{"id":8808,"date":"2024-01-22T09:15:07","date_gmt":"2024-01-22T08:15:07","guid":{"rendered":"https:\/\/cnrm.uniri.hr\/?page_id=8808"},"modified":"2024-01-22T09:30:26","modified_gmt":"2024-01-22T08:30:26","slug":"computationally-efficient-optimisation-of-elbow-type-draft-tube-using-neural-network-surrogates","status":"publish","type":"page","link":"https:\/\/cnrm.uniri.hr\/hr\/computationally-efficient-optimisation-of-elbow-type-draft-tube-using-neural-network-surrogates\/","title":{"rendered":"Computationally Efficient Optimisation of Elbow-Type Draft Tube Using Neural Network Surrogates"},"content":{"rendered":"<style>\nul {list-style-position: outside;text-align: justify;}\n<\/style>\n<p style=\"text-align: left;\"><strong><a href=\"https:\/\/arxiv.org\/abs\/2401.08700\">Sikirica, A., Lu\u010din, I., Alvir, M., Kranj\u010devi\u0107, L., \u010carija, Z.<\/p>\n<p>Computationally Efficient Optimisation of Elbow-Type Draft Tube Using Neural Network Surrogates<br \/>\narXiv, (2024), doi.org\/10.48550\/arXiv.2401.08700<\/a><\/strong><\/p>\n<p>&nbsp;<\/p>\n<p style=\"text-align: justify;\"><strong>Abstract:<\/strong> This study aims to provide a comprehensive assessment of single-objective and multi-objective optimisation algorithms for the design of an elbow-type draft tube, as well as to introduce a computationally efficient optimisation workflow. The proposed workflow leverages deep neural network surrogates trained on data obtained from numerical simulations. The use of surrogates allows for a more flexible and faster evaluation of novel designs. The success history-based adaptive differential evolution with linear reduction and the multi-objective evolutionary algorithm based on decomposition were identified as the best-performing algorithms and used to determine the influence of different objectives in the single-objective optimisation and their combined impact on the draft tube design in the multi-objective optimisation. The results for the single-objective algorithm are consistent with those of the multi-objective algorithm when the objectives are considered separately. Multi-objective approach, however, should typically be chosen, especially for computationally inexpensive surrogates. A multi-criteria decision analysis method was used to obtain optimal multi-objective results, showing an improvement of 1.5% and 17% for the pressure recovery factor and drag coefficient, respectively. The difference between the predictions and the numerical results is less than 0.5% for the pressure recovery factor and 3% for the drag coefficient. As the demand for renewable energy continues to increase, the relevance of data-driven optimisation workflows, as discussed in this study, will become increasingly important, especially in the context of global sustainability efforts.<\/p>\n<p><center><img decoding=\"async\" src=\"https:\/\/cnrm.uniri.hr\/upload\/2024\/01\/sikirica2024_arxiv2.png\" alt=\"\" width=\"750\" style=\"padding: 25px;\" \/><\/center><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Sikirica, A., Lu\u010din, I., Alvir, M., Kranj\u010devi\u0107, L., \u010carija, Z. Computationally Efficient Optimisation of Elbow-Type Draft Tube Using Neural Network Surrogates arXiv, (2024), doi.org\/10.48550\/arXiv.2401.08700 &nbsp; Abstract: This study aims to provide a comprehensive assessment of single-objective and multi-objective optimisation algorithms&hellip;&nbsp;<a href=\"https:\/\/cnrm.uniri.hr\/hr\/computationally-efficient-optimisation-of-elbow-type-draft-tube-using-neural-network-surrogates\/\" class=\"more-link\">Read More<\/a><\/p>\n","protected":false},"author":17,"featured_media":8815,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"templates\/builder.php","meta":{"_links_to":"","_links_to_target":""},"categories":[26],"tags":[],"_links":{"self":[{"href":"https:\/\/cnrm.uniri.hr\/hr\/wp-json\/wp\/v2\/pages\/8808"}],"collection":[{"href":"https:\/\/cnrm.uniri.hr\/hr\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/cnrm.uniri.hr\/hr\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/cnrm.uniri.hr\/hr\/wp-json\/wp\/v2\/users\/17"}],"replies":[{"embeddable":true,"href":"https:\/\/cnrm.uniri.hr\/hr\/wp-json\/wp\/v2\/comments?post=8808"}],"version-history":[{"count":2,"href":"https:\/\/cnrm.uniri.hr\/hr\/wp-json\/wp\/v2\/pages\/8808\/revisions"}],"predecessor-version":[{"id":8819,"href":"https:\/\/cnrm.uniri.hr\/hr\/wp-json\/wp\/v2\/pages\/8808\/revisions\/8819"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cnrm.uniri.hr\/hr\/wp-json\/wp\/v2\/media\/8815"}],"wp:attachment":[{"href":"https:\/\/cnrm.uniri.hr\/hr\/wp-json\/wp\/v2\/media?parent=8808"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cnrm.uniri.hr\/hr\/wp-json\/wp\/v2\/categories?post=8808"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cnrm.uniri.hr\/hr\/wp-json\/wp\/v2\/tags?post=8808"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}