| 154 | 0 | 128 |
| 下载次数 | 被引频次 | 阅读次数 |
针对需要大量采样点保证参数估计的精确度使得样本分析成本过高的问题，提出一种基于拉丁超立方体采样的最优采样策略，既能减少采样点数量又能保证参数估计精度。最优采样策略通过拉丁超立方体采样参数空间候选值并求解相应的最优采样子问题，构建各潜在采样点的选择频率，使用启发式策略和迭代增强策略选择采样点，并实现参数估计。数值仿真结果表明，提出的采样策略在保证参数估计精度情况下，能够大幅度降低采样点数量，基于随机采样的最优采样方法相比，稳定性更好。
Abstract：A large number of sampling points are required to ensure the accuracy of parameter estimation,which leads to high cost of sample analysis. An optimal sampling strategy was thus put forward based on Latin hypercube sampling to reduce the number of sampling points and ensure parameter estimation accuracy. By solving corresponding optimal sampling sub-problems with the candidate values of parameter space by Latin hypercube sampling, the selection frequency of each potential sampling point was constructed in the optimal sampling strategy. Sampling points were selected by virtue of heuristic strategy and iterative enhancement strategy, and parameter estimation was achieved. The numerical simulation results show that the sampling strategy proposed can greatly reduce the number of sampling points while ensuring parameter estimation accuracy. In addition, it is more stable than the optimal sampling method based on random sampling.
[1]蔡伟.国内外高密度聚乙烯的供需现状及未来发展分析[J].石油化工技术与经济, 2020, 36(4):9-14.CAI W. Worldwide supply-demand status and future development analysis of high-density polyethylene resins[J].Techno-Economics in Petrochemicals, 2020, 36(4):9-14.
[2]顾雪萍,王艳丽,陈曦,等.基于聚合物分子量分布的乙烯淤浆聚合工艺优化[J].化工学报, 2013, 64(2):649-655.GU X P, WANG Y L, CHEN X, et al. Optimization of ethylene slurry polymerization conditions based on molecular weight distribution[J]. CIESC Journal, 2013, 64(2):649-655.
[3] MCLEAN K A P, MCAULEY K B. Mathematical modelling of chemical processes—Obtaining the best model predictions and parameter estimates using identifiability and estimability procedures[J]. The Canadian Journal of Chemical Engineering, 2012,90(2):351-366.
[4] YAO K Z, SHAW B M, KOU B, et al. Modeling ethylene/butene copolymerization with multi-site catalysts:Parameter estimability and experimental design[J]. Polymer Reaction Engineering, 2003, 11(3):563-588.
[5] CHU Y, HAHN J. Parameter set selection for estimation of nonlinear dynamic systems[J]. AIChE Journal, 2007, 53(11):2858-2870.
[6] FYSIKOPOULOS D, BENYAHIA B, BORSOS A, et al. A framework for model reliability and estimability analysis of crystallization processes with multi-impurity multi-dimensional population balance models[J]. Computers&Chemical Engineering, 2019, 122:275-292.
[7] ONYEMELUKWE I I, BENYAHIA B, REIS N M, et al. The heat transfer characteristics of a mesoscale continuous oscillatory flow crystalliser with smooth periodic constrictions[J]. International Journal of Heat and Mass Transfer, 2018, 123:1109-1119.
[8] CHEN W, BIEGLER L T, MUNOZ S G. Kinetic parameter estimation based on spectroscopic data with unknown absorbing species[J]. AIChE Journal, 2018, 64(10):3595-3613.
[9] NOGUEIRA I B R, PONTES K V. Parameter estimation with estimability analysis app lied to an industrial scale polymerization process[J]. Computers&Chemical Engineering, 2017, 96:75-86.
[10] MACHADO V C, TAPIA G, GABRIEL D, et al. Systematic identifiability study based on the Fisher information matrix for reducing the number of parameters calibration of an activated sludge model[J]. Environmental Modelling&Software, 2009, 24(11):1274-1284.
