<![CDATA[Methyl chloride (CH₃Cl) is an essential intermediate in the manufacture of silicones, agrochemicals, amines, refrigerants, and synthetic rubber; however, conventional production routes are constrained by substantial energy inefficiencies and exergy destruction. This study seeks to enhance the hydrochlorination of methanol to methyl chloride by integrating heat exchangers (HE) as a waste‑heat recovery strategy. Simulation software was used to simulate both the baseline and heat‑integrated process configurations, employing the Peng–Robinson EOS to represent thermodynamic behavior. In the baseline system, the process required 12,302.48 kW of energy input and produced 9,028.60 kW of useful output, achieving a conversion of 73.4%, with unrecovered hot streams contributing significantly to entropy generation. The modified configuration introduced three heat exchangers (E‑100, E‑101, E‑102) to recover reaction and condensation heat, enabling feed preheating and reducing external utility demand. This integration increased conversion from 73.4% to 95%, raised energy output to 11,912 kW, and reduced both energy losses and exergy destruction. The resulting dataset from the optimized system was subsequently evaluated using machine learning models, among which Bayesian Ridge Regression (BRR) demonstrated the highest accuracy and stability, exhibiting superior MSE, MAE, and R² performance. Overall, the findings show that coupling heat‑integration strategies with machine‑learning analysis provides a robust pathway for improving energy efficiency, product quality, and predictive reliability in methyl chloride production. Copyright © 2026 by Authors, Published by Universitas Diponegoro and BCREC Publishing Group. This is an open access article under the CC BY-SA License (https://creativecommons.org/licenses/by-sa/4.0).]]>
Copyrights © 2026
