Huan Yang, Shu Guo, Haolin Xie, Jian Wen, Jiarui Wang
{"title":"Evaluation of machine learning models for predicting performance metrics of aero-engine combustors","authors":"Huan Yang, Shu Guo, Haolin Xie, Jian Wen, Jiarui Wang","doi":"10.1016/j.csite.2024.105627","DOIUrl":null,"url":null,"abstract":"As environmental standards tighten and aero-engine performance improves, credible mapping between structural parameters and performance metrics is crucial for optimizing combustion chamber design. A new consolidated dataset with 46 various geometric structures for lean premixed prevaporized combustors is established based on the numerical simulation. The prediction performance of six machine learning models is evaluated for key combustor metrics, including the overall temperature distribution factor (OTDF), radial temperature distribution factor (RTDF), total pressure loss (Δ<ce:italic>P</ce:italic>), and cooling effect evaluation index (<ce:italic>R</ce:italic><ce:inf loc=\"post\">t</ce:inf>). The Extra Tree model exhibits superior predictive accuracy for various combustor performance metrics. It achieves the mean absolute percentage error values of 5.70 % and 6.33 % for OTDF and RTDF, respectively. For total pressure loss Δ<ce:italic>P</ce:italic>, the Extra Tree demonstrates a mean absolute percentage error of 1.62 % and an R-Square value of 0.9971. For the cooling effect evaluation index <ce:italic>R</ce:italic><ce:inf loc=\"post\">t</ce:inf>, the Extra Tree achieves a mean absolute percentage error of 14.07 %. The Support Vector Machine model is not recommended for predicting combustor performance metrics. Feature importance analysis indicates that the cooling hole diameter and the third-stage swirler angle significantly impact combustor performance. The findings highlight the promise of machine learning in optimizing combustor design and improving the reliability of the aero-engine.","PeriodicalId":9658,"journal":{"name":"Case Studies in Thermal Engineering","volume":"30 1","pages":""},"PeriodicalIF":6.4000,"publicationDate":"2024-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Case Studies in Thermal Engineering","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1016/j.csite.2024.105627","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"THERMODYNAMICS","Score":null,"Total":0}
引用次数: 0
Abstract
As environmental standards tighten and aero-engine performance improves, credible mapping between structural parameters and performance metrics is crucial for optimizing combustion chamber design. A new consolidated dataset with 46 various geometric structures for lean premixed prevaporized combustors is established based on the numerical simulation. The prediction performance of six machine learning models is evaluated for key combustor metrics, including the overall temperature distribution factor (OTDF), radial temperature distribution factor (RTDF), total pressure loss (ΔP), and cooling effect evaluation index (Rt). The Extra Tree model exhibits superior predictive accuracy for various combustor performance metrics. It achieves the mean absolute percentage error values of 5.70 % and 6.33 % for OTDF and RTDF, respectively. For total pressure loss ΔP, the Extra Tree demonstrates a mean absolute percentage error of 1.62 % and an R-Square value of 0.9971. For the cooling effect evaluation index Rt, the Extra Tree achieves a mean absolute percentage error of 14.07 %. The Support Vector Machine model is not recommended for predicting combustor performance metrics. Feature importance analysis indicates that the cooling hole diameter and the third-stage swirler angle significantly impact combustor performance. The findings highlight the promise of machine learning in optimizing combustor design and improving the reliability of the aero-engine.
期刊介绍:
Case Studies in Thermal Engineering provides a forum for the rapid publication of short, structured Case Studies in Thermal Engineering and related Short Communications. It provides an essential compendium of case studies for researchers and practitioners in the field of thermal engineering and others who are interested in aspects of thermal engineering cases that could affect other engineering processes. The journal not only publishes new and novel case studies, but also provides a forum for the publication of high quality descriptions of classic thermal engineering problems. The scope of the journal includes case studies of thermal engineering problems in components, devices and systems using existing experimental and numerical techniques in the areas of mechanical, aerospace, chemical, medical, thermal management for electronics, heat exchangers, regeneration, solar thermal energy, thermal storage, building energy conservation, and power generation. Case studies of thermal problems in other areas will also be considered.