Hybridization of a multi-objective genetic algorithm, a neural network and a classical optimizer for a complex design problem in fluid dynamics

Poloni, Carlo; Giurgevich, A; Onesti, Luka; Pediroda, Valentino

doi:10.1016/s0045-7825(99)00394-1

Cited by 185 publications

(92 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The results presented in this paper were performed applying the MultiObjective Genetic Algorithm MOGA-II [9].MOGA II is an improved version of MOGA (Fonseca and Fleming [10]) and uses five different operators for reproduction: selection, classical cross-over, directional cross-over, mutation and elitism. At each step of the reproduction process, one of the five operators is chosen and applied to the current individual.…”

Section: Methodsmentioning

confidence: 99%

Design optimization of a bioreactor for ethanol production using CFD simulation and genetic algorithms

Góis

Seleghim

2011

Computational Methods and Experimental Measurements XV

View full text Add to dashboard Cite

The increase of the use of biofuels, like bioethanol, has presented new challenges to engineering problems. The optimization of bioreactors is crucial to improve the bioethanol extraction and to avoid stagnant zones in the flow that can compromise the chemical reactions involved in the process. This paper presents a solution using Computational Fluid Dynamics tools coupled with Genetics Algorithm to find an improved reactor structure. The preliminary results show that the influence of the height outlet tube alone is able to modify completely the flow pattern inside the reactor, improving the efficiency of the reactor.

show abstract

Section: Methodsmentioning

confidence: 99%

Design optimization of a bioreactor for ethanol production using CFD simulation and genetic algorithms

Góis

Seleghim

2011

Computational Methods and Experimental Measurements XV

View full text Add to dashboard Cite

show abstract

“…Airfoil shape optimization is a critical activity documented in a large number of scientific papers and particularly the design of airfoils for sailing yachts have some specificity as reported in [6,7] where the optimization of deformable composite wing was also described.…”

Section: Optimization Of a Flexible Trailing Edgementioning

confidence: 99%

A Passively Morphing Trailing Edge Concept for Sailing Hydrofoil

Hueber¹,

Caponnetto²,

Poloni³

2017

Preprint

Self Cite

View full text Add to dashboard Cite

Sailing sports are experiencing a period of radical innovations. Traditional displacing monohulls have always been the reference for yachting in the past, but the continuous quest for performances has generated many variations and many convergences with surprising results. On the aerodynamic side conventional soft sails have been sometime replaced by rigid wings, but the biggest innovation has been the use of traction kites as a propulsion device. On the hydrodynamic side we have seen the rapid growth of hydrofoils, an old concept that is having a rebirth. Probably the most remarkable expression of innovation and integration between concepts having different roots is the hydrofoil kite-board, point of encounter of the traditional wave surfing, the traction kite innovation and the hydrofoil technology. Hydrofoil kite-board can reach speeds up to 3 times the wind speed, are at least one order of magnitude cheaper than any boat with comparable performances, easy to manage and races are spectacular. Hydrofoil are object of investigation trying to further improve performances as well as to increase the stability and the "sailability". In the following we will present a concept that extends the range of efficiency of the foil through a completely passive morphing of the wing.

show abstract

“…SI vectors have been reported in numerous studies, with references such as "failure of the simulation code" (Poloni et al, 2000) or "attempts to evaluate the objective function failed" (Booker et al, 1999), while additional examples include the works by Büche et al (2005), Conn et al (1998), andOkabe (2007). Accordingly, several approaches have been explored to handle such SI vectors.…”

Section: 2mentioning

confidence: 99%

“…Numerous studies, such as those by Büche et al (2005), Jin et al (2002), and Poloni et al (2000), have reported encountering SI designs in simulation-driven problems, which indicates that the issue is both common and requires an effective strategy to address it. In these settings, this paper describes the integration of classifiers, borrowed from the domain of machine-learning, into the optimization search as a means of more effectively handling SI vectors.…”

mentioning

confidence: 99%

Machine–Learning in Optimization of Expensive Black–Box Functions

Tenne

2017

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

Modern engineering design optimization often uses computer simulations to evaluate candidate designs. For some of these designs the simulation can fail for an unknown reason, which in turn may hamper the optimization process. To handle such scenarios more effectively, this study proposes the integration of classifiers, borrowed from the domain of machine learning, into the optimization process. Several implementations of the proposed approach are described. An extensive set of numerical experiments shows that the proposed approach improves search effectiveness.

show abstract

Hybridization of a multi-objective genetic algorithm, a neural network and a classical optimizer for a complex design problem in fluid dynamics

Cited by 185 publications

References 6 publications

Design optimization of a bioreactor for ethanol production using CFD simulation and genetic algorithms

Design optimization of a bioreactor for ethanol production using CFD simulation and genetic algorithms

A Passively Morphing Trailing Edge Concept for Sailing Hydrofoil

Machine–Learning in Optimization of Expensive Black–Box Functions

Contact Info

Product

Resources

About