no code implementations • 9 Apr 2024 • Christine Foss Sjulstad, Danielle Monteiro, Bjarne Grimstad
In this paper, we highlight that a combination of statistical tests and supporting logic for gross error detection and elimination can be beneficial in obtaining a more justifiable production allocation.
no code implementations • 27 Sep 2023 • Bjarne Grimstad, Kristian Løvland, Lars S. Imsland
Using a large industrial dataset, we demonstrate that, when the soft sensor is learned from a sufficient number of tasks, it permits few-shot learning on data from new units.
no code implementations • 13 Apr 2023 • Anders T. Sandnes, Bjarne Grimstad, Odd Kolbjørnsen
This paper presents a calibration method based on the measurement provided by the production separator, and the assumption that the observed flow should be equal to the sum of flow rates from each individual well.
no code implementations • 1 Mar 2023 • Anders T. Sandnes, Bjarne Grimstad, Odd Kolbjørnsen
It is a multi-task learning architecture based on a fully shared neural network and an augmented input vector containing trainable task parameters.
no code implementations • 10 Nov 2022 • Kristian Løvland, Bjarne Grimstad, Lars Struen Imsland
Steady-state models which have been learned from historical operational data may be unfit for model-based optimization unless correlations in the training data which are introduced by control are accounted for.
no code implementations • 7 Feb 2022 • Mathilde Hotvedt, Bjarne Grimstad, Lars Imsland
Nevertheless, the prediction performance of steady-state models typically degrades with time due to the inherent nonstationarity of the underlying process being modeled.
no code implementations • 23 Mar 2021 • Mathilde Hotvedt, Bjarne Grimstad, Dag Ljungquist, Lars Imsland
Nevertheless, the results are promising and indicate that gray-box VFMs may reduce the prediction error of a mechanistic VFM while remaining scientifically consistent.
no code implementations • 15 Mar 2021 • Anders T. Sandnes, Bjarne Grimstad, Odd Kolbjørnsen
Virtual flow metering (VFM) is a cost-effective and non-intrusive technology for inferring multiphase flow rates in petroleum assets.
1 code implementation • 2 Feb 2021 • Bjarne Grimstad, Mathilde Hotvedt, Anders T. Sandnes, Odd Kolbjørnsen, Lars S. Imsland
Recent works have presented promising results from the application of machine learning (ML) to the modeling of flow rates in oil and gas wells.
no code implementations • 7 Feb 2020 • Mathilde Hotvedt, Bjarne Grimstad, Lars Imsland
Virtual flow meters, mathematical models predicting production flow rates in petroleum assets, are useful aids in production monitoring and optimization.
no code implementations • 6 Jul 2019 • Bjarne Grimstad, Henrik Andersson
To this end, we devise and study several bound tightening procedures that consider both input and output bounds.