基于Kriging代理模型的复杂精馏系统操作参数优化

石油炼制与化工 ›› 2020, Vol. 51 ›› Issue (1): 114-120.

• 优化与控制 • 上一篇

基于Kriging代理模型的复杂精馏系统操作参数优化

刘思乐¹,王修纲²,吴静^1,3,李德豹¹

1. 沈阳科技学院化学工程系
2. 上海交通大学化学化工学院
3. 沈阳化工大学化学工程学院

收稿日期:2019-07-02 修回日期:2019-10-08 出版日期:2020-01-12 发布日期:2020-01-19
通讯作者: 刘思乐 E-mail:sl.0117@163.com
基金资助:

OPERATION PARAMETER OPTIMIZATION OF COMPLEX DISTILLATION SYSTEM BASED ON KRIGING SURROGATE

Received:2019-07-02 Revised:2019-10-08 Online:2020-01-12 Published:2020-01-19
Supported by:

摘要/Abstract

摘要： 优化常减压装置的操作参数可有效提升炼化企业的经济效益，但基于其严格机理模型进行迭代寻优将十分耗时。为降低计算成本，提出了一种基于Kriging代理模型的常压精馏系统操作参数智能优化方法。该方法采用Kriging元建模技术构造精馏过程中关键操作参数与主要输出变量间的关系模型，并以此关系模型代理复杂精馏系统的MESH方程组（包括物料守恒方程M、气液平衡方程E、归一方程S、焓守恒方程H），在设计空间中采用粒子群优化（PSO）算法进行操作参数的全局智能搜索。所提方法不仅能够保证寻找到的操作参数全局最优，而且可以大幅度地减少求解的时间，具有十分明显的工程实用性。基于Aspen HYSYS的仿真试验表明了本文所提方法的有效性和优越性。

关键词: 复杂精馏系统, 常压蒸馏系统, Kriging 代理模型, 粒子群优化

Abstract: Optimizing the operation parameters of atmospheric and vacuum distillation units can effectively improve the economic benefits of refineries，but it would be time-consuming if the optimization process was iteratively conducted with their rigorous mechanism model. In order to reduce the computational cost，Kriging surrogate-based intelligent method is proposed to optimize the operation parameters of an atmospheric distillation system in this paper. In detail，Kriging meta-modeling technology is adopted to construct the relationship model between some key operation parameters and output variables for the distillation process，and then the relationship model is used to represent the MESH equations of the complex distillation system. Moreover，employing particle swarm optimization (PSO) algorithm in the design space to conduct global intelligent search of operation parameters. The proposed method can not only ensure the global optimization of the operation parameters，but also greatly reduce the computing time when solving the problems. Simulation results, using Aspen HYSYS, shows the effectiveness and superiority of our method and confirms its obvious engineering practicability.

Key words: complex distillation system, atmospheric distillation system, Kriging surrogate model, particle swarm optimization

中图分类号:

刘思乐王修纲吴静李德豹. 基于Kriging代理模型的复杂精馏系统操作参数优化[J]. 石油炼制与化工, 2020, 51(1): 114-120.

