English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In recent years, the use of machine learning-based surrogate models forcomputational fluid dynamics (CFD) simulations has emerged as a promisingtechnique for reducing the computational cost associated with engine designoptimization. However, such methods still suffer from drawbacks. One maindisadvantage of is that the default machine learning (ML) hyperparameters areoften severely suboptimal for a given problem. This has often been addressed bymanually trying out different hyperparameter settings, but this solution isineffective in a high-dimensional hyperparameter space. Besides this problem,the amount of data needed for training is also not known a priori. In responseto these issues that need to be addressed, the present work describes andvalidates an automated active learning approach, AutoML-GA, for surrogate-basedoptimization of internal combustion engines. In this approach, a Bayesianoptimization technique is used to find the best machine learninghyperparameters based on an initial dataset obtained from a small number of CFDsimulations. Subsequently, a genetic algorithm is employed to locate the designoptimum on the ML surrogate surface. In the vicinity of the design optimum, thesolution is refined by repeatedly running CFD simulations at the projectedoptimum and adding the newly obtained data to the training dataset. It isdemonstrated that AutoML-GA leads to a better optimum with a lower number ofCFD simulations, compared to the use of default hyperparameters. The proposedframework offers the advantage of being a more hands-off approach that can bereadily utilized by researchers and engineers in industry who do not haveextensive machine learning expertise.

Application of an automated machine learning-genetic algorithm  (AutoML-GA) coupled with computational fluid dynamics simulations for rapid  engine design optimization