Title :
Inverse deduction of parameters of slip of bridge plug based on RBF neural network model
Author :
Geng, Dai ; Zhang, Shimin ; Wang, Deguo
Author_Institution :
Fac. of Mech.-Electron. Eng., China Univ. of Pet., Beijing, China
Abstract :
According to the demand of exploitating the poor thin oil layer in Daqing oilfield, bridge plug is designed. The clamping function which is respectively accomplished through the slip is the key techniques of bridge plug. For the aim of designing the clamping function, firstly, the slip structure of Slip is introduced. Then in order to calculate contact stress of test model with combinations of different levels of parameters corresponding to different compactions of slip structure, FEM model of slip was established and analyzed.At the same time with normalized different levels of parameters of slip structure for input targets and simultaneously normalized results of model test for output variables, parameters of slip structure were inversely deducted with RBF neural network model; With the use of these parameters were carried out with ANSYS software in this paper, shows that it is feasible that unsaturated parameters are inversely deduced with RBF neural network mode.
Keywords :
bridges (structures); finite element analysis; petroleum industry; radial basis function networks; structural engineering computing; ANSYS software; Daqing oilfield; FEM model; RBF neural network model; bridge plug; clamping function design; inverse deduction; model test; poor thin oil layer; slip structure parameters; Analytical models; Bridges; Finite element methods; Neurons; Plugs; Solid modeling; Stress; Finite element analysis; RBF neural network mode; Slip; Structure parameter; bridge plug;
Conference_Titel :
Electric Technology and Civil Engineering (ICETCE), 2011 International Conference on
Conference_Location :
Lushan
Print_ISBN :
978-1-4577-0289-1
DOI :
10.1109/ICETCE.2011.5774388