Mohammad Mahdi Barzegar, Feridun Esmaeilzadeh, Ali Zandifar
{"title":"基于密度和神经网络建模预测有机化合物在超临界二氧化碳中溶解度的对比分析","authors":"Mohammad Mahdi Barzegar, Feridun Esmaeilzadeh, Ali Zandifar","doi":"10.1016/j.supflu.2024.106345","DOIUrl":null,"url":null,"abstract":"<div><p>This study investigates the estimation of solute solubility in supercritical carbon dioxide (SC-CO<sub>2</sub>) within a pressure and temperature range of 80 bar to 490.29 bar and 308 K to 423 K. We propose a novel empirical model that establishes a correlation between relevant parameters and the targeted solubility. A feature importance algorithm facilitated the development of this empirical model. The model’s accuracy is comprehensively evaluated using 40 published experimental datasets, with an average absolute relative deviation (AARD) of 9.9 %. It demonstrates superior performance compared to 12 previously established models. Furthermore, a fine-tuned artificial neural network (ANN) is developed to harness the unique capabilities of machine learning techniques. The ANN outperforms the proposed model, achieving a significantly lower AARD% of 4.38. This outcome emphasizes the potential of machine learning techniques, particularly ANNs, for achieving superior accuracy.</p></div>","PeriodicalId":17078,"journal":{"name":"Journal of Supercritical Fluids","volume":null,"pages":null},"PeriodicalIF":3.4000,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A comparative analysis of density-based and neural network modeling for predicting the solubility of organic compounds in supercritical carbon dioxide\",\"authors\":\"Mohammad Mahdi Barzegar, Feridun Esmaeilzadeh, Ali Zandifar\",\"doi\":\"10.1016/j.supflu.2024.106345\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>This study investigates the estimation of solute solubility in supercritical carbon dioxide (SC-CO<sub>2</sub>) within a pressure and temperature range of 80 bar to 490.29 bar and 308 K to 423 K. We propose a novel empirical model that establishes a correlation between relevant parameters and the targeted solubility. A feature importance algorithm facilitated the development of this empirical model. The model’s accuracy is comprehensively evaluated using 40 published experimental datasets, with an average absolute relative deviation (AARD) of 9.9 %. It demonstrates superior performance compared to 12 previously established models. Furthermore, a fine-tuned artificial neural network (ANN) is developed to harness the unique capabilities of machine learning techniques. The ANN outperforms the proposed model, achieving a significantly lower AARD% of 4.38. This outcome emphasizes the potential of machine learning techniques, particularly ANNs, for achieving superior accuracy.</p></div>\",\"PeriodicalId\":17078,\"journal\":{\"name\":\"Journal of Supercritical Fluids\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.4000,\"publicationDate\":\"2024-07-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Supercritical Fluids\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0896844624001803\",\"RegionNum\":3,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"CHEMISTRY, PHYSICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Supercritical Fluids","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0896844624001803","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
A comparative analysis of density-based and neural network modeling for predicting the solubility of organic compounds in supercritical carbon dioxide
This study investigates the estimation of solute solubility in supercritical carbon dioxide (SC-CO2) within a pressure and temperature range of 80 bar to 490.29 bar and 308 K to 423 K. We propose a novel empirical model that establishes a correlation between relevant parameters and the targeted solubility. A feature importance algorithm facilitated the development of this empirical model. The model’s accuracy is comprehensively evaluated using 40 published experimental datasets, with an average absolute relative deviation (AARD) of 9.9 %. It demonstrates superior performance compared to 12 previously established models. Furthermore, a fine-tuned artificial neural network (ANN) is developed to harness the unique capabilities of machine learning techniques. The ANN outperforms the proposed model, achieving a significantly lower AARD% of 4.38. This outcome emphasizes the potential of machine learning techniques, particularly ANNs, for achieving superior accuracy.
期刊介绍:
The Journal of Supercritical Fluids is an international journal devoted to the fundamental and applied aspects of supercritical fluids and processes. Its aim is to provide a focused platform for academic and industrial researchers to report their findings and to have ready access to the advances in this rapidly growing field. Its coverage is multidisciplinary and includes both basic and applied topics.
Thermodynamics and phase equilibria, reaction kinetics and rate processes, thermal and transport properties, and all topics related to processing such as separations (extraction, fractionation, purification, chromatography) nucleation and impregnation are within the scope. Accounts of specific engineering applications such as those encountered in food, fuel, natural products, minerals, pharmaceuticals and polymer industries are included. Topics related to high pressure equipment design, analytical techniques, sensors, and process control methodologies are also within the scope of the journal.