Pipeline Inspection Gauge’s Velocity Simulation Based on Pressure Differential Using Artificial Neural Networks

Industrial pipelines must be inspected to detect typical failures, such as obstructions and deformations, during their lifetime. In the petroleum industry, the most used non-destructive technique to inspect buried pipelines is pigging. This technique consists of launching a Pipeline Inspection Gauge (PIG) inside the pipeline, which is driven by the pressure differential produced by fluid flow. The purpose of this work is to study the application of artificial neural networks to calculate the PIG’s velocity based on the pressure differential. We launch a prototype PIG inside a testing pipeline, where this PIG gathers velocity data from an odometer-based system, while a supervisory system gathers pressure data from the testing pipeline. Then we train a Multilayer Perceptron (MLP) and a Nonlinear Autoregressive Network with eXogenous Inputs (NARX) network with the gathered data to predict velocity. The results suggest it is possible to use a neural network to model the PIG’s velocity from pressure differential measurements. Our method is a new approach to the typical speed measurements based only on odometer, since the odometer is prone to fail and present poor results under some circumstances. Moreover, it can be used to provide redundancy, improving reliability of data obtained during the test.

[1]  K S Narendra,et al.  IDENTIFICATION AND CONTROL OF DYNAMIC SYSTEMS USING NEURAL NETWORKS , 1990 .

[2]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[3]  Sang Bong Kim,et al.  Speed control of PIG using bypass flow in natural gas pipeline , 2001, ISIE 2001. 2001 IEEE International Symposium on Industrial Electronics Proceedings (Cat. No.01TH8570).

[4]  J. N. H. Tiratsoo.  Pipeline pigging technology , 1988 .

[5]  Chaitanya Narendra Yardi.  Design of regulated velocity flow assurance device for petroleum industry , 2005 .

[6]  V. Ponomaryov,et al.  Evaluation of distance measurement accuracy by odometer for pipelines pigs , 2006 .

[7]  André Laurindo Maitelli,et al.  PIG’s Speed Estimated with Pressure Transducers and Hall Effect Sensor: An Industrial Application of Sensors to Validate a Testing Laboratory , 2017, Sensors.

[8]  Q. Y. Li,et al.  Pipeline robot and intelligent control method , 2015 .

[9]  Hongda Liu,et al.  Pipeline defect detection and sizing based on MFL data using immune RBF neural networks , 2007, 2007 IEEE Congress on Evolutionary Computation.

[10]  M Mirshamsi,et al.  Speed Control of Pipeline Pig Using the QFT Method Contrôle de la vitesse d’un racleur grâce à la méthode de synthèse QFT , 2012 .

[11]  J. Sjöberg.  Non-Linear System Identification with Neural Networks , 1995 .

[12]  Tan Tien Nguyen,et al.  Modeling and simulation for PIG flow control in natural gas Pipeline , 2001 .

[13]  Rahmat Shoureshi,et al.  Neural networks for system identification , 1989, IEEE Control Systems Magazine.

[14]  Fakhruldin Mohd Hashim,et al.  Recent Developments in Speed Control System of Pipeline PIGs for Deepwater Pipeline Applications , 2012 .

[15]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[16]  Luis Volnei Sudati Sagrilo,et al.  MFL signals and artificial neural networks applied to detection and classification of pipe weld defects , 2006 .

[17]  Karsten Berns,et al.  NeuroPipe: a neural-network-based automatic pipeline inspection system , 1996, Other Conferences.

[18]  Emad Elwakil,et al.  A model for predicting failure of oil pipelines , 2014 .