Optimization of methanol distillation process based on chemical mechanism and industrial digital twinning modeling

被引：0
|
作者：
Wang X. [1 ]
Yang Z. [2 ]
Li Y. [1 ]
Shen W. [1 ]
机构：
[1] School of Chemistry and Chemical Engineering, Chongqing University, Chongqing
[2] Chongqing Changfeng Chemical Industry Co., Ltd., Chongqing
来源：
Huagong Jinzhan/Chemical Industry and Engineering Progress | 2024年 / 43卷 / 01期
关键词：
confidence analysis; data reconciliation; data-driven; digital twin; methanol distillation; process optimization;
D O I：
10.16085/j.issn.1000-6613.2023-1286
中图分类号：
学科分类号：
摘要：
In the production of the chemical industry, the data from the distributed control system (DCS) is crucial for reflecting the production status of the process. However, due to measurement errors, it often fails to meet the requirements for accurate process modeling and optimization. Conventional process modeling and optimization studies do not fully consider the deviations caused by industrial production and design data. In this work, we proposed a twin modeling framework based on industrial production data of methanol distillation and chemical mechanisms, combined with industrial experience, to guide more accurate optimization of industrial processes. We established material and energy conservation constraints and assigned weights to measurement variables based on the measurement range of instruments. Using nonlinear programming algorithms and chemical mechanism constraints, we calibrated and solved for the calibrated values of the measurement variables. We also proposed a confidence score model for process variables based on the calibrated values and industrial experience to evaluate the confidence of the measurement variables. By constructing a methanol distillation process model which was closer to industrial reality based on the calibrated measurement variables, we achieved more accurate process optimization. The twin modeling approach combining chemical mechanisms and industrial data proposed in this work has significant scientific and practical value for the construction of digital twin systems and intelligent chemical plants. © 2024 Chemical Industry Press Co., Ltd.. All rights reserved.
引用
收藏
页码：310 / 319
页数：9
相关论文
共 27 条
  • [1] WANG Zizong, WANG Jiming, GAO Libing, Classification and maturity analysis on petrochemical industrial software, Chemical Industry and Engineering Progress, 40, 4, pp. 1827-1836, (2021)
  • [2] GRIEVES Michael W., Product lifecycle management: The new paradigm for enterprises, International Journal of Product Development, 2, 1, (2005)
  • [3] MIAO Tian, ZHANG Xu, XIONG Hui, Et al., Applications and expectation of digital twin in product lifecycle, Computer Integrated Manufacturing Systems, 25, 6, pp. 1546-1558, (2019)
  • [4] LIN Zhicheng, Digital twins technology framework and its applications in manufacturing industry, Industrial Control Computer, 33, 6, pp. 129-131, (2020)
  • [5] SHANKAR Narasimhan, CORNELIUS Jordache, Data reconciliation and gross error detection[M], pp. 142-173, (1999)
  • [6] XIE Sen, YANG Chunhua, WANG Xiaoli, Et al., A data-driven adaptive multivariate steady state detection strategy for the evaporation process of the sodium aluminate solution, Journal of Process Control, 68, pp. 145-159, (2018)
  • [7] WANG Zan, WANG Xianpeng, Multiobjective multifactorial operation optimization for continuous annealing production process, Industrial & Engineering Chemistry Research, 58, 41, pp. 19166-19178, (2019)
  • [8] WANG Yalin, PAN Zhuofu, YUAN Xiaofeng, Et al., A novel deep learning based fault diagnosis approach for chemical process with extended deep belief network, ISA Transactions, 96, pp. 457-467, (2020)
  • [9] YUAN Xiaofeng, OU Chen, WANG Yalin, Et al., Deep quality-related feature extraction for soft sensing modeling: A deep learning approach with hybrid VW-SAE, Neurocomputing, 396, pp. 375-382, (2020)
  • [10] KUEHN D R, DAVIDSON H., Computer control Ⅱ . Mathematics of control, Chemical Engineering Progress, 57, 6, pp. 44-47, (1961)
123