文献类型：期刊文献

英文题名：Data-driven robust operating optimization of energy-material coupled system in refineries under uncertainty

作者：Long, Jian[1];Zhu, Jiawei[1];Wang, Ning[1];Zhai, Jiazi[2];Xu, Tiantian[1];Liang, Chen[1,3];Zhao, Liang[1,3]

机构：[1]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[2]China Petr Pipeline Bur Co Ltd, Reserve Oil Management Serv Co, Langfang, Peoples R China;[3]East China Univ Sci & Technol, Engn Res Ctr Proc Syst Engn, Minist Educ, Shanghai 200237, Peoples R China

年份：2025

卷号：267

外文期刊名：EXPERT SYSTEMS WITH APPLICATIONS

收录：;EI(收录号：20245217575943);WOS:【SCI-EXPANDED(收录号:WOS:001394596000001)】；

基金：This work was supported by National Key Research and Develop-ment Program of China (2023YFB3307800) , National Natural Science Foundation of China (62394345, 62373155, 62373154) , Major Science and Technology Project of Xinjiang (No. 2022A01006-4) , and the Fundamental Research Funds for the Central Universities.

语种：英文

外文关键词：Refinery material systems; Steam system; Coupling system; Data-driven robust optimization; Uncertainty set

摘要：Refineries face the dual challenge of improving operational efficiency while minimizing environmental impact, necessitating effective optimization of coupled energy-material systems under uncertainty. This study introduces a novel data-driven robust optimization framework that combines deterministic modeling with principal component analysis (PCA) and robust kernel density estimation (RKDE) to manage variations in steam generation and consumption. An industrial-scale case study demonstrates the framework's effectiveness, achieving a 48.7% reduction in steam system costs and a 1.4% overall cost reduction through integrated optimization. The novelty of the approach lies in its integration of energy and material flows, along with the construction of a refined uncertainty set using PCA-RKDE, providing a robust solution for real-world refinery operations. This research advances optimization practices in energy-intensive industries and paves the way for future work on dynamic modeling, multi-objective optimization, and renewable energy integration.