SOFT COMPUTING METHOD FOR PREDICTION OF CO2 CORROSION IN FLOW LINES BASED ON NEURAL NETWORK APPROACH

An important aspect of corrosion prediction for oil/gas wells and pipelines is to obtain a realistic estimate of the corrosion rate. Corrosion rate prediction involves developing a predictive model that utilizes commonly available operational parameters, existing lab/field data, and theoretical models to obtain realistic assessments of corrosion rates. This study presents a new model to predict corrosion rates by using artificial neural network (ANN) systems. The values of pH, velocity, temperature, and partial pressure of the CO2 are input variables of the network and the rate of corrosion has been set as the network output. Among the 718 data sets, 503 of the data were implemented to find the best ANN structure, and 108 of the data that were not used in the development of the model were used to examine the reliability of this method. Statistical error analysis was used to evaluate the performance and the accuracy of the ANN system for predicting the rate of corrosion. It is shown that the predictions of this method are in acceptable agreement with experimental data, indicating the capability of the ANN for prediction of CO2 corrosion rate in production flow lines.

[1]  S. Srinivasan,et al.  An Analytical Model to Experimentally Emulate Flow Effects in Multiphase CO2/H2S Systems , 2000 .

[2]  J. Crolet,et al.  Basics of the prediction of the risks of CO sub 2 corrosion in oil and gas wells , 1989 .

[3]  Y. M. Gunaltun.  Combining Research And Field Data For beorrosion Rate Prediction , 1996 .

[4]  W. P. Jepson,et al.  Development Of A Mechanistic Model For Predicting Corrosion Rate In Multiphase Oil/Water/Gas Flows , 1997 .

[5]  Aage Stangeland,et al.  A Mechanistic Model for Carbon Dioxide Corrosion of Mild Steel in the Presence of Protective Iron Carbonate Films—Part 1: Theory and Verification , 2003 .

[6]  Andrzej Anderko,et al.  Simulation of CO2/H2S Corrosion Using Thermodynamic and Electrochemical Models , 1999 .

[7]  Hossein Jalalifar,et al.  Predicting bottomhole pressure in vertical multiphase flowing wells using artificial neural networks , 2011 .

[8]  S. Nešić,et al.  A MECHANISTIC MODEL OF IRON CARBONATE FILM GROWTH AND THE EFFECT ON CO2 CORROSION OF MILD STEEL , 2002 .

[9]  K. Videm,et al.  Parametric study of CO{sub 2} corrosion of carbon steel , 1994 .

[10]  W. P. Jepson,et al.  Predictive Model for Sweet Corrosion in Horizontal Multiphase Slug Flow , 1996 .

[11]  Stein Olsen,et al.  An Electrochemical Model for Prediction of Corrosion of Mild Steel in Aqueous Carbon Dioxide Solutions , 1996 .

[12]  Bruce Brown,et al.  General CO2 Corrosion in High Salinity Brines , 2006 .

[13]  A. Halvorsen,et al.  CO{sub 2} corrosion model for carbon steel including a wall shear stress model for multiphase flow and limits for production rate to avoid mesa attack , 1999 .

[14]  M. S. High,et al.  Mechanistic Modeling of Mass Transfer in the Laminar Sublayer in Downhole Systems , 2000 .

[15]  Ş. Niculescu.  Artificial neural networks and genetic algorithms in QSAR , 2003 .

[16]  Martin T. Hagan,et al.  Neural network design , 1995 .

[17]  S. Nešić.  Key issues related to modelling of internal corrosion of oil and gas pipelines - A review , 2007 .