In modern industry, one element plays a crucial operation: artificial lift systems. Among these, one stands out among other methods: Electric Submersible Pumps (ESPs). By providing more demanding and technically complex solutions, particularly in heavy oil and carbonated formations, their use has gained importance. By using predictive maintenance driven by real-time analytics, these systems can operate effectively, reducing the likelihood of premature failure and thus prolonging their lifespan. Furthermore, with advances in technology, we can now leverage artificial intelligence for failure prediction, improving the operational durability of ESPs. In this research article, we will explore how the integration of machine learning algorithms with real-time data analytics and proactive maintenance strategies can improve the performance and durability of ESPs at ADNOC's offshore facilities. As a result of the joint venture of the UAE's state-owned oil company, Abu Dhabi National Oil Company (ADNOC) and Group 42 Energy LLC (G42), an Abu Dhabi-based artificial intelligence company and a leader in cloud computing services, Artificial Intelligence & Intelligence Quotient company has been created, proposing the implementation of its open solutions development platform, E-Novus, to address Electrical Submersible Pump equipment solutions. ADNOC Offshore is producing oil from an offshore oilfield located in Abu Dhabi, classified as a complex carbonate limestone reservoir with a significant underlying aquifer.
Alsaeedi et al. (2025) studied this question.