publication . Conference object . 2020

Combining Physics-Based and Data-Driven Modeling for Pressure Prediction in Well Construction

Oney Erge; Eric van Oort;
Open Access
  • Published: 24 Jun 2020
  • Publisher: SciPy
Abstract
This poster introduces a novel framework to combine the physics-based and data-driven modeling, aiming to attain the best features of both approaches for well construction. Gaussian processes, neural networks and deep learning models are trained and executed together with a physics model that is directly derived using the first principles. Then the results are combined through a decision-making algorithm, a hidden Markov model. The approach is tested within the scope of wellbore hydraulics on a dataset from an actual drilling operation. The results suggest the proposed approach has a good potential to allow safer, optimized drilling operations.
Subjects
free text keywords: Deep Learning, Machine Learning, Combining Physics-Based Modeling and Data-Driven Modeling, Hydraulics Modeling, Frictional Pressure Loss Modeling., Deep Learning, Machine Learning, Combining Physics-Based Modeling and Data-Driven Modeling, Hydraulics Modeling, Frictional Pressure Loss Modeling., Physics based, Data-driven, Control engineering, Computer science
Download fromView all 3 versions
Open Access
Zenodo
Conference object . 2020
Provider: Datacite
Open Access
ZENODO
Conference object . 2020
Provider: ZENODO
Open Access
Zenodo
Conference object . 2020
Provider: Datacite
Any information missing or wrong?Report an Issue