Affiliation:
1. PETRONAS Carigali Sdn. Bhd.
2. SLB
Abstract
Abstract
This paper discussed the operationalization effort of an automated and integrated Machine Learning (ML) system to support Production Enhancement (PE) opportunity generation and workflow processes driven by data analytics. The digital solution focuses on prescriptive engines to calculate variables such as potential gain, Locked-In-Potential (LIP) and behind casing potential using big data such as reservoir properties, historical production, well intervention history and petrophysics interpretation. Additionally, the solution provides constraint detection for each well using an Analytic Hierarchy Process (AHP) on conventional petroleum engineering workflows.
The objective of this paper is to demonstrate the operationalization effort that was utilized to gain the maximum value possible from the workflow by connecting people with this digital solution. The efforts are founded on the following three (3) key methodologies: 1) Operationalization, 2) Optimization, and 3) Value Creation.
This digital solution has enabled engineers to identify and rank PE opportunities more quickly and efficiently, leading to a potential increase in field production and recovery. Adopting this methodical approach which utilizes advanced data analytics and ML, automated and systematic PE opportunity has been made possible and this has given a positive impact on work process whereby engineers will have more time to focus on strategic and value-added activities, increasing workforce satisfaction and productivity. As of this report, this digital solution is currently available in over forty (40) different fields. The goal is to connect people with the enhanced workflow, which will make it possible for workforce upskilling and foster a better collaborative work environment to boost field productivity and work process efficiency.