Predicting heat transfer of wedged latticework cooling structure under high thermal load using GA-BP neural network

IF 4.9 2区工程技术 Q1 ENGINEERING, MECHANICAL

International Journal of Thermal Sciences Pub Date : 2025-06-23 DOI:10.1016/j.ijthermalsci.2025.110100

Binye Yu , Xingwei Li , Jie Li , Shi Bu , Ao Wang , Weigang Xu

{"title":"Predicting heat transfer of wedged latticework cooling structure under high thermal load using GA-BP neural network","authors":"Binye Yu , Xingwei Li , Jie Li , Shi Bu , Ao Wang , Weigang Xu","doi":"10.1016/j.ijthermalsci.2025.110100","DOIUrl":null,"url":null,"abstract":"<div><div>Wedged latticework is a competitive cooling scheme to resolve the ultra-high thermal load in the trailing edge of modern gas turbine blade. Its performance is closely related to numerous structural parameters, making heat transfer prediction a complicated issue. This paper built a GA-BP neural network for the purpose of fast predicting heat transfer coefficient of wedged latticework cooling channel. Upon analyzing the influence of wedge angle (<em>α</em>), rib-cross angle (<em>β</em>), rib-to-spacing ratio (<em>t</em>/<em>W</em><sub><em>t</em></sub>) and height of channel entrance (<em>H</em><sub>1</sub>) on heat transfer coefficient <em>h</em>, an orthogonal design database is established which is then used as the training set to optimize the BP network based on genetic algorithm (GA). The network is validated by experimental measurement on a wind tunnel test facility. The results indicated that GA-BP network can reach an accuracy of 91.200 %, better than the 87.689 % accuracy of BP network. Furthermore, the proposed GA-BP network owns superior model stability and generalization, making faster heat transfer prediction and more convenient cooling design.</div></div>","PeriodicalId":341,"journal":{"name":"International Journal of Thermal Sciences","volume":"217 ","pages":"Article 110100"},"PeriodicalIF":4.9000,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Thermal Sciences","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1290072925004235","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MECHANICAL","Score":null,"Total":0}

引用次数: 0

Abstract

Wedged latticework is a competitive cooling scheme to resolve the ultra-high thermal load in the trailing edge of modern gas turbine blade. Its performance is closely related to numerous structural parameters, making heat transfer prediction a complicated issue. This paper built a GA-BP neural network for the purpose of fast predicting heat transfer coefficient of wedged latticework cooling channel. Upon analyzing the influence of wedge angle (α), rib-cross angle (β), rib-to-spacing ratio (t/W_t) and height of channel entrance (H₁) on heat transfer coefficient h, an orthogonal design database is established which is then used as the training set to optimize the BP network based on genetic algorithm (GA). The network is validated by experimental measurement on a wind tunnel test facility. The results indicated that GA-BP network can reach an accuracy of 91.200 %, better than the 87.689 % accuracy of BP network. Furthermore, the proposed GA-BP network owns superior model stability and generalization, making faster heat transfer prediction and more convenient cooling design.

查看原文本刊更多论文

基于GA-BP神经网络的高热负荷楔格冷却结构传热预测

楔形格网是解决现代燃气轮机叶片尾缘超高热负荷的一种极具竞争力的冷却方案。它的性能与许多结构参数密切相关，使传热预测成为一个复杂的问题。为了快速预测楔形格子冷却通道的换热系数，本文建立了GA-BP神经网络。通过分析楔形角（α）、肋横角（β）、肋间距比（t/Wt）和通道入口高度（H1）对换热系数h的影响，建立正交设计数据库，并将其作为基于遗传算法（GA）的BP网络优化训练集。通过风洞试验装置的实验测量，验证了该网络的有效性。结果表明，GA-BP网络的准确率为91.200%，优于BP网络的87.689%。此外，本文提出的GA-BP网络具有良好的模型稳定性和泛化性，可以更快地进行传热预测，更方便地进行冷却设计。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Journal of Thermal Sciences 工程技术-工程：机械

CiteScore

8.10

自引率

11.10%

发文量

531

审稿时长

55 days

期刊介绍： The International Journal of Thermal Sciences is a journal devoted to the publication of fundamental studies on the physics of transfer processes in general, with an emphasis on thermal aspects and also applied research on various processes, energy systems and the environment. Articles are published in English and French, and are subject to peer review. The fundamental subjects considered within the scope of the journal are: * Heat and relevant mass transfer at all scales (nano, micro and macro) and in all types of material (heterogeneous, composites, biological,...) and fluid flow * Forced, natural or mixed convection in reactive or non-reactive media * Single or multi–phase fluid flow with or without phase change * Near–and far–field radiative heat transfer * Combined modes of heat transfer in complex systems (for example, plasmas, biological, geological,...) * Multiscale modelling The applied research topics include: * Heat exchangers, heat pipes, cooling processes * Transport phenomena taking place in industrial processes (chemical, food and agricultural, metallurgical, space and aeronautical, automobile industries) * Nano–and micro–technology for energy, space, biosystems and devices * Heat transport analysis in advanced systems * Impact of energy–related processes on environment, and emerging energy systems The study of thermophysical properties of materials and fluids, thermal measurement techniques, inverse methods, and the developments of experimental methods are within the scope of the International Journal of Thermal Sciences which also covers the modelling, and numerical methods applied to thermal transfer.