{"title":"利用线性回归、人工神经网络和基因表达编程对 R466A 的热力学特性进行比较研究","authors":"Erkan Dikmen","doi":"10.1007/s10973-024-13509-6","DOIUrl":null,"url":null,"abstract":"<p>The use of next-generation refrigerant fluids is preferred to improve the global environment’s livability. In this context, the thermodynamic properties of R466A, a new-generation refrigerant with low ozone depletion potential and global warming potential, have been modelled using various methods. Linear regression, artificial neural network (ANN), and gene expression programming (GEP) models were used to predict R466A’s temperature–pressure relationship in the saturated liquid–vapor phase and its enthalpy-entropy relationship in the superheated vapor phase. The models’ performance was evaluated based on statistical parameters such as the determination coefficient (<i>R</i><sup>2</sup>), mean absolute error, and root mean square error (RMSE), and compared with actual values. The research results indicate that the GEP model achieved the lowest RMSE values for predicting thermodynamic properties in the saturated vapor phase. On the other hand, ANN models were found to be more suitable for estimating properties in the superheated vapor phase. The <i>R</i><sup>2</sup> values for ANN models ranged from 0.999 to 0.986, whereas GEP models exhibited <i>R</i><sup>2</sup> values between 0.999 and 0.982. Despite slightly lower performance compared to some ANN models, GEP models employed explicit equations.</p>","PeriodicalId":678,"journal":{"name":"Journal of Thermal Analysis and Calorimetry","volume":null,"pages":null},"PeriodicalIF":3.0000,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A comparative study of thermodynamic properties of R466A using linear regression, artificial neural network and gene expression programming\",\"authors\":\"Erkan Dikmen\",\"doi\":\"10.1007/s10973-024-13509-6\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>The use of next-generation refrigerant fluids is preferred to improve the global environment’s livability. In this context, the thermodynamic properties of R466A, a new-generation refrigerant with low ozone depletion potential and global warming potential, have been modelled using various methods. Linear regression, artificial neural network (ANN), and gene expression programming (GEP) models were used to predict R466A’s temperature–pressure relationship in the saturated liquid–vapor phase and its enthalpy-entropy relationship in the superheated vapor phase. The models’ performance was evaluated based on statistical parameters such as the determination coefficient (<i>R</i><sup>2</sup>), mean absolute error, and root mean square error (RMSE), and compared with actual values. The research results indicate that the GEP model achieved the lowest RMSE values for predicting thermodynamic properties in the saturated vapor phase. On the other hand, ANN models were found to be more suitable for estimating properties in the superheated vapor phase. The <i>R</i><sup>2</sup> values for ANN models ranged from 0.999 to 0.986, whereas GEP models exhibited <i>R</i><sup>2</sup> values between 0.999 and 0.982. Despite slightly lower performance compared to some ANN models, GEP models employed explicit equations.</p>\",\"PeriodicalId\":678,\"journal\":{\"name\":\"Journal of Thermal Analysis and Calorimetry\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.0000,\"publicationDate\":\"2024-09-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Thermal Analysis and Calorimetry\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1007/s10973-024-13509-6\",\"RegionNum\":3,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"CHEMISTRY, ANALYTICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Thermal Analysis and Calorimetry","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s10973-024-13509-6","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CHEMISTRY, ANALYTICAL","Score":null,"Total":0}
A comparative study of thermodynamic properties of R466A using linear regression, artificial neural network and gene expression programming
The use of next-generation refrigerant fluids is preferred to improve the global environment’s livability. In this context, the thermodynamic properties of R466A, a new-generation refrigerant with low ozone depletion potential and global warming potential, have been modelled using various methods. Linear regression, artificial neural network (ANN), and gene expression programming (GEP) models were used to predict R466A’s temperature–pressure relationship in the saturated liquid–vapor phase and its enthalpy-entropy relationship in the superheated vapor phase. The models’ performance was evaluated based on statistical parameters such as the determination coefficient (R2), mean absolute error, and root mean square error (RMSE), and compared with actual values. The research results indicate that the GEP model achieved the lowest RMSE values for predicting thermodynamic properties in the saturated vapor phase. On the other hand, ANN models were found to be more suitable for estimating properties in the superheated vapor phase. The R2 values for ANN models ranged from 0.999 to 0.986, whereas GEP models exhibited R2 values between 0.999 and 0.982. Despite slightly lower performance compared to some ANN models, GEP models employed explicit equations.
期刊介绍:
Journal of Thermal Analysis and Calorimetry is a fully peer reviewed journal publishing high quality papers covering all aspects of thermal analysis, calorimetry, and experimental thermodynamics. The journal publishes regular and special issues in twelve issues every year. The following types of papers are published: Original Research Papers, Short Communications, Reviews, Modern Instruments, Events and Book reviews.
The subjects covered are: thermogravimetry, derivative thermogravimetry, differential thermal analysis, thermodilatometry, differential scanning calorimetry of all types, non-scanning calorimetry of all types, thermometry, evolved gas analysis, thermomechanical analysis, emanation thermal analysis, thermal conductivity, multiple techniques, and miscellaneous thermal methods (including the combination of the thermal method with various instrumental techniques), theory and instrumentation for thermal analysis and calorimetry.