基于bootstrap GEI算法的碳二加氢反应器代理模型

doi:10.11949/j.issn.0438-1157.20151421

化工学报 ›› 2015, Vol. 66 ›› Issue (12): 4904-4909.DOI: 10.11949/j.issn.0438-1157.20151421

基于bootstrap GEI算法的碳二加氢反应器代理模型

段星辰, 杜文莉

华东理工大学化工过程先进控制和优化技术教育部重点实验室, 上海 200237

收稿日期:2015-09-08 修回日期:2015-09-30 出版日期:2015-12-05 发布日期:2015-12-05
通讯作者: 杜文莉
基金资助:
国家自然科学基金优秀青年基金项目(61422303, 61222303);国家自然科学基金青年项目(21206037);上海市教育委员会和上海市教育发展基金会曙光计划。

Surrogate model of acetylene hydrogenation reactor based on bootstrap GEI algorithm

DUAN Xingchen, DU Wenli

Key Laboratory of Advanced Control and Optimization for Chemical Processed of Ministry of Education, East China University of Science and Technology, Shanghai 200237, China

Received:2015-09-08 Revised:2015-09-30 Online:2015-12-05 Published:2015-12-05
Supported by:
supported by the China National Funds for Distinguished Young Scientists(61422303,61222303), the National Natural Science Foundation of China(21206037) and the Shu Guang Project of Shanghai Municipal Education Commisson and Shanghai Education Development Foundation.

摘要/Abstract

摘要：

碳二加氢反应器是乙烯工厂的一个重要装置,其运行状况直接影响着乙烯产品的纯度和产量,因此,提高碳二加氢反应过程的建模和优化效率对于工业实际具有重要意义。但是,直接对碳二加氢反应器的CFD高精度分析模型进行优化,计算量大,优化效率非常低。本文从模型预测方差准确性和提高全局搜索的有效性出发,基于Kriging代理模型,提出了一种求取无偏预测方差的广义期望提高算法——bootstrap GEI算法,通过测试函数的仿真对比,与bootstrap EI算法相比,该算法能够从全局角度搜索最优样本点,减少样本点的个数,从而提高模型更新和优化效率。该算法在实际工业碳二加氢等温反应器的代理模型中也得到了有效验证。

关键词: 模型, 全局优化算法, bootstrap算法, 加氢, 模拟

Abstract:

Acetylene hydrogenation reactor is an important device of the ethylene plant, and its working condition directly affects the purity and yield of ethylene products, so it is of great significance to improve the modeling and optimization efficiency of the reaction process for acetylene hydrogenation. However, directly optimizing high precision CFD models are often low efficiency because of the large calculation. This paper from the model accuracy of prediction variance and improvement of the effectiveness of global search, proposes a bootstrap GEI algorithm based on Kriging surrogate model. Through simulation contrast of test functions, compared with bootstrap EI algorithm, this algorithm can find the optimal sample points of global search and reduce the number of sample points, so as to improve the efficiency of the model updating and optimization. And this algorithm is effectively validated in the surrogate model of acetylene hydrogenation reactor.

Key words: model, EGO, bootstrap algorithm, hydrogenation, simulation

中图分类号:

TP18
TQ211

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.

DUAN Xingchen, DU Wenli. Surrogate model of acetylene hydrogenation reactor based on bootstrap GEI algorithm[J]. CIESC Journal, 2015, 66(12): 4904-4909.

