[an error occurred while processing this directive] ������� 2012, 31(4) 785-790 DOI:     ISSN: 1004-5589 CN: 22-1111/P

����Ŀ¼ | ����Ŀ¼ | ������� | �߼�����                                                            [��ӡ��ҳ]   [�ر�]
����
��չ����
������Ϣ
Supporting info
PDF(926KB)
[HTMLȫ��]
�����[PDF]
�����
�����뷴��
�ѱ����Ƽ�������
�����ҵ����
�������ù�����
����
Email Alert
���·���
���������Ϣ
���Ĺؼ����������
�Ϳ׵���
ɰ�Ҵ���
ѹ�Ѳ���
BP ������
�����Ͳ�
���������������
ׯ��
�˱�֥
������
PubMed
Article by Zhuang, H.
Article by Pan, B. Z.
Article by Zhang, L. H.
BP ������ģ���ڳ������������Ͳ�ѹ�Ѳ���Ԥ���е�Ӧ��
ׯ��, �˱�֥, ������
���ִ�ѧ����̽���ѧ�뼼��ѧԺ������130026
ժҪ��

������س������������Ͳ��ǵ��͵ĵͿ׵���ɰ�Ҵ��㣬��Ҫ����ѹ�Ѹ��죬����Ӱ�����ؽ϶࣬�ó������Է������еIJ���Ԥ�����������Ȳ��������о������⾮������Ӧ�����Ļ����ϣ����ݵ�������ͻ�ɫ��������������ѡ��Ȼ٤�������������ʡ����Ӻ��ܶ�5 ���⾮��������������ɰ�ȡ�����ѹ��2 ��ѹ��ʩ�������������е����ͽ�����Ϊģ�͵�ѵ������������Ԥ�ⴢ��ѹ�Ѹ����λ��Ȳ�Һ���͵�λ��Ȳ�������BP ������ģ�͡���ʵ��Ӧ�ù����У������ܽ�׼ȷ�ػ�����ˮ�㣬ͬʱ�����˲������ļ���ο�ֵ��ʵ���˶ԵͿ׵���ɰ�Ҵ���ѹ�Ѳ��ܵ���Ч����Ԥ�⡣

�ؼ����� �Ϳ׵���   ɰ�Ҵ���   ѹ�Ѳ���   BP ������   �����Ͳ�  
Application of BP neural network model in fracturing productivity prediction of Fuyang oil layer in Chaochang area
ZHUANG Hua, PAN Bao-Zhi, ZHANG Li-Hua
College of Geo-Exploration Science and Technology��Jilin University��Changchun 130026��China
Abstract:

Fuyang oil layer in Chaochang area located in Songliao Basin is a typical sandstone reservoir with low porosity and permeability��which often needs to be fractured�� Many factors can affect the productivity�� The accuracies of productivity prediction getting from conventional linear methods are not enough�� Based on the study of the response characteristics of logging curves in this area��combining with the regional experience and grey relational analysis method��five response characteristic parameters are optimized: GR��AC��LLD��CN and DEN�� Sand ratio and fracture pressure are also optimized�� Combining the chosen data with the test result as the training samples of the model��the established model can be used to predict liquid production in thickness and oil production in thickness of a fractured reservoir�� In the progress of practical application��the model not only can divide the oil layers and water layers precisely��but also can give a reference value of the oil production��which could achieve the effective and rapid fracturing productivity prediction of sandstone reservoir with low porosity and permeability.

Keywords: low porosity and low permeability   sandstone reservoir   fracturing productivity   BP neural network   Fuyang reservoir  
�ո�����  �޻�����  ����淢������  
DOI:
������Ŀ:

ͨѶ����:
���߼��:
����Email:

�ο����ף�
�������������
1�� �ŷ1,2, �˱�֥3.��ˮģ������Ӣ̨���ﴢ��⾮�����е�Ӧ��[J]. �������, 2009,28(2): 226-232
2�� �̺���1, 2, ����ΰ3.�����Ϳ׵��������������[J]. �������, 2010,29(3): 459-465
3�� ����1, 2, 3, ������2, �����1.BP ģ�����Ϻ����������Ȼ��ˮ���ﴢ������Ԥ���е�Ӧ��[J]. �������, 2011,30(1): 80-84
4�� ������1, �˱�֥1, ������1, ��С��2, �����2, ������2.�Ϳ׵���������Ȼ���ܲ⾮Ԥ�ⷽ��———�Գ���������Ϊ��[J]. �������, 2012,31(3): 561-566

Copyright by �������