Session: 03-03-04 Feature Assessment Case Studies - Corrosion II

Paper Number: 129041

129041 - Accounting for Corrosion Growth and Interaction in Future Severity Assessments 

Abstract: 

The determination of corrosion growth rates and their application in the prediction of future severity is a critical part of pipeline integrity management.  Accurate corrosion growth rates are needed to predict pipeline reliability as a function of time, to identify the need for and timing of field investigations and/or repairs and to determine optimum re-inspection intervals.  The consequences associated with both underestimating and overestimating growth rates can be significant in terms of both safety and resource performance. 

The use of repeat ILI data to match and compare metal loss sites in order to estimate the corrosion growth rates at individual defects along a pipeline is a well-used and established practice in the industry.  There are many ways that corrosion growth rates can be used in future integrity predictions with most approaches only accounting for corrosion growth in the depth dimension taking no account of surface area growth and potential interactions between adjacent corrosion areas over time.

Now that we have a wealth of historical data with 3, 4 or even 5 sets of ILI data for the same pipelines we are able to experiment with more advanced three-dimensional modelling and have the ability to test new approaches vs actual “truth” data.   With the benefit of this progressive viewpoint, the methodologies employed for evaluating and applying ILI based corrosion rates are being further improved and refined to give more accurate predictions of the future pipeline condition, the response schedule and for setting the timing of re-inspections.

This paper describes a new approach that predicts how an area (cluster) or corrosion could grow over time combining with surrounding corrosion defects and with newly developing defects as well as in the depth dimension.  The main differences between this and the more established approaches are:

·        It does not use fixed individual defect or pipe spool growth rates, but instead uses a growth rate distribution drawn from a group of corrosion defects under the same or very similar corrosive environment.

·        The assessment accounts for growth in all three dimensions (depth, length and width) and models the more complex interaction between nearby areas of corrosion.

·        It uses a machine learning model to predict the location and pattern of potential new corrosion sites.

The new approach is illustrated and compared to the more established methodologies via the use of case studies on real ILI data sets.

Presenting Author: Steven Farnie Baker Hughes

Presenting Author Biography: Steve Farnie is Regional Data Science Manager based in Cramlington, UK. Steve has over 20 years’ experience in the pipeline industry and has held roles as Mathematician, Sizing Specialist, Software Developer, Software Team Leader and Data Scientist. Steve holds a BSc in Mathematics from the University of Warwick and an MSc in Mathematical Modelling from the University of Coventry, UK.

Authors:

Jane Dawson Baker Hughes
Steven Farnie Baker Hughes