Blar i NTNU Open på forfatter "Grimstad, Bjarne Andre"
-
Bayesian neural networks for virtual flow metering: An empirical study
Grimstad, Bjarne Andre; Hotvedt, Mathilde; Sandnes, Anders Thoresen; Kolbjørnsen, Odd; Imsland, Lars Struen (Peer reviewed; Journal article, 2021)Recent works have presented promising results from the application of machine learning (ML) to the modeling of flow rates in oil and gas wells. Encouraging results and advantageous properties of ML models, such as ... -
Developing a Hybrid Data-Driven, Mechanistic Virtual Flow Meter - a Case Study
Hotvedt, Mathilde; Grimstad, Bjarne Andre; Imsland, Lars Struen (Peer reviewed; Journal article, 2021)Virtual flow meters, mathematical models predicting production flow rates in petroleum assets, are useful aids in production monitoring and optimization. Mechanistic models based on first-principles are most common, however, ... -
Hyperparameter Optimization for Neural Network-based Virtual Flow Metering
Eriksen, Knut Vågnes (Master thesis, 2022)Hyperparametere er parameterne som kontrollerer hvordan en maskinlæringsalgoritme lærer, og hyperparameteroptimalisering er prosessen med å optimalisere disse parameterne. Riktig valg av hyperparameter verdier er avgjørende ... -
Identifiability and physical interpretability of hybrid, gray-box models - a case study
Hotvedt, Mathilde; Grimstad, Bjarne Andre; Imsland, Lars Struen (Journal article; Peer reviewed, 2021)Model identifiability concerns the uniqueness of uncertain model parameters to be estimated from available process data and is often thought of as a prerequisite for the physical interpretability of a model. Nevertheless, ... -
Mathematical programming formulations for piecewise polynomial functions
Grimstad, Bjarne Andre; Knudsen, Brage Rugstad (Journal article; Peer reviewed, 2020)This paper studies mathematical programming formulations for solving optimization problems with piecewise polynomial (PWP) constraints. We elaborate on suitable polynomial bases as a means of efficiently representing PWPs ... -
Multi-task learning for virtual flow metering
Sandnes, Anders Thoresen; Grimstad, Bjarne Andre; Kolbjørnsen, Odd (Peer reviewed; Journal article, 2021)Virtual flow metering (VFM) is a cost-effective and non-intrusive technology for inferring multiphase flow rates in petroleum assets. Inferences about flow rates are fundamental to decision support systems that operators ... -
On gray-box modeling for virtual flow metering
Hotvedt, Mathilde; Grimstad, Bjarne Andre; Ljungquist, Dag; Imsland, Lars Struen (Journal article; Peer reviewed, 2021)A virtual flow meter (VFM) enables continuous prediction of flow rates in petroleum production systems. The predicted flow rates may aid the daily control and optimization of a petroleum asset. Gray-box modeling is an ... -
Passive learning to address nonstationarity in virtual flow metering applications
Hotvedt, Mathilde; Grimstad, Bjarne Andre; Imsland, Lars Struen (Peer reviewed; Journal article, 2022)Steady-state process models are common in virtual flow meter applications due to low computational complexity, and low model development and maintenance cost. Nevertheless, the prediction performance of steady-state models ... -
Quantifying Predictive Uncertainty in Artificial Neural Networks
Lehre, Christian Nilsen (Master thesis, 2021)To metoder for å konstruere Bayesianske nevrale nettverk, MC Dropout og SGVB, er implementert og anvendt på et reelt datasett levert av det norske E\&P selskapet Aker BP. Datasettet består av brønndata hentet fra 34 brønner ...