Scholarlink

<p>This study focuses on the metathesis of 2-butene to convert low value products into higher value propylene. In this work, using machine learning (ML) techniques, several robust models were built and developed to predict the mole fraction of components in products of catalytic metathesis process over WO<sub>3</sub> on mesoporous support without the need for profound knowledge about exact reaction mechanism and their kinetics. The operative parameters were reaction temperature and residence time. The process performance was assessed using conversion and product selectivity as responses. Cross-validation technique was used during the model development. The developed models were used to investigate the mechanism of process as well as examining the effects of operative parameters on process performance. Further, these models were used to optimize the process in companion with genetic algorithm (GA).</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Optimizing propylene production via 2-butene metathesis: catalytic efficiencies and AI-driven process enhancement

  • 期刊论文

  • 发表日期：

    2025年8月19日

查看全文
  • Amin Hedayati Moghaddam,
  • Morteza Esfandyari,
  • Hossein Sakhaeinia,
  • Abdellatif Mohammad Sadeq

摘要

This study focuses on the metathesis of 2-butene to convert low value products into higher value propylene. In this work, using machine learning (ML) techniques, several robust models were built and developed to predict the mole fraction of components in products of catalytic metathesis process over WO3 on mesoporous support without the need for profound knowledge about exact reaction mechanism and their kinetics. The operative parameters were reaction temperature and residence time. The process performance was assessed using conversion and product selectivity as responses. Cross-validation technique was used during the model development. The developed models were used to investigate the mechanism of process as well as examining the effects of operative parameters on process performance. Further, these models were used to optimize the process in companion with genetic algorithm (GA).