-bearing formation with low resistivity[J].Special Oil & Gas Reservoirs,2001,8(2):8-10. |
| |
| Authors: | Yang Qingjun Deng Chuncheng Yang Yongli Lu Guopu |
| |
| Abstract: | As an unconventional one, low resistivity oil-bearing formation is affected by many factors and common logging interpretation method meets difficulty in evaluating the same formation. However, artificial nerve network features self-adapting, self-learning and strong disturbance resistant. Oil and gasformations are identified successfully with BP model combining the electrical properties of low resistivityoil formation. |
| |
| Keywords: | artificial nerve network BP model low resistivity oil-bearing formation identification Henan oil province Xia'ermen oilfield |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
