MD Mumtaz A. Ansari, Vijay K. Mishra, Kunja B. Sahu, Sumanta Chaudhuri, Prakash Ghose, Vishesh Ranjan Kar
{"title":"基于混合遗传算法-Kohonen 图的决策支持系统,用于多孔介质中的传导-辐射组合模式传热:柯霍能图三种变体的比较评估","authors":"MD Mumtaz A. Ansari, Vijay K. Mishra, Kunja B. Sahu, Sumanta Chaudhuri, Prakash Ghose, Vishesh Ranjan Kar","doi":"10.1002/htj.23005","DOIUrl":null,"url":null,"abstract":"<p>A hybrid genetic algorithm (GA)–Kohonen map, with its three variants, is explored for the first time for the decision-making system in a porous ceramic matrix (PCM)-based burner through determination of the regime of operation. Four different attributes of PCMs such as convective coupling (<i>P</i><sub>2</sub>), extinction coefficient (<i>β</i>), downstream porosity (<i>ϕ</i><sub>2</sub>), and scattering albedo (<i>ω</i>) are selected for determining the regime of operation of a PCM-based burner. Changes in any of these attributes of a PCM lead to significant changes in the temperature profiles of the gas and solid phases. Temperature profiles of the gas and solid phases are computed by developing a numerical model. Various samples corresponding to different regimes are generated and used in a hybrid GA–Kohonen map. The best architectural details such as the neuron number and training epochs are obtained from GA as output. The best Kohonen map is trained with the input data, and regimes of operation for new temperature profiles are predicted. A supervised Kohonen map is able to provide the highest average class prediction of more than 40%. All the variants are assessed under two different types of neuron grids: hexagonal and rectangular. Comparative assessments of the three different variants of Kohonen maps, in terms of CPU time and average class prediction, are carried out.</p>","PeriodicalId":44939,"journal":{"name":"Heat Transfer","volume":null,"pages":null},"PeriodicalIF":2.8000,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Decision support system based on a hybrid genetic algorithm–Kohonen map for combined mode conduction–radiation heat transfer in a porous medium: A comparative assessment of three variations of the Kohonen map\",\"authors\":\"MD Mumtaz A. Ansari, Vijay K. Mishra, Kunja B. Sahu, Sumanta Chaudhuri, Prakash Ghose, Vishesh Ranjan Kar\",\"doi\":\"10.1002/htj.23005\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>A hybrid genetic algorithm (GA)–Kohonen map, with its three variants, is explored for the first time for the decision-making system in a porous ceramic matrix (PCM)-based burner through determination of the regime of operation. Four different attributes of PCMs such as convective coupling (<i>P</i><sub>2</sub>), extinction coefficient (<i>β</i>), downstream porosity (<i>ϕ</i><sub>2</sub>), and scattering albedo (<i>ω</i>) are selected for determining the regime of operation of a PCM-based burner. Changes in any of these attributes of a PCM lead to significant changes in the temperature profiles of the gas and solid phases. Temperature profiles of the gas and solid phases are computed by developing a numerical model. Various samples corresponding to different regimes are generated and used in a hybrid GA–Kohonen map. The best architectural details such as the neuron number and training epochs are obtained from GA as output. The best Kohonen map is trained with the input data, and regimes of operation for new temperature profiles are predicted. A supervised Kohonen map is able to provide the highest average class prediction of more than 40%. All the variants are assessed under two different types of neuron grids: hexagonal and rectangular. Comparative assessments of the three different variants of Kohonen maps, in terms of CPU time and average class prediction, are carried out.</p>\",\"PeriodicalId\":44939,\"journal\":{\"name\":\"Heat Transfer\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.8000,\"publicationDate\":\"2024-01-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Heat Transfer\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/htj.23005\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"THERMODYNAMICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Heat Transfer","FirstCategoryId":"1085","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/htj.23005","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"THERMODYNAMICS","Score":null,"Total":0}
Decision support system based on a hybrid genetic algorithm–Kohonen map for combined mode conduction–radiation heat transfer in a porous medium: A comparative assessment of three variations of the Kohonen map
A hybrid genetic algorithm (GA)–Kohonen map, with its three variants, is explored for the first time for the decision-making system in a porous ceramic matrix (PCM)-based burner through determination of the regime of operation. Four different attributes of PCMs such as convective coupling (P2), extinction coefficient (β), downstream porosity (ϕ2), and scattering albedo (ω) are selected for determining the regime of operation of a PCM-based burner. Changes in any of these attributes of a PCM lead to significant changes in the temperature profiles of the gas and solid phases. Temperature profiles of the gas and solid phases are computed by developing a numerical model. Various samples corresponding to different regimes are generated and used in a hybrid GA–Kohonen map. The best architectural details such as the neuron number and training epochs are obtained from GA as output. The best Kohonen map is trained with the input data, and regimes of operation for new temperature profiles are predicted. A supervised Kohonen map is able to provide the highest average class prediction of more than 40%. All the variants are assessed under two different types of neuron grids: hexagonal and rectangular. Comparative assessments of the three different variants of Kohonen maps, in terms of CPU time and average class prediction, are carried out.