文献类型：期刊文献

英文题名：Efficient prediction framework for large-scale nonlinear petrochemical process based on feature selection and temporal-attention LSTM: Applied to fluid catalytic cracking

作者：Long, Jian[1];Ye, Long[1];Peng, Haifei[1];Tian, Zhou[1,2]

机构：[1]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[2]Qingyuan Innovat Lab, Quanzhou 362801, Peoples R China

年份：2025

卷号：301

外文期刊名：CHEMICAL ENGINEERING SCIENCE

收录：;EI(收录号：20243917083958);WOS:【SCI-EXPANDED(收录号:WOS:001320478600001)】；

基金：This work was supported by National Natural Science Foundation of China (Basic Science Center Program: 61988101) , National Natural Science Foundation of China (62136003, 62373155) , Major Program of Qingyuan Innovation Laboratory (Grant No. 00122002) , and the Programme of Introducing Talents of Discipline to Universities (the 111 Project) under Grant B17017.

语种：英文

外文关键词：FCC process; Data-driven; Feature selection; Temporal-attention mechanisms; LSTM network

摘要：Data-driven modeling plays a vital role in petrochemical industry, especially fluid catalytic cracking (FCC). However, the long operational cycles, large-scale measurements, multivariate data, and intricate temporal correlations in FCC units may lead to the problem of low prediction accuracy when only use a single time series data-driven modeling neural network such as long short-term memory (LSTM) network. To address these challenges, an effective prediction framework is proposed that integrates LSTM network with extreme gradient boosting (XGBOOST)-based feature selection and temporal-attention (TA) mechanisms. XGBOOST is applied to filter features related to the predictive variables in order to eliminate redundant variables. TA mechanisms within an LSTM network is used to capture the relevant historical time steps of the current moment. The results of our efficient prediction framework, applied to FCC process and three additional petrochemical processes, have proven to be superior to other methods.