This course offers an introduction to multiphase flow and machine learning techniques, leading to the application of virtual flow metering. Virtual flow metering (VFM) is a method for estimating the flow rates from produced wells and pipelines without direct measurement. It relies on physics-based multiphase flow models, and more recently, machine learning using existing sensors, such as pressure and temperature.
Designed by NTNU's Department of Geosciences, this course is part of the MultiFlow SUITE research project and is currently under development. Learn more here
This course is aimed for bachelor, master, and Ph.D. students, researcher, and engineers with background in fluid mechanics and basic knowledge in programming
André is a Postdoctoral fellow at the Department of Geosciences (IGV) at NTNU. He holds a Ph.D. in mechanical engineering from the University of São Paulo and his research interest include multiphase flow and machine learning. The former focuses on physics-based modeling, flow pattern transition, and experimental work, and the latter on data-driven, hybrid, and stochastic machine learning.
Milan is an associate professor in production engineering and field development at the Department of Geosciences (IGV) at NTNU. He holds a Ph.D. in petroleum production engineering from NTNU and his research interest are modeling and experiments of production and injection systems (including CO2) and applications within design and operations.
No, this is an open course for bachelor, master, and Ph.D. students, interested professionals from the industry, and the general public.
The course is based on the Open edx platform and it works better with current versions of Chrome, Edge, Firefox, or Safari.
See our list of supported browsers for the most up-to-date information.
This course is free of charge, and open for enroll.