Advertisement
Published in:
2017 | OriginalPaper | Chapter
A Heuristic Method to Optimize High-Dimensional Expensive Problems: Application to the Dynamic Optimization of a Waste Water Treatment Plant
Authors : Alberto Garre, Pablo S. Fernandez, Julio R. Banga, Jose A. Egea
Published in: Progress in Industrial Mathematics at ECMI 2016
Publisher: Springer International Publishing
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
The mathematical description of industrial processes usually requires the use of models consisting of large systems of differential and algebraic equations. The numerical simulations of such models may lead to high computation times, therefore, making optimization unaffordable using classical optimization methods.
This contribution describes an evolutionary approach for the optimization of computationally expensive, highly dimensional problems. The performance of the algorithm has been compared against well known surrogate based optimization methods using classical benchmark functions. The results show that our method outperforms the reference methods, specially for the high dimensional case.
The proposed algorithm has been applied to the optimization of the operation parameters of a waste water treatment plant, using dynamic profiles. The algorithm has been able to produce better solutions than those obtained previously using static profiles.