参考文献 19

[1]	Li Zheng(李征). The system-based optimization of the injection molding process and its Parallel Computing [D]. Dalian:Dalian University of Technology, 2013.
[2]	Mu Xuefeng(穆雪峰), Yao Weixing(姚卫星), Yu Xiongqing(余雄庆), Liu Kelong(刘克龙), Xue Fei(薛飞). A survey of surrogate models used in MDO [J]. Chinese Journal of Computational Mechanics (计算力学学报), 2005, 22(5): 608-612.
[3]	Gao Yuehua(高月华). Optimization methods based on Kriging surrogate model and their application in injection modeling [D]. Dalian: Dalian University of Technology, 2009.
[4]	Jones D R, Schonlau M, Welch W J. Efficient global optimization of expensive black-box functions[J] . Journal of Global Optimization, 1998, 13(4): 455-492.
[5]	Schonlau M. Global versus local search in constrained optimization of computer models [J]. Lecture Notes-Monograph Series, 1998, 34(1): 11-25.
[6]	Sobester A, Leary S J, Keanr A J. On the design of optimization strategies based on global response surface approximation model [J]. Journal of Global Optimization, 2005, 33(1): 41-59.
[7]	Gao Yuehua(高月华),Wang Xicheng(王希诚). A sequential optimization method with multi-point sampling criterion based on Kriging Surrogate model [J]. Engineering Mechanics(工程力学), 2012, 29(4): 90-95.
[8]	Sykulski A M, Adams N M, Jennings N R. On-line adaptation of explotation in the one-armed bandit with covariates peoblem// Machine Learning and Applications[C]. Fourth International Conference. Washington, D.C, USA, 2010.
[9]	Xiao S, Rotaru M, Sykulski J K. Exploration versus exploitation using Kriging surrogate modeling in electromagnetic design [J]. The International Journal for Computation and Mathematics in Electrical and Electronic Engineering, 2012, 31(5): 1541-1551.
[10]	Xiao S, Rotaru M, Sykulski J K. Adaptive weighted expected improvement with reward approach in Kriging assisted electromagnetic design [J]. IEEE Transactions on Magnetics, 2013, 49(5): 2057-2060.
[11]	den Hertog D, Kleijnen J P C, Siem A Y D. The correct Kriging variance estimated by bootstrapping [J]. Journal of the Operational Research Society, 2006, 57(4): 400-409.
[12]	Kleijnen J P C, van Beers W, van Nieuwenhuyse I. Expected improvement in efficient global optimization through bootstrapped Kriging [J]. Journal of Global Optimization, 2012, 54(1): 59-73.
[13]	Lophaven S N, Nielsen H B, Sondergaard J. DACE-A Matlab Kriging toolbox, version 2.0[R].2002.
[14]	Zheng Anbo(郑安波), Ma Handong(马汉东), Luo Xiaoyun(罗小云). Multiobjective genetic algorithm based on Kriging [J]. Aeronautical Copputing Technique(航空计算技术), 2014, 36(2): 87-90.
[15]	Wang Fei(王飞). Steady-state, dynamic simulation and optimization of acetylene hydrogenation reactor in ethylene plant[D].Shanghai: East China University of Science and Technology, 2012 .
[16]	Wang Fei(王飞), Luo Na(罗娜), Jiang Da(蒋达), Qian Feng(钱锋). Dynamic simulation and control of acetylene hydrogenation reactor in ethylene plant [J]. Computers and Applied Chenistry(计算机与应用化学), 2012, 29(1): 85-89.
[17]	Hu Baolong(胡宝龙), Hu Guihua(胡贵华), Jiang Da(蒋达), Qian Feng(钱锋). Simulation and oprimization of operating parameters of isothermal reaction process for acetylene hydrogenation [J]. CIESC Journal (化工学报), 2015, 66(1): 366-372.
[18]	Müller J, Piché R. Mixture surrogate models based on Dempster-Shafer theory for global optimization problems [J]. Journal of Global Optimization, 2011, 51(1): 79-104.
[19]	Müller J, Shoemaker C A. Influence of ensemble surrogate models and sampling strategy on the solution quality of algorithms for computationally expensive black-box global optimization problems [J]. Journal of Global Optimization, 2014, 60(2): 123-144.

基于bootstrap GEI算法的碳二加氢反应器代理模型

Surrogate model of acetylene hydrogenation reactor based on bootstrap GEI algorithm

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献 19

相关文章 15

编辑推荐

Metrics

本文评价

[1]	叶展羽, 山訸, 徐震原. 用于太阳能蒸发的折纸式蒸发器性能仿真[J]. 化工学报, 2023, 74(S1): 132-140.
[2]	张龙, 宋孟杰, 邵苛苛, 张旋, 沈俊, 高润淼, 甄泽康, 江正勇. 管翅式换热器迎风侧翅片末端霜层生长模拟研究[J]. 化工学报, 2023, 74(S1): 179-182.
[3]	张义飞, 刘舫辰, 张双星, 杜文静. 超临界二氧化碳用印刷电路板式换热器性能分析[J]. 化工学报, 2023, 74(S1): 183-190.
[4]	王志国, 薛孟, 董芋双, 张田震, 秦晓凯, 韩强. 基于裂隙粗糙性表征方法的地热岩体热流耦合数值模拟与分析[J]. 化工学报, 2023, 74(S1): 223-234.
[5]	杨欣, 王文, 徐凯, 马凡华. 高压氢气加注过程中温度特征仿真分析[J]. 化工学报, 2023, 74(S1): 280-286.
[6]	宋嘉豪, 王文. 斯特林发动机与高温热管耦合运行特性研究[J]. 化工学报, 2023, 74(S1): 287-294.
[7]	张思雨, 殷勇高, 贾鹏琦, 叶威. 双U型地埋管群跨季节蓄热特性研究[J]. 化工学报, 2023, 74(S1): 295-301.
[8]	连梦雅, 谈莹莹, 王林, 陈枫, 曹艺飞. 地下水预热新风一体化热泵空调系统制热性能研究[J]. 化工学报, 2023, 74(S1): 311-319.
[9]	金正浩, 封立杰, 李舒宏. 氨水溶液交叉型再吸收式热泵的能量及分析[J]. 化工学报, 2023, 74(S1): 53-63.
[10]	王浩, 王振雷. 基于自适应谱方法的裂解炉烧焦模型化简策略[J]. 化工学报, 2023, 74(9): 3855-3864.
[11]	陈哲文, 魏俊杰, 张玉明. 超临界水煤气化耦合SOFC发电系统集成及其能量转化机制[J]. 化工学报, 2023, 74(9): 3888-3902.
[12]	宋明昊, 赵霏, 刘淑晴, 李国选, 杨声, 雷志刚. 离子液体脱除模拟油中挥发酚的多尺度模拟与研究[J]. 化工学报, 2023, 74(9): 3654-3664.
[13]	曹跃, 余冲, 李智, 杨明磊. 工业数据驱动的加氢裂化装置多工况切换过渡状态检测[J]. 化工学报, 2023, 74(9): 3841-3854.
[14]	胡建波, 刘洪超, 胡齐, 黄美英, 宋先雨, 赵双良. 有机笼跨细胞膜易位行为的分子动力学模拟研究[J]. 化工学报, 2023, 74(9): 3756-3765.
[15]	赵佳佳, 田世祥, 李鹏, 谢洪高. SiO₂-H₂O纳米流体强化煤尘润湿性的微观机理研究[J]. 化工学报, 2023, 74(9): 3931-3945.