参考文献

[1] 董晓杨, 赵浩, 冯毅萍, 荣冈. 基于流程模拟的常减压装置过程操作与生产计划集成优化[J]. 化工学报, 2015, 66(01): 237-243.
[2] Raimondi A, Favela-Contreras A, Beltran-Carbajal F, Pinon-Rubio A, De La Pena-Elizondo J L. Design of an adaptive predictive control strategy for crude oil atmospheric distillation process[J]. Control Engineering Practice, 2015, 34: 39-48.
[3] 李秀芝. 常减压装置稳态模拟及改进的建模方法[J]. 计算机与应用化学, 2015, 32(05): 619-622.
[4] Chang A F, Liu Y A. Predictive Modeling of Large-Scale Integrated Refinery Reaction and Fractionation Systems from Plant Data. Part 1: Hydrocracking Processes[J]. Energy & Fuels, 2011, 25(11): 5264-5297.
[5] Pashikanti K, Liu Y A. Predictive Modeling of Large-Scale Integrated Refinery Reaction and Fractionation Systems from Plant Data. Part 2: Fluid Catalytic Cracking (FCC) Process[J]. Energy & Fuels, 2011, 25(11): 5298-5319.
[6] Pashikanti K, Liu Y A. Predictive Modeling of Large-Scale Integrated Refinery Reaction and Fractionation Systems from Plant Data. Part 3: Continuous Catalyst Regeneration (CCR) Reforming Process[J]. Energy & Fuels, 2011, 25(11): 5320-5344.
[7] Deb K, Pratap A, Agarwal S, Meyarivan T. A fast and elitist multiobjective genetic algorithm: NSGA-II[J]. IEEE Transactions on Evolutionary Computation, 2002, 6(2): 182-197.
[8] Sadighi S, Mohaddecy R S, Norouzian A. Optimizing an Industrial Scale Naphtha Catalytic Reforming Plant Using a Hybrid Artificial Neural Network and Genetic Algorithm Technique[J]. Bulletin of Chemical Reaction Engineering and Catalysis, 2015, 10(2): 210-220.
[9] Venter G, Sobieszczanski-Sobieski J. Particle swarm optimization[J]. Aiaa Journal, 2003, 41(8): 1583-1589.
[10] Yu H B, Tan Y C, Zeng J, Sun C L, Jin Y C. Surrogate-assisted hierarchical particle swarm optimization[J]. Information Sciences, 2018, 454(7): 59-72.
[11] 朱颢东, 钟勇. 一种改进的模拟退火算法[J]. 计算机技术与发展, 2009, 19(06): 32-35.
[12] Storn R, Price K. Differential Evolution - A Simple and Efficient Heuristic for global Optimization over Continuous Spaces[J]. Journal of Global Optimization, 1997, 11(4): 341-359.
[13] Wang Y, Yin D Q, Yang S X, Sun G Y. Global and Local Surrogate-Assisted Differential Evolution for Expensive Constrained Optimization Problems with Inequality Constraints[J]. IEEE Transactions on Cybernetics, 2019, 49(5): 1642-1656.
[14] 周明, 孙树栋, 彭炎午. 基于遗传模拟退火算法的机器人路径规划[J]. 航空学报, 1998, (01): 119-121.
[15] Zhang P, Chen H, Liu X, Zhang Z. An iterative multi-objective particle swarm optimization-based control vector parameterization for state constrained chemical and biochemical engineering problems[J]. Biochemical Engineering Journal, 2015, 103: 138-151.
[16] 何东海, 祁荣宾, 钱锋. 基于Kriging代理模型的序列优化[J]. 计算机与应用化学, 2014, 31(11): 1323-1328.
[17] 段星辰, 杜文莉. 基于bootstrap GEI算法的碳二加氢反应器代理模型 [J]. 化工学报, 2015, 66(12): 4904-4909.
[18] 刘宽, 王铁刚, 曹祖宾, 王莉. 化工流程模拟软件的介绍与对比[J]. 当代化工, 2013, (11): 1550-1553.
[19] 张兴, 袁飞. 轻烃蒸汽转化制氢HYSYS软件全流程模拟[J]. 当代化工, 2017, (03): 546-549.
[20] 王钧炎, 黄德先. 基于差分进化算法和HYSYS机理模型的催化重整过程优化[J]. 化工学报, 2008, (07): 1755-1760.
[21] 柏杨进, 薄翠梅, 丁良辉, 乔旭, 张公民. 运用HYSYS对背包式反应精馏过程控制的仿真[J]. 化工自动化及仪表, 2011, (06): 679-681+688.
[22] 王钧炎, 黄德先. 基于HYSYS的催化重整流程模拟及其应用[J]. 计算机与应用化学, 2007, (10): 1302-1306.
[23] 于晓栋, 吕文祥, 黄德先, 金以慧. 基于HYSYS和NSGA-Ⅱ的常压塔多目标优化[J]. 化工学报, 2008, (07): 1646-1649.
[24] Krige D G. A Statistical Approach to Some Basic Mine Valuation Problems on the Witwatersrand[J]. Journal of the Chemical, Metallurgical and Mining Society of South Africa, 1951, 52(6): 119-139.
[25] Zhou J, Su X, Cui G. An adaptive Kriging surrogate method for efficient joint estimation of hydraulic and biochemical parameters in reactive transport modeling[J]. Journal of Contaminant Hydrology, 2018, 216: 50-57.
[26] Wu C D, Zeng Y T, Lung S C C. A hybrid kriging/land-use regression model to assess PM2.5 spatial-temporal variability[J]. Science of the Total Environment, 2018, 645: 1456-1464.
[27] 乔成, 钟伟民, 范琛. 基于偏最小二乘的Kriging代理模型在加氢裂化建模中的应用[J]. 华东理工大学学报(自然科学版), 2017, (03): 383-388+396.
[28] 柳强, 焦国帅. 基于Kriging模型和NSGA-II的航空发动机管路卡箍布局优化[J]. 智能系统学报, 2019, (02): 1-7.
[29] 石博文, 尹燕燕, 刘飞. 基于PSO-控制变量参数化混合策略的间歇化工过程优化控制[J]. 化工学报, 2019, 70(03): 979-986.
[30] Jiang Y, Hu T, Huang C, Wu X. An improved particle swarm optimization algorithm[J]. Applied Mathematics and Computation, 2007, 193(1): 231-239.

基于Kriging代理模型的复杂精馏系统操作参数优化

OPERATION PARAMETER OPTIMIZATION OF COMPLEX DISTILLATION SYSTEM BASED ON KRIGING SURROGATE

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价