THE CONVENTIONAL LOGGING IDENTIFICATION OF FRACTURED FORMATION WITH ARTIFICIAL NEURAL NETWORK

摘要： 裂缝识别是长期困扰裂缝油气藏勘探的难题之一,单纯依靠常规测井资料进行裂缝识别,存在主观不确定性及多解性;成像测井直观准确,但成本较高.本文基于人工神经网络理论,开展了常规测井资料识别评价裂缝性储层的研究.结果表明,基于人工神经网络的裂缝性储集层常规测井识别,具有较好的效果.

关键词: 裂缝识别, 常规测井, 人工神经网络

CLC Number:

梁利喜, 许强, 刘向君. 基于人工神经网络实现裂缝性储集层的测井识别[J]. 新疆石油天然气, 2005, 1(3): 51-53.

[1]	LIAN Zhanghua, MOU Yisheng, ZHANG Qiang. Finite Element Analysis for Vibration Mechanical Behavior of Tubing String in Gas Wells under Extreme Conditions [J]. Xinjiang Oil & Gas, 2021, 17(3): 59-66.
[2]	. [J]. Xinjiang Oil & Gas, 2021, 17(2): 46-49.
[3]	. [J]. Xinjiang Oil & Gas, 2021, 17(2): 50-52.
[4]	. [J]. Xinjiang Oil & Gas, 2020, 16(1): 45-50.
[5]	. [J]. Xinjiang Oil & Gas, 2019, 15(3): 49-53.
[6]	. [J]. Xinjiang Oil & Gas, 2019, 15(1): 47-51.
[7]	. [J]. Xinjiang Oil & Gas, 2017, 13(3): 29-32.
[8]	. [J]. Xinjiang Oil & Gas, 2017, 13(2): 38-42.
[9]	. [J]. Xinjiang Oil & Gas, 2016, 12(3): 29-31.
[10]	. [J]. Xinjiang Oil & Gas, 2015, 11(3): 49-52.
[11]	. [J]. Xinjiang Oil & Gas, 2015, 11(2): 66-69.
[12]	. [J]. Xinjiang Oil & Gas, 2014, 10(2): 25-28.
[13]	. [J]. Xinjiang Oil & Gas, 2014, 10(2): 29-33.
[14]	. [J]. Xinjiang Oil & Gas, 2013, 9(4): 42-44.
[15]	. [J]. Xinjiang Oil & Gas, 2013, 9(4): 45-48.

PDF (PC)