Key points are not available for this paper at this time.
Abstract The assets and infrastructure of offshore oil and gas platforms, such as pipelines, operate in harsh environments and often require frequent maintenance for sustained operation. The conventional asset management protocols, such as pigging, aerial and surface inspection, and ultrasonic testing, are resource-intensive and often reactive, leading to high operational costs and unplanned downtime. In this context, the capabilities of artificial intelligence (AI) can be effectively leveraged to manage these assets efficiently and economically. This paper investigates the recent advances in AI-driven asset management to enhance the reliability, safety, and cost-effectiveness of offshore oil and gas pipeline asset management. The study begins with mapping recent research on AI applications in oil and gas pipeline management using citational network analysis. Eight key thematic clusters were identified, each highlighting specific research areas and future directions. Based on these insights, a structured AI-based asset integrity management system is proposed for oil and gas infrastructure, including pipelines, accounting for practical implementation considerations such as system integration, data reliability, and regional constraints. The system is structured into three phases: operational asset integrity management, asset life extension, and AI-driven applications. This approach integrates both qualitative and quantitative methods, utilizing real-time data analytics, machine learning, and predictive modeling. The proposed protocols are designed to be a practical and affordable roadmap for achieving continuous, reliable and safe integrity management supported by real-time analytical and economic justification. While the framework offers broader applicability, regional environmental factors and data variability may require adjustments to suit specific contexts.
Raj et al. (Tue,) studied this question.