基于正交余弦相似度的间歇过程操作曲线优化
|
摘要
针对间歇过程的操作曲线优化问题,利用正交信号校正算法,提出一种基于正交余弦相似度的数据驱动型优化策略。利用部分批次指标变量定义指标相关子空间,并通过奇异值分解获得背景空间的基,将新批次时段变量投影到正交基上从而提取出指标相关的信息;采用主元分析算法对校正后的变量降维,在降维后的载荷平面中,基于各校正时段变量与指标变量的余弦相似度实现操作曲线的优化;考虑到变量间的相似度会随着批次发生变化,推导出递推算法来更新操作曲线。将该方法应用到双酚A间歇结晶过程的温度曲线优化中,预测产率的提升验证了所提方法的可行性。
For manipulated trajectory optimization of batch processes, a data-driven optimization method based on orthogonal cosine similarity was proposed with orthogonal signal correction algorithm. Firstly, the index-relevant subspace was defined and the basis of background space was acquired with some batches of index variable. The index-irrelevant information was removed from time-segmental variables after correction. Then, the dimension of the corrected variables was reduced with principal component analysis algorithm and the trajectory was optimized by cosine similarity between the corrected time-segmental variables and the controlled quality index variable in the low dimensional plane. Finally, the recursive algorithm for trajectory optimization was derived considering changes of cosine similarity between batches. The method was employed in the temperature trajectory optimization of Bisphenol A crystallization process and the results illustrate the effectiveness and benefit.
For manipulated trajectory optimization of batch processes, a data-driven optimization method based on orthogonal cosine similarity was proposed with orthogonal signal correction algorithm. Firstly, the index-relevant subspace was defined and the basis of background space was acquired with some batches of index variable. The index-irrelevant information was removed from time-segmental variables after correction. Then, the dimension of the corrected variables was reduced with principal component analysis algorithm and the trajectory was optimized by cosine similarity between the corrected time-segmental variables and the controlled quality index variable in the low dimensional plane. Finally, the recursive algorithm for trajectory optimization was derived considering changes of cosine similarity between batches. The method was employed in the temperature trajectory optimization of Bisphenol A crystallization process and the results illustrate the effectiveness and benefit.
引文
[1] 邱爽,宋一鸣.间歇式反应釜温度串级预测函数控制[J].化学工程,2013,41(10):63-68.
[2] SRINIVASAN B,BONVIN D.Real-time optimization of batch processes by tracking the necessary conditions of optimality[J].Industrial and Engineering Chemistry Research,2007,46(2):301-320.
[3] CHACHUAT B,SRINIVASAN B,BONVIN D.Adaptation strategies for real-time optimization[J].Computers and Chemical Engineering,2009,33(10):1557-1567.
[4] DAI Wei,WORD P D,HAHN J.Modeling and dynamic optimization of fuel-grade ethanol fermentation using fed-batch process[J].Control Engineering Practice,2014,22(1):231-241.
[5] FACCO P,DOPLICHER F,BEZZO F,et al.Moving ave-rage PLS soft sensor for online product quality estimation in an industrial batch polymerization process[J].Journal of Process Control,2009,19(3):520-529.
[6] GUNTHER J C,CONNER J S,SEBORG D E.Process monitoring and quality variable prediction utilizing PLS in industrial fed-batch cell culture[J].Journal of Process Control,2009,19(5):914-921.
[7] YU Zhongbo,LIU Di,LV Haishen,et al.A multi-layer soil moisture data assimilation using support vector machines and ensemble particle filter[J].Journal of Hydrology,2012,475(6):53-64.
[8] SI Fengqi,ROMERO C E,YAO Zheng,et al.Optimization of coal-fired boiler SCRs based on modified support vector machine models and genetic algorithms[J].Fuel,2009,88(5):806-816.
[9] YILDIZ S.Artificial neural network (ANN) approach for modeling Zn(II) adsorption in batch process[J].Korean Journal of Chemical Engineering,2017,34(8):1-12.
[10] SHAHRYARI Z,SHARIFI A,MOHEBBI A.Artificial neural network (ANN) approach for modeling and formulation of phenol adsorption onto activated carbon[J].Journal of Engineering Thermophysics,2013,22(4):322-336.
[11] MARTINEZ E C,CRISTALDI M D,GRAU R J.Design of dynamic experiments in modeling for optimization of batch processes[J].Industrial and Engineering Chemistry Research,2009,48(7):3453-3465.
[12] WISSMANN P J,GROVER M A.A new approach to batch process optimization using experimental design[J].AIChE Journal,2010,55(2):353.
[13] CHU Yunfei,HAHN J.Quantitative optimal experimental design using global sensitivity analysis via quasi-linearization[J].Industrial and Engineering Chemistry Research,2010,49(17):7782-7794.
[14] CHEN Xi,ZHANG Lei,KONG Xiangsong,et al.Automa-tic velocity profile determination for uniform filling in injection molding[J].Polymer Engineering and Science,2010,50(7):1358-1371.
[15] KONG Xiangsong,YANG Yi,CHEN Xi,et al.Quality control via model-free optimization for a type of batch process with a short cycle time and low operational cost[J].Industrial and Engineering Chemistry Research,2011,50(5):2994-3003.
[16] YANG Yi,YANG Bo,ZHU Shengqiang,et al.Online quality optimization of the injection molding process via digital image processing and model-free optimization[J].Journal of Materials Processing Technology,2015,226:85-98.
