In-line Inspection Results Research Articles

Forecasting pipeline safety and remaining life with machine learning methods and SHAP interaction values

In-line inspection (ILI) is a common and useful way to provide comprehensive threat assessments and to detect defect dimensions. However, the ILI is very expensive and most of its costs are unnecessary since very few pipelines contain defects. Many previous studies have used machine learning (ML) methods to predict the safety of pipelines based on the features extracted from ILI signal results, which is very laborious and difficult to apply in industry. In this paper, the ILI results were predicted using multiple ML models through three prediction cases with only pipeline attributes and environmental features as input variables. In the first case, six ML methods were compared to predict whether there are defects in a pipeline section. The Catboost (CAT) method showed the best performance in all evaluation metrics with the highest certain prediction ratio (94%). The second case was using three ML methods to predict a defect depth, defect length, and defect width. The prediction accuracy of the defect depth was much higher than that of the defect length and defect width. A CAT model was the optimal model in this case due to its best performance in all the predictions. In the third prediction case, three ML methods were used to predict a defect length growth rate and defect depth growth rate based on different ILI results from different years. CAT was also the best method in this case with the highest accuracy. The predicted defect length growth rate and defect depth growth rate were used to calculate the remaining lifetime of pipelines based on the maximum allowable defect depth and failure pressure. The remaining lifetime of pipelines with different thickness, land use, and soil types was analyzed with changes in the specified minimum yield strength of a pipeline, a pipeline year, and maximum operating pressure. The accurate predictions in the three cases and the correlation analysis between input features and outputs helped company save a lot of costs and provided valuable information and suggestions in the further progress.

Structural Integrity of Steel Pipeline with Clusters of Corrosion Defects.

The main goal of this paper is to evaluate the burst pressure and structural integrity of a steel pipeline based on in-line inspection results, in respect to the grouping criteria of closely spaced volumetric surface features. In the study, special attention is paid to evaluation of data provided from the diagnostics using an axial excitation magnetic flux leakage technology in respect to multiple defects grouping. Standardized clustering rules were applied to the corrosion pits taken from an in-line inspection of the gas transmission pipeline. Basic rules of interaction of pipe wall metal losses are expressed in terms of longitudinal and circumferential spacing of the features in the colony. The effect of interactions of the detected anomalies on the tube residual strength evaluated according to the Det Norske Veritas Recommended practice was investigated in the current study. In the presented case, groups of closely-spaced defects behaved similarly as individual flaws with regard to their influence on burst pressure and pipeline failure probability.

Внедрение показателя техногенного риска с целью определения приоритетности воздействий на объекты линейной части магистральных газопроводов с учетом результатов внутритрубного технического диагностирования

Внедрение показателя техногенного риска с целью определения приоритетности воздействий на объекты линейной части магистральных газопроводов с учетом результатов внутритрубного технического диагностирования

Pipeline life extension and integrity management based on optimized use of above ground survey data and inline inspection results

We present a detailed description of probabilistic methodologies based on Bayesian updating and structural reliability analysis for optimizing survey and/or inspection frequencies in a way that provides cost-effective solutions for ongoing integrity management or indeed for life extension or pressure uprating. A full description of the method is provided and the application of the techniques is clearly illustrated through case studies.