Adoption of big data analytics for energy pipeline condition assessment - A systematic review

Due to complexity, the oil and gas industry use various sensors to collect data for analysis to maintain the safety and integrity of pipelines and associated infrastructures. There is an enormous amount of data available to conceal crucial information, including precursor data on failure modes and knowledge that may be analyzed. The availability of large amounts of data has enabled the development of analytical tools that integrate methods like predictive analytics using different decision-making models, artificial intelligence (AI), and machine learning. These tools are crucial for managing pipeline conditions, preventing unwarranted failures, enhancing asset performance, availability, and decision-making. Big data analytics enables energy companies to implement a proactive approach to pipeline condition assessment. By integrating real-time data from sensors embedded in pipelines, weather conditions, and maintenance records, it becomes possible to detect potential issues and predict anomalies. The application of big data analytics in the energy pipeline industry is still at its early stage, although literature review discusses big data in oil and gas, however, the application's specific relevance to energy pipeline integrity and condition assessment has been largely unexplored. Therefore, this study addresses the applications of big data analytics in energy pipeline condition assessment by investigating the challenges and benefits. Collaboration among pipeline operators, data scientists, and technology providers were emphasized for successful adoption. The study envisions a future where big data analytics will be crucial in enhancing pipeline safety, efficiency, availability, integrity, and reliability. Recommendations for further research were also provided, culminating in a proposed conceptual framework for adopting big data analytics in the oil and gas pipeline industry.