[11] BRUN R, KUHNI M, SIEGRIST H, et al. Practical identifiability of ASM2d parameters-systematic selection and tuning of parameter subsets[J]. Water Research, 2002, 36(16):4113-4127.
[12] JOLLIFFE I T. Discarding variables in a principal component analysis. I:Artificial data[J]. Journal of the Royal Statistical Society:Series C(Applied Statistics), 1972, 21(2):160-173.
[13] CHEN W, BIEGLER L T. Reduced Hessian based parameter selection and estimation with simultaneous collocation approach[J].AIChE Journal, 2020, 66(7):e16242.
[14] ATKINSON A, DONEV A, TOBIAS R. Optimum experimental designs, with SAS[M]. New York:Oxford University Press, 2007.
[15] GOOS P, JONES B. Optimal design of experiments:a case study approach[M]. Chichester:John Wiley&Sons, 2011.
[16] PUKELSHEIM F. Optimal design of experiments[M]. New York:Society for Industrial and Applied Mathematics, 2006.
[17] FRANCESCHINI G, MACCHIETTO S. Model-based design of experiments for parameter precision:State of the art[J]. Chemical Engineering Science, 2008, 63(19):4846-4872.
[18] KUTALIK Z, CHO K H, WOLKENHAUER O. Optimal sampling time selection for parameter estimation in dynamic pathway modeling[J]. Biosystems, 2004, 75(1-3):43-55.
[19] HOANG M D, BARZ T, MERCHAN V A, et al. Simultaneous solution approach to model-based experimental design[J]. AIChE Journal, 2013, 59(11):4169-4183.
[20] CHEN W, BIEGLER L T. Near-optimal time series sampling based on the reduced Hessian[J]. AIChE Journal, 2020, 66(7):e16248.
[21] GILL P E, MURRAY W, SAUNDERS M A, et al. Computing forward-difference intervals for numerical optimization[J]. SIAM Journal on Scientific and Statistical Computing, 1983, 4(2):310-321.
[22] ZHANG C, SHAO Z, CHEN X, et al. Kinetic parameter estimation of HDPE slurry process from molecular weight distribution:Estimability analysis and multistep methodology[J]. AIChE Journal, 2014, 60(10):3442-3459.
[23] FONTES C H, MENDES M J. Analysis of an industrial continuous slurry reactor for ethylene-butene copolymerization[J]. Polymer,2005, 46(9):2922-2932.
[24]沈航.淤浆聚乙烯生产流程ASPEN建模[D].杭州:浙江大学, 2006.SHEN H. Modeling of slurry polyethylene processes using Aspen Plus[D]. Hangzhou:Zhejiang University, 2006.
[25]刘蒙蒙,占志良,邵之江,等.基于联立法的乙烯淤浆聚合牌号切换过程动态模拟[J].化工学报, 2012, 63(9):2703-2709.LIU M M, ZHAN Z L, SHAO Z J, et al. Dynamic simulation of grade transition for ethylene slurry polymerization process based on simultaneous approach[J]. CIESC Journal, 2012, 63(9):2703-2709.
[26] MA Y, CHEN X, EASON J P, et al. Dynamic optimization for grade transition processes using orthogonal collocation on molecular weight distribution[J]. AIChE Journal, 2019, 65(4):1198-1210.
[27] MCKAY M D, BECKMAN R J, CONOVER W J. A comparison of three methods for selecting values of input variables in the analysis of output from a computer code[J]. Technometrics, 2000, 42(1):55-61.
[28]孔婧.考虑传递现象的复杂聚合反应过程模拟与优化方法[D].杭州:浙江大学, 2020.KONG J. Simulation and optimization of complex polymerization processes with transport phenomenon[D]. Hangzhou:Zhejiang University, 2020.
基本信息:
中图分类号:TQ325.12
引用信息:
[1]尹鹏,陈伟锋.面向高密度聚乙烯生产过程的最优采样策略[J],2022,36(05):738-747.
基金信息:
国家重点研发计划(2017YFE0106700);; 国家自然科学基金(61873242)
2021-06-11
2021
2021-10-27
2021
1