This paper deals with the development of effective techniques to automatically obtain the optimum management of petroleum fields aiming to increase the oil production during a given concession period of exploration. The optimization formulations of such a problem turn out to be highly multimodal, and may involve constraints. In this paper, we develop a robust particle swarm algorithm coupled with a novel adaptive constraint-handling technique to search for the global optimum of these formulations. However, this is a population-based method, which therefore requires a high number of evaluations of an objective function. Since the performance evaluation of a given management scheme requires a computationally expensive high-fidelity simulation, it is not practicable to use it directly to guide the search. In order to overcome this drawback, a Kriging surrogate model is used, which is trained offline via evaluations of a High-Fidelity simulator on a number of sample points. The optimizer then seeks the optimum of the surrogate model.
|Number of pages||22|
|Journal||Applied Soft Computing|
|Early online date||28 May 2015|
|Publication status||Published - Sept 2015|
Bibliographical noteNOTICE: this is the author’s version of a work that was accepted for publication in Applied Soft Computing. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Applied Soft Computing, 34 (2015)] DOI: 10.1016/j.asoc.2015.05.032
© 2015, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/
- Adaptive constraint handling
- Global search
- Particle swarm
- Reservoir simulation
- Surrogate-based optimization
- Waterflooding management
FingerprintDive into the research topics of 'Particle swarm algorithm with adaptive constraint handling and integrated surrogate model for the management of petroleum fields'. Together they form a unique fingerprint.
- Centre for Future Transport and Cities - Assistant Professor Academic
Person: Teaching and Research