Energy pipeline degradation condition assessment using predictive analytics – challenges, issues, and future directions

Abstract

It is of paramount importance to ensure the safe operation of energy pipelines for pipeline owners and operators. Therefore, effective condition assessment of pipelines is imperative. For this purpose, there are a great number of models developed using various techniques. How to select a modeling approach and associated techniques to get the most of the effectiveness of the model under a condition with limited monitoring data and experience remains a big concern to pipeline operators.This paper provides a comprehensive review of the developed approaches and techniques for energy pipeline degradation condition assessment. The primary motivation behind this review is the pivotal role of condition assessment in energy pipeline integrity management and the proliferation of models and techniques, including statistical modeling, stochastic processes, machine learning, and deep learning, used for assessing pipeline degradation. This work aims to identify and assess the challenges and gaps inherent in the utilization of these condition modeling approaches. By systematically analyzing the current state of research and practice, this review not only highlights the strengths and limitations of various modeling approaches but also offers insights into future opportunities for enhancing the research and management practice in the field of pipeline integrity management.Our analysis offers valuable insights for researchers, practitioners, and policymakers in the domain of pipeline integrity management. It facilitates a better understanding of the complexities and intricacies of condition assessment, ultimately contributing to the development of more robust and effective strategies for safeguarding the integrity of energy pipelines.

Keywords

• Corrosion management
• Degradation modeling
• Machine learning
• Pipeline condition assessment
• Pipeline integrity management