Development of a novel approach for strain demand prediction of pipes at fault crossings on the basis of multi-layer neural network driven by strain data

Abstract The active fault is one of the commonest geological disasters in the pipeline construction. Excessive tensile or compressive strain may be induced in pipelines which may lead to the rupture or buckling when the two fault plates generate relative movement on the fault plane so that the pipeline cannot operate normally. In this study, a finite element model of pipelines subjected to fault displacements has been established for obtaining the database of strain demand which contains the prospective engineering conditions by considering the influencing factors, i.e. pipe geometrical parameters, internal pressure, fault parameters, and soil parameters. This process has been conducted by an effective hybrid methodology which can integrate the function of .inp documents generation, automatic calculation, and results extraction based on the technology of Python, Abaqus batch processing, and Matlab. The database can be utilized as training data in the multi-layer neural network for developing the strain demand prediction model which shows accurate results with high efficiency compared with general finite element methods.

[1]  Rp Kennedy,et al.  Fault Movement Effects on Buried Oil Pipeline , 1977 .

[2]  Tarek Abdoun,et al.  Centrifuge modeling of PGD response of buried pipe , 2005 .

[3]  Ikuo Towhata,et al.  Shaking table tests modelling small diameter pipes crossing a vertical fault , 2012 .

[4]  Oleg V. Trifonov,et al.  A semi-analytical approach to a nonlinear stress–strain analysis of buried steel pipelines crossing active faults , 2010 .

[5]  Shiro Takada,et al.  An equivalent-boundary method for the shell analysis of buried pipelines under fault movement , 2004 .

[6]  Hong Zhang,et al.  Strain demand prediction method for buried X80 steel pipelines crossing oblique-reverse faults , 2017 .

[7]  Spyros A. Karamanos,et al.  Analytical model for the strain analysis of continuous buried pipelines in geohazard areas , 2017 .

[8]  Azam Dolatshah,et al.  Seismic strain analysis of buried pipelines in a fault zone using hybrid FEM-ANN approach , 2013 .

[9]  Oleg V. Trifonov Numerical Stress-Strain Analysis of Buried Steel Pipelines Crossing Active Strike-Slip Faults with an Emphasis on Fault Modeling Aspects , 2015 .

[10]  Wei Zheng,et al.  A semi-empirical model for peak strain prediction of buried X80 steel pipelines under compression and bending at strike-slip fault crossings , 2016 .

[11]  Oleg V. Trifonov,et al.  Elastoplastic stress–strain analysis of buried steel pipelines subjected to fault displacements with account for service loads , 2012 .

[12]  Katsumi Fukuda,et al.  A new proposal for simplified design of buried steel pipes crossing active faults , 2001 .

[13]  George P. Kouretzis,et al.  Stress analysis of buried steel pipelines at strike-slip fault crossings , 2007 .

[14]  Leon Ru-Liang Wang,et al.  A refined seismic analysis and design of buried pipeline for fault movement , 1985 .

[15]  George P. Kouretzis,et al.  An analytical method for strength verification of buried steel pipelines at normal fault crossings , 2011 .

[16]  Tarek Zayed,et al.  Artificial neural network models for predicting condition of offshore oil and gas pipelines , 2014 .