文献类型：期刊文献

英文题名：Low Temperature Pyrolysis of Plastics Based on Small Sample Machine Learning: Product Prediction, Optimization Conditions, and Model Interpretability Analysis

作者：Ma, Zheng[1];Lin, HanLe[1];Huang, Changfei[2];Tian, Chengcheng[2,3];Zhang, Yayun[1]

机构：[1]East China Univ Sci & Technol, Sch Chem Engn, Key Lab Specially Funct Polymer Mat & Related Tech, Minist Educ, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, Sch Resources & Environm Engn, Shanghai 200237, Peoples R China;[3]Shanghai Inst Pollut Control & Ecol Secur, Shanghai 200092, Peoples R China

年份：2025

卷号：13

期号：44

起止页码：19383

外文期刊名：ACS SUSTAINABLE CHEMISTRY & ENGINEERING

收录：;EI(收录号：20254619482450);WOS:【SCI-EXPANDED(收录号:WOS:001604073800001)】；

基金：This work was financially supported by National Natural Science Foundation of China (Nos. 22008073, 22478123), Shanghai Sailing Program (No. 20YF1410600), Shanghai Talent Development Fund (2021026), and Natural Science Foundation of Shanghai (24ZR1417200).

语种：英文

外文关键词：catalytic pyrolysis; machinelearning; TabPFN; plastics; zeolite ZSM-5; SHAP interpretability

摘要：This study proposes a novel data-driven strategy that integrates machine learning (ML) with low-temperature catalytic pyrolysis to optimize the selection of plastic feedstocks and catalyst designs. Using a custom-built experimental data set based on polyethylene (PE) model compounds and zeolite ZSM-5 catalysts, we trained and evaluated three ML models-TabPFN, CatBoost, and XGBoost-on a small-sample data set of 105 orthogonally designed experiments. TabPFN outperformed conventional gradient boosting models in both classification and regression tasks, achieving an R 2 of 0.982 and RMSE of 4.37 on test data, with strong generalization capacity. SHAP analysis and Pearson correlation jointly revealed that temperature and the Si/Al ratio were the dominant factors influencing C2-C6 olefins selectivity, with the latter exhibiting an inverted U-shaped influence on olefin selectivity. The trained TabPFN model successfully identified optimal reaction conditions, which were experimentally validated with a high C2-C6 olefin yield of 82.5% and minimal coke formation. This work demonstrates the potential of ML-based small-sample frameworks for rapidly optimizing catalytic systems, and the analysis of SHAP interpretation provides possible insights into the reaction pathway.