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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This study aims to provide a comprehensive assessment of single-objective andmulti-objective optimisation algorithms for the design of an elbow-type drafttube, as well as to introduce a computationally efficient optimisationworkflow. The proposed workflow leverages deep neural network surrogatestrained on data obtained from numerical simulations. The use of surrogatesallows for a more flexible and faster evaluation of novel designs. The successhistory-based adaptive differential evolution with linear reduction and themulti-objective evolutionary algorithm based on decomposition were identifiedas the best-performing algorithms and used to determine the influence ofdifferent objectives in the single-objective optimisation and their combinedimpact on the draft tube design in the multi-objective optimisation. Theresults for the single-objective algorithm are consistent with those of themulti-objective algorithm when the objectives are considered separately.Multi-objective approach, however, should typically be chosen, especially forcomputationally inexpensive surrogates. A multi-criteria decision analysismethod was used to obtain optimal multi-objective results, showing animprovement of 1.5% and 17% for the pressure recovery factor and dragcoefficient, respectively. The difference between the predictions and thenumerical results is less than 0.5% for the pressure recovery factor and 3% forthe drag coefficient. As the demand for renewable energy continues to increase,the relevance of data-driven optimisation workflows, as discussed in thisstudy, will become increasingly important, especially in the context of globalsustainability efforts.

Computationally Efficient Optimisation of Elbow-Type Draft Tube Using Neural Network Surrogates