[17] 仇力,栾小丽,刘飞.基于主元相似度的间歇过程操作曲线递推优化[J].化工学报,2017,68(7):2859-2865.
[18] WANG Guang,YIN Shen.Quality-related fault detection approach based on orthogonal signal correction and modified PLS[J].IEEE Transactions on Industrial Informa-tics,2015,11(2):398-405.
[19] 叶凌箭,马修水,宋执环.不确定性间歇过程的一种实时优化控制方法[J].化工学报,2014,65(9):3535-3543.
[20] HARRINGTON P B,KISTER J,ARTAUD J,et al.Automated principal component-based orthogonal signal correction applied to fused near infrared-mid-infrared spectra of french olive oils[J].Analytical Chemistry,2009,81(17):7160-7169.
[21] HARKAT M F,MOUROT G,RAGOT J.An improved PCA scheme for sensor FDI: Application to an air quality monitoring network[J].Journal of Process Control,2006,16(6):625-634.
[22] 张媛媛,韩少廷,耿志强,等.自适应移动窗递推PCA过程监测方法研究[J].计算机与应用化学,2011,28(8):1022-1026.
[2] SRINIVASAN B,BONVIN D.Real-time optimization of batch processes by tracking the necessary conditions of optimality[J].Industrial and Engineering Chemistry Research,2007,46(2):301-320.
[3] CHACHUAT B,SRINIVASAN B,BONVIN D.Adaptation strategies for real-time optimization[J].Computers and Chemical Engineering,2009,33(10):1557-1567.
[4] DAI Wei,WORD P D,HAHN J.Modeling and dynamic optimization of fuel-grade ethanol fermentation using fed-batch process[J].Control Engineering Practice,2014,22(1):231-241.
[5] FACCO P,DOPLICHER F,BEZZO F,et al.Moving ave-rage PLS soft sensor for online product quality estimation in an industrial batch polymerization process[J].Journal of Process Control,2009,19(3):520-529.
[6] GUNTHER J C,CONNER J S,SEBORG D E.Process monitoring and quality variable prediction utilizing PLS in industrial fed-batch cell culture[J].Journal of Process Control,2009,19(5):914-921.
[7] YU Zhongbo,LIU Di,LV Haishen,et al.A multi-layer soil moisture data assimilation using support vector machines and ensemble particle filter[J].Journal of Hydrology,2012,475(6):53-64.
[8] SI Fengqi,ROMERO C E,YAO Zheng,et al.Optimization of coal-fired boiler SCRs based on modified support vector machine models and genetic algorithms[J].Fuel,2009,88(5):806-816.
[9] YILDIZ S.Artificial neural network (ANN) approach for modeling Zn(II) adsorption in batch process[J].Korean Journal of Chemical Engineering,2017,34(8):1-12.
[10] SHAHRYARI Z,SHARIFI A,MOHEBBI A.Artificial neural network (ANN) approach for modeling and formulation of phenol adsorption onto activated carbon[J].Journal of Engineering Thermophysics,2013,22(4):322-336.
[11] MARTINEZ E C,CRISTALDI M D,GRAU R J.Design of dynamic experiments in modeling for optimization of batch processes[J].Industrial and Engineering Chemistry Research,2009,48(7):3453-3465.
[12] WISSMANN P J,GROVER M A.A new approach to batch process optimization using experimental design[J].AIChE Journal,2010,55(2):353.
[13] CHU Yunfei,HAHN J.Quantitative optimal experimental design using global sensitivity analysis via quasi-linearization[J].Industrial and Engineering Chemistry Research,2010,49(17):7782-7794.
[14] CHEN Xi,ZHANG Lei,KONG Xiangsong,et al.Automa-tic velocity profile determination for uniform filling in injection molding[J].Polymer Engineering and Science,2010,50(7):1358-1371.
[15] KONG Xiangsong,YANG Yi,CHEN Xi,et al.Quality control via model-free optimization for a type of batch process with a short cycle time and low operational cost[J].Industrial and Engineering Chemistry Research,2011,50(5):2994-3003.
[16] YANG Yi,YANG Bo,ZHU Shengqiang,et al.Online quality optimization of the injection molding process via digital image processing and model-free optimization[J].Journal of Materials Processing Technology,2015,226:85-98.
[17] 仇力,栾小丽,刘飞.基于主元相似度的间歇过程操作曲线递推优化[J].化工学报,2017,68(7):2859-2865.
[18] WANG Guang,YIN Shen.Quality-related fault detection approach based on orthogonal signal correction and modified PLS[J].IEEE Transactions on Industrial Informa-tics,2015,11(2):398-405.
[19] 叶凌箭,马修水,宋执环.不确定性间歇过程的一种实时优化控制方法[J].化工学报,2014,65(9):3535-3543.
[20] HARRINGTON P B,KISTER J,ARTAUD J,et al.Automated principal component-based orthogonal signal correction applied to fused near infrared-mid-infrared spectra of french olive oils[J].Analytical Chemistry,2009,81(17):7160-7169.
[21] HARKAT M F,MOUROT G,RAGOT J.An improved PCA scheme for sensor FDI: Application to an air quality monitoring network[J].Journal of Process Control,2006,16(6):625-634.
[22] 张媛媛,韩少廷,耿志强,等.自适应移动窗递推PCA过程监测方法研究[J].计算机与应用化学,2011,28(8):1022-1026.