{"title":"通过数据驱动方法提高燃气轮机应用过渡模型的准确性","authors":"Harshal D. Akolekar","doi":"arxiv-2409.07803","DOIUrl":null,"url":null,"abstract":"Separated flow transition is a very popular phenomenon in gas turbines,\nespecially low-pressure turbines (LPT). Low-fidelity simulations are often used\nfor gas turbine design. However, they are unable to predict separated flow\ntransition accurately. To improve the separated flow transition prediction for\nLPTs, the empirical relations that are derived for transition prediction need\nto be significantly modified. To achieve this, machine learning approaches are\nused to investigate a large number of functional forms using computational\nfluid dynamics-driven gene expression programming. These functional forms are\ninvestigated using a multi-expression multi-objective algorithm in terms of\nseparation onset, transition onset, separation bubble length, wall shear\nstress, and pressure coefficient. The models generated after 177 generations\nshow significant improvements over the baseline result in terms of the above\nparameters. All of the models developed improve the wall shear stress\nprediction by 40-70\\% over the baseline laminar kinetic energy model. This\nmethod has immense potential to improve boundary layer transition prediction\nfor gas turbine applications across several geometries and operating\nconditions.","PeriodicalId":501125,"journal":{"name":"arXiv - PHYS - Fluid Dynamics","volume":"273 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Enhancing Accuracy of Transition Models for Gas Turbine Applications Through Data-Driven Approaches\",\"authors\":\"Harshal D. Akolekar\",\"doi\":\"arxiv-2409.07803\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Separated flow transition is a very popular phenomenon in gas turbines,\\nespecially low-pressure turbines (LPT). Low-fidelity simulations are often used\\nfor gas turbine design. However, they are unable to predict separated flow\\ntransition accurately. To improve the separated flow transition prediction for\\nLPTs, the empirical relations that are derived for transition prediction need\\nto be significantly modified. To achieve this, machine learning approaches are\\nused to investigate a large number of functional forms using computational\\nfluid dynamics-driven gene expression programming. These functional forms are\\ninvestigated using a multi-expression multi-objective algorithm in terms of\\nseparation onset, transition onset, separation bubble length, wall shear\\nstress, and pressure coefficient. The models generated after 177 generations\\nshow significant improvements over the baseline result in terms of the above\\nparameters. All of the models developed improve the wall shear stress\\nprediction by 40-70\\\\% over the baseline laminar kinetic energy model. This\\nmethod has immense potential to improve boundary layer transition prediction\\nfor gas turbine applications across several geometries and operating\\nconditions.\",\"PeriodicalId\":501125,\"journal\":{\"name\":\"arXiv - PHYS - Fluid Dynamics\",\"volume\":\"273 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Fluid Dynamics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.07803\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Fluid Dynamics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.07803","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Enhancing Accuracy of Transition Models for Gas Turbine Applications Through Data-Driven Approaches
Separated flow transition is a very popular phenomenon in gas turbines,
especially low-pressure turbines (LPT). Low-fidelity simulations are often used
for gas turbine design. However, they are unable to predict separated flow
transition accurately. To improve the separated flow transition prediction for
LPTs, the empirical relations that are derived for transition prediction need
to be significantly modified. To achieve this, machine learning approaches are
used to investigate a large number of functional forms using computational
fluid dynamics-driven gene expression programming. These functional forms are
investigated using a multi-expression multi-objective algorithm in terms of
separation onset, transition onset, separation bubble length, wall shear
stress, and pressure coefficient. The models generated after 177 generations
show significant improvements over the baseline result in terms of the above
parameters. All of the models developed improve the wall shear stress
prediction by 40-70\% over the baseline laminar kinetic energy model. This
method has immense potential to improve boundary layer transition prediction
for gas turbine applications across several geometries and operating
conditions.