{"title":"Modeling, Sensitivity Analysis, and Optimization of the Methanol-to-Gasoline Process using Artificial Intelligence Methods","authors":"M. Pashangpoor, S. Askari, M. J. Azarhoosh","doi":"10.1134/S0040579523070102","DOIUrl":null,"url":null,"abstract":"<p>In this study, the gasoline yield in the methanol-to-gasoline (MTG) process was modeled using artificial neural network (ANN) and multivariate polynomial regression (MPR) techniques. The ANN trained using the Levenberg–Marquardt (LM) method and having three neurons in the hidden layer was the most accurate at predicting gasoline yield (<i>R</i><sup>2</sup> = 0.993 and RMSE = 0.024). Therefore, this network was used to investigate the influence of operational conditions such as pressure, weight hourly space velocity (WHSV), temperature, and the average particle size of the Zeolite Socony Mobil–5 (ZSM-5) catalyst on the gasoline yield. Then, the particle swarm optimization (PSO) and genetic algorithm (GA) were used to approach the best operating parameters and catalyst size to get the most gasoline yield. The mentioned neural network was used as a fitness function in the optimization algorithms. The optimization results showed that at a pressure of 1 bar, a temperature of 400°C, a WHSV equal to 1 h<sup>–1</sup>, and a particle size of 1466 nm, the maximum gasoline yield is equivalent to 45.43.</p>","PeriodicalId":798,"journal":{"name":"Theoretical Foundations of Chemical Engineering","volume":null,"pages":null},"PeriodicalIF":0.7000,"publicationDate":"2024-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Theoretical Foundations of Chemical Engineering","FirstCategoryId":"5","ListUrlMain":"https://link.springer.com/article/10.1134/S0040579523070102","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, CHEMICAL","Score":null,"Total":0}
引用次数: 0
Abstract
In this study, the gasoline yield in the methanol-to-gasoline (MTG) process was modeled using artificial neural network (ANN) and multivariate polynomial regression (MPR) techniques. The ANN trained using the Levenberg–Marquardt (LM) method and having three neurons in the hidden layer was the most accurate at predicting gasoline yield (R2 = 0.993 and RMSE = 0.024). Therefore, this network was used to investigate the influence of operational conditions such as pressure, weight hourly space velocity (WHSV), temperature, and the average particle size of the Zeolite Socony Mobil–5 (ZSM-5) catalyst on the gasoline yield. Then, the particle swarm optimization (PSO) and genetic algorithm (GA) were used to approach the best operating parameters and catalyst size to get the most gasoline yield. The mentioned neural network was used as a fitness function in the optimization algorithms. The optimization results showed that at a pressure of 1 bar, a temperature of 400°C, a WHSV equal to 1 h–1, and a particle size of 1466 nm, the maximum gasoline yield is equivalent to 45.43.
期刊介绍:
Theoretical Foundations of Chemical Engineering is a comprehensive journal covering all aspects of theoretical and applied research in chemical engineering, including transport phenomena; surface phenomena; processes of mixture separation; theory and methods of chemical reactor design; combined processes and multifunctional reactors; hydromechanic, thermal, diffusion, and chemical processes and apparatus, membrane processes and reactors; biotechnology; dispersed systems; nanotechnologies; process intensification; information modeling and analysis; energy- and resource-saving processes; environmentally clean processes and technologies.