A Recent Review of Risk-Based Inspection Development to Support Service Excellence in the Oil and Gas Industry: An Artificial Intelligence Perspective

Abstract

Inspection and Maintenance methods development have a pivotal role in preventing the uncertainty-induced risks in the oil and gas industry. A key aspect of inspection is evaluating the risk of equipment from the scheduled and monitored assessment in the dynamic system. This activity includes assessing the modification factor's Probability of Failure (PoF) and calculating the equipment's remaining useful life (RUL). The traditional inspection model constitutes a partial solution to grouping the vast amount of real-data inspection and observations at equal intervals. This literature review aims to offer a comprehensive review concerning the benefit of Machine Learning (ML) in managing the risk while incorporating time-series forecasting studies and an overview of Risk-Based Inspection (RBI) methods (e.g. quantitative, semi-quantitative, and qualitative). A literature review with a deductive approach is used to discuss the improvement of the clustering Gaussian Mixture Model (GMM) to overcome the non-circular shape data that may show in the K-Means models. Machine Learning classifiers such as Decision Trees, Logistic Regression, Support Vector Machines, K-nearest neighbours, and Random Forests were selected to provide a platform for risk assessment and give a promising prediction towards the actual condition and their severity level of equipment. This work approaches complementary tools and grows interest in embedded artificial intelligence in Risk Management systems and can be used as the basis of more robust guidance to organize complexity in handling inspection data, but further and future research is required.