The Study of Artificial Intelligent in Risk-Based Inspection Assessment and Screening: A Study Case of Inline Inspection

Abstract

The work reports the systematic approach to the study of Artificial Intelligence (AI) in addressing the complexity of ILI data management to forecast the risk in natural gas pipelines. A recent conventional standard may not be sufficient to address the variation data of corrosion defects and inherent human subjectivity. Such methodology undermines the accuracy assessment confidence and is ineffective in reducing inspection costs. In this work, a combination of Unsupervised and Supervised Machine Learning and Deep Learning has profoundly accelerated the Probability of Failure (PoF) assessment and analysis. K-Means Clustering and Gaussian Mixture Models show direct relevance between the corrosion depth and corrosion rate, while the overlapping PoF value is scattered in three clusters. Logistic Regression, Support Vector Machine, k-Nearest Neighbors, and ensemble classifiers of AdaBoost, Random Forest, and Gradient Boosting are constructed using particular features, labels, and hyperparameters. The algorithm correctly predicted the score of PoF from 4790 instances and confirmed the 25% metal loss at a location of 13.399 m. The Artificial Neural Network is designed with various layers (input, hidden, and output) architecture. It is optimized using an activation function to predict that 74% of the pipeline's anomalies that classified at low-medium and medium-high risk. Furthermore, it provides a quick and precise prediction about the external defects at 13.1 m and requires the personnel to conduct wrapping composite. This work can be used as a standard guideline for risk assessment based on ILI and applies to industry and academia.

Development of risk-based inspection of 28-years-old subsea sales gas pipelines to support the energy demand

“…Based on (6), A corresponds to the impacted area, and X is the continuous leakage rate and instantaneous leakage mass. The variables a and b are specified in the API 581 standard for the reference fluid of the API 581 standard handbook.…”

“…A company must reduce the hazard and impact of the risk posed in the event of a failure by implementing preventive steps to ensure that the pipeline's operation is maintained and safe in a more effective manner. The Risk-Based Inspection (RBI) method is one strategy that is thought to be effective in maintaining pipeline integrity [6,7]. Compared to the Time-Based Inspection approach, RBI is a method for developing an inspection plan based on the probability of failure during equipment operation and the impact if a failure occurs.…”

Insight on Corrosion Prevention of C1018 in 1.0 M Hydrochloric Acid Using Liquid Smoke of Rice Husk Ash: Electrochemical, Surface Analysis, and Deep Learning Studies

“…Specifically, developing a deep learning model in corrosion mitigation has not been fully explored. Deep learning is the subset of machine learning that has been used successfully across various applications, including corrosion detection [18] and the risk assessment of pipelines [19]. Inclusively in the field of corrosion science, the application of artificial intelligence has been found on many fronts.…”

Integrating the root cause analysis to machine learning interpretation for predicting future failure

“…At the same time, regular pigging before corrosion inhibitor [ [14] , [15] , [16] ] injection is more effective in maintaining the integrity of pipelines. Recently, a study [ 17 ] showed that the tools are effective in acquiring the condition of internal corrosion due to the lack of a scrubber of the dehydration system. However, the relationship between the features of ILI inspection and the effect of CO 2 in the gas pipelines was ignored.…”