Browsing SINTEF Open by Author "Silva, Thiago Lima"
Now showing items 1-5 of 5
-
Derivative-free trust region optimization for robust well control under geological uncertainty
Silva, Thiago Lima; Bellout, Mathias; Giuliani, Caio M.; Camponogara, Eduardo; Pavlov, Alexey (Peer reviewed; Journal article, 2022)A Derivative-Free Trust-Region (DFTR) algorithm is proposed to solve the robust well control optimization problem under geological uncertainty. Derivative-Free (DF) methods are often a practical alternative when gradients ... -
Efficient well placement optimization under uncertainty using a virtual drilling procedure
Kristoffersen, Brage Strand; Silva, Thiago Lima; Bellout, Mathias; Berg, Carl Fredrik (Peer reviewed; Journal article, 2021)An Automatic Well Planner (AWP) is used to efficiently adjust pre-determined well paths to honor near-well properties and increase overall production. AWP replicates modern geosteering decision-making where adjustments to ... -
Formulations for automatic optimization of decommissioning timing in offshore oil and gas field development planning
Lei, Guowen; Stanko, Milan; Silva, Thiago Lima (Peer reviewed; Journal article, 2022)A mathematical programming formulation has been developed to optimize the drilling program, the production allocation, and the decommissioning time in early-stage field development planning. Various abandonment constraints ... -
Nondisturbing extremum seeking control for multi-agent industrial systems
Haring, Mark A. M.; Fossøy, Synne; Silva, Thiago Lima; Pavlov, Alexey (Peer reviewed; Journal article, 2022)Industrial applications of extremum seeking control (ESC) can be a hit and miss affair. Although a gain in performance can be achieved, the dither applied to excite the system causes unwanted fluctuations in the performance ... -
Reduced well path parameterization for optimization problems through machine learning
Kristoffersen, Brage Strand; Bellout, Mathias; Silva, Thiago Lima; Berg, Carl Fredrik (Peer reviewed; Journal article, 2021)In this work we apply a recently developed machine learning routine for automatic well planning to simplify well parameterization in reservoir simulation models. This reduced-order parameterization is shown to be beneficial ...