化工学报2026，Vol.77Issue(2)：791-802,12.DOI:10.11949/0438-1157.20250952
基于NMI-GBR-SHAP的甲醇制烯烃催化剂积炭过程解释性分析
Interpretative analysis of carbon deposition process of methanol to olefins catalyst based on NMI-GBR-SHAP
摘要
Abstract
Catalyst carbon deposition in the methanol to olefins(MTO)process is complex and interdependent,making it difficult to effectively control carbon deposition.This study employed an integrated analytical framework based on normalized mutual information(NMI),gradient boosting regression(GBR),and SHAP to explain the key factors influencing catalyst carbon deposition.The results revealed that when the regeneration swirl inlet linear velocity was maintained at 16.0-18.5 m/s,combined with a reactor protection steam rate of 9-11 t/h,the total regenerator char air volume was controlled at 26000-30000 m3/h,the regeneration slide valve position was maintained at 34%—36%,and the steam injection rate was no less than 34%,catalyst carbon deposition could be effectively controlled(6.5%—7.3%).Based on the above process parameters,a baseline limit is constructed.Once the operating conditions exceed this monitoring limit,SHAP analysis of the interaction characteristics can explain the corresponding coking trend(rate of change),providing necessary monitoring information for the stable operation of the process and offering a technical solution with both predictive accuracy and mechanistic explanation for catalyst coking monitoring in the MTO process.关键词
甲醇制烯烃/催化剂积炭/归一化互信息/梯度提升回归/可解释机器学习/过程控制/预测/化学过程Key words
methanol to olefins/catalyst coking/normalized mutual information/gradient boosting regression/interpretable machine learning/process control/prediction/chemical processes分类
化学化工引用本文复制引用
李文亮,张浩,陈鸣睿,梁晨,翟持..基于NMI-GBR-SHAP的甲醇制烯烃催化剂积炭过程解释性分析[J].化工学报,2026,77(2):791-802,12.基金项目
云南省兴滇英才支持计划项目(KKRD202205037) （KKRD202205037）
