Predicting Failure in Crude Oil Pipelines Using First Degree Polynomial Model and Reduced Second Degree Polynomial Model, Validating the Models Using Goodness of Fit Indices

To mitigate these risks, pipelines require constant monitoring and maintenance to detect and rectify defects such as corrosion before they lead to failure. However, the regular monitoring and non-destructive testing of pipelines incur substantial costs. Consequently, there is a growing interest in research focused on predictive corrosion monitoring of pipelines based on easily measurable operational parameters. This study aims to employ a model-based condition monitoring and failure avoidance approach to predict failures in crude oil pipelines. Secondary data on mean corrosion rates, mean pH levels, mean temperatures, mean pressures, and mean aqueous CO2 partial pressures were collected from an oil and gas multinational company spanning the years 2007 to 2011. Polynomial regression models were developed. The models' validity was assessed using Goodness of Fit Indices (GFI).
For the first-degree polynomial model, the following results were obtained for both training and testing datasets: Coefficient of Determination (R2) = 0.3022/0.2948, Root Mean Square Error (RMSE) = 0.0050/0.0040, Mean Biased Error (MBE) = 0.0000/0.00010, Mean Absolute Biased Error (MABE) = 0.0037/0.0026, Mean Percentage Error (MPE) = 0.0320/0.3633, and correlation coefficient (r) = 0.5497/0.5891. Furthermore, the goodness of fit for the reduced second-degree model for both training and testing datasets provided the following results: (R2) = 0.9859/0.9341, (RMSE) = 0.0007/0.0012, (MBE) = 0.0000/0.0001, (MABE) = 0.0004/0.0008, (MPE) =
0.0006/0.0390, and (r) = 0.9929/0.9676. This research contributes valuable insights into the technological applications and policy implications of predictive corrosion monitoring for pipelines.