Artificial Intelligence–Driven Asset Optimizer

Abstract

Currently, as oil and gas companies continue to face risk of volatility in oil prices, production optimization and maintenance play a critical role in driving operational excellence for the industry while maintaining good profit margins. E&P companies must maintain a focus on reducing unit cost/barrel. This can be achieved by reducing operating costs, increasing production, and reducing downtime. We propose a recommendation engine driven by artificial intelligence (AI) that seamlessly integrates subsurface information and production characteristics for knowledge extraction needed to optimize production operations across conventional and unconventional assets. We used a three-phase approach to designing and building an advisory system that ingests data, learns patterns, and feeds these learnings from the data into different functional workflows necessary for improving the efficiency and effectiveness of production operations. The system uses these mechanisms of knowledge extraction, statistical learning, and contextual adaptation as it evolves into an autonomous asset optimization system that can proactively recommend actions for effective decision making to lower the unit cost/barrel.