Research on Prediction and Optimization Design Method of Slip Anchoring Performance Based on BP&NSGA-II

被引:4
作者
Ming, Lu [1 ,2 ]
Hualin, Liao [1 ,2 ]
Huajian, Wang [1 ,2 ]
Jiansheng, Liu [1 ,2 ]
Yuhang, He [1 ,2 ]
Fengtao, Qu [1 ,2 ]
Wenlong, Niu [1 ,2 ]
Yifan, Wang [1 ,2 ,3 ]
机构
[1] China Univ Petr East China, Sch Petr Engn, Qingdao, Peoples R China
[2] MOE Key Lab Unconvent Oil & Gas Dev, Qingdao, Peoples R China
[3] CNPC Tarim Oilfield Co, Res Inst Oil & Gas Engn, Korla, Peoples R China
关键词
prediction model; BP neural network; numerical analysis; slip sealing; indoor test; NEURAL-NETWORKS;
D O I
10.3389/fenrg.2022.907877
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
The slip of the packer is the core part of the anchoring system. Unreasonable design of the slip structure can easily cause damage to the anchor claw of the slip, unstable anchoring, and even damage to the casing. At present, the main methods of slip anchoring performance tests are indoor design and field tests, and slips with different structural parameters need to be processed to verify their anchoring performance. In order to ensure that the slips can play a good anchoring effect and reduce the damage to the casing, this study uses a combination of finite element analysis, BP & NSGA-II, and indoor tests to study the mechanical behavior of the slips during the anchoring process. A prediction model was established to optimize the key parameters affecting anchoring performance, such as slip angle, inclination angle, inner cone angle, the radius of curvature, and spacing. Indoor experiments show that the prediction method can greatly improve the efficiency and accuracy of the design and test the anchoring performance of slips.
引用
收藏
页数:10
相关论文
共 20 条
[1]  
[Anonymous], 2009, IPEMC
[2]   Performance of neural networks in materials science [J].
Bhadeshia, H. K. D. H. ;
Dimitriu, R. C. ;
Forsik, S. ;
Pak, J. H. ;
Ryu, J. H. .
MATERIALS SCIENCE AND TECHNOLOGY, 2009, 25 (04) :504-510
[3]  
Gao Yifei., 2012, IMPLEMENTATION GUIDE
[4]   On the influence of stress triaxiality and strain rate on the behaviour of a structural steel. Part I. Experiments [J].
Hopperstad, OS ;
Borvik, T ;
Langseth, M ;
Labibes, K ;
Albertini, C .
EUROPEAN JOURNAL OF MECHANICS A-SOLIDS, 2003, 22 (01) :1-13
[5]  
Jingchao Liu, 2016, DRILL PROD TECHNOL, V39, P67, DOI [10.1016/j.fuel.2021.121789, DOI 10.1016/J.FUEL.2021.121789]
[6]   The use of neural networks for the prediction of fatigue lives of composite materials [J].
Lee, JA ;
Almond, DP ;
Harris, B .
COMPOSITES PART A-APPLIED SCIENCE AND MANUFACTURING, 1999, 30 (10) :1159-1169
[7]  
Lou Shuntian., 1998, DESIGN ANAL BASED MA
[8]  
Ma C., 2009, REFINING CHEM IND
[9]   Application of artificial neural networks for modelling correlations in titanium alloys [J].
Malinov, S ;
Sha, W .
MATERIALS SCIENCE AND ENGINEERING A-STRUCTURAL MATERIALS PROPERTIES MICROSTRUCTURE AND PROCESSING, 2004, 365 (1-2) :202-211
[10]  
Sun Y, 2010, RARE METAL MAT ENG, V39, P1031