CIESC Journal ›› 2023, Vol. 74 ›› Issue (5): 2075-2087.DOI: 10.11949/0438-1157.20230345

• Process system engineering • Previous Articles     Next Articles

Optimization of ternary-distillation sequence based on gradient boosting decision tree

Shanghao LIU1(), Shengkun JIA1,2(), Yiqing LUO1,2, Xigang YUAN1,2,3()   

  1. 1.School of Chemical Engineering and Technology, Tianjin University, Tianjin 300354, China
    2.Chemical Engineering Research Center, Tianjin University, Tianjin 300354, China
    3.State Key Laboratory of Chemical Engineering, Tianjin University, Tianjin 300354, China
  • Received:2023-04-06 Revised:2023-05-05 Online:2023-06-29 Published:2023-05-05
  • Contact: Shengkun JIA, Xigang YUAN

基于梯度提升决策树的三组元精馏流程结构最优化

刘尚豪1(), 贾胜坤1,2(), 罗祎青1,2, 袁希钢1,2,3()   

  1. 1.天津大学化工学院,天津 300354
    2.天津大学化学工程研究所,天津 300354
    3.化学工程联合国家重点实验室(天津大学),天津 300354
  • 通讯作者: 贾胜坤,袁希钢
  • 作者简介:刘尚豪(1998—),男,硕士研究生,liushanghao_2020@tju.edu.cn
  • 基金资助:
    国家自然科学基金项目(22178247)

Abstract:

A machine learning method based on gradient boosting decision tree (GBDT) is proposed for the optimal selection of ternary-distillation process structure. Economic evaluation data of 9 ternary mixtures separated by 7 distillation process structures were used for model training. By applying both traditional decision tree and GBDT models to multiple cases, the results show that the proposed GBDT model has higher prediction accuracy than the traditional decision tree model for both known and unknown ternary mixtures.

Key words: ternary-distillation, optimal distillation configuration, machine learning, gradient boosting decision tree, distillation, computer simulation, optimal design

摘要:

针对三组元精馏流程结构最优选择问题,提出一种基于梯度提升决策树(gradient boosting decision tree,GBDT)的机器学习方法,利用7种精馏流程结构分离9种三组元混合物的经济评价结果数据用于模型训练。分别应用传统决策树和GBDT模型对多个实际案例进行验证,结果显示无论是对已知物系还是未知物系,提出的GBDT模型相较传统决策树模型具有更高的预测准确率。

关键词: 三组元精馏, 精馏最优流程结构, 机器学习, 梯度提升树, 蒸馏, 计算机模拟, 优化设计

CLC Number: