Session: 11-10-01 Digitalization of Subsurface Wells Systems, Subsea Systems and Operations

Paper Number: 121766

121766 - Develop Ai-Aid Drilling Enviroment via Micro Service Systems 

In the dynamic realm of modern drilling operations, the increasing demand for efficient and accurate advisory and decision-making has led to the integration of Artificial Intelligence (AI) techniques into drilling data analytics. This paper presents a comprehensive software architecture designed to facilitate real-time drilling data analytics using AI technologies.

In this study, an AI-aid drilling environment has been developed with micro-service systems.  Micro-service architecture plays a crucial role in real-time operations by providing a flexible and scalable framework for managing various AI components and services. It allows for the modularization of AI algorithms and data processing tasks, enabling easy integration of new AI models and technologies as they evolve. Moreover, micro-services facilitate real-time data exchange and communication between different AI modules, ensuring smooth coordination and collaboration among them, ultimately improving overall performance and adaptability.

The proposed architecture harnesses the power of AI algorithms to manage and interpret real-time data streams measured during drilling operations instantaneously. By leveraging machine learning models and data-driven technologies, the architecture empowers drilling engineers to make informed decisions promptly, enhancing operational efficiency and minimizing downtime.  The paper outlines its key components, including data acquisition, storage, preprocessing, feature engineering, integration of AI models, and the critical stages of result visualization and validation. It also provides comprehensive documentation for the development of application programming interfaces (APIs) to facilitate data communication. Notably, the architecture underscores its adaptability and scalability, emphasizing its ability to a wide range of drilling scenarios and accommodate various AI methodologies.

The effectiveness of the proposed software architecture is demonstrated through several drilling scenarios, showcasing its ability to enhance decision-making processes, reduce downtime, accurate predictions, and improve overall drilling efficiency. By presenting a holistic approach to integrating AI into drilling operations,  our work contributes to the advancement of intelligent drilling systems and shows the transformative potential of AI in the energy sector.

Presenting Author: Hamed Sahebi University of Stavanger

Presenting Author Biography: Mr. Hamed Sahebi holds a master's degree in drilling technology from the University of Stavanger. He has been participating in several research projects about drilling digitalization, optimization, and software development since 2020. Currently, he is a researcher in the UiS working on microservice development for drilling real-time data analysis.

Authors:

Hamed Sahebi University of Stavanger
Dan Sui University of Stavanger