基于数据驱动的石化过程建模与优化平台设计与开发
摘要
流程模拟、先进控制和过程优化技术的研究与应用是企业提高效益的主要手段之一,而建立准确的系统模型是实现优化的重要前提。由于石化过程的复杂性,智能建模方法得到了广泛的应用。因此设计开发一个基于生产数据驱动的智能化实用数据处理、建模与优化集成的平台具有重要的实用价值。
本文综合利用化学工程、系统工程、计算机、自动化技术,以大型石油化工生产过程为背景,研究石油化工过程的数据处理、过程建模与优化控制等技术,应用基于系统托管堆的动态链表以及多线程并行处理技术开发了基于数据流驱动的石化过程数据处理、建模与优化平台。平台的开发主要针对实验室从事的石油化工科研领域,同时兼顾其他领域的应用。平台采用组件化程序设计方法,设计了一系列具有良好的可重用性、语言无关性、高度开放性的软件组件。
基于平台,快速地定制了高密度聚乙烯装置串级反应优化操作改造系统,系统在实际企业应用取得社会与经济效益,从而证明了平台的通用性、可移植性与定制方面的便捷性。
Process simulation, advanced control and process optimization technologies are the main technical means for promoting the beneficial efficiency in enterprises. Then, building accurate system model is an important premise to realize the optimization. As petrochemical process is very complicated, Intelligence modeling method gets broad application. Thereby, there will be of great value to design and develop an intelligent integrated system based on data-driven, which is included by data processing, modeling and optimization.
In this paper, by comprehensive utilizing chemical engineering, system engineering, computer, automation technology, taking large-scale petrochemical industry procedure of production as background, studying data processing, modeling and optimization technology in petrochemical process, using the component programming, a series of software components are designed with well-reusability, language-irrelevant and highly open-performance, a software system is developed by integrating data processing, modeling and optimization with dynamic chain based on managed heap and multi-thread parallel processing technologies。a modeling and optimization system is suitable for petrochemical process, and the social and economic benefit are obtained from the actual application in the enterprise.
Based on that platform, HDPE Device cascade reaction optimizes operation reforming system has been customized rapidly. It proves applicability and portability of the platform and serviceability in customization.
本文综合利用化学工程、系统工程、计算机、自动化技术,以大型石油化工生产过程为背景,研究石油化工过程的数据处理、过程建模与优化控制等技术,应用基于系统托管堆的动态链表以及多线程并行处理技术开发了基于数据流驱动的石化过程数据处理、建模与优化平台。平台的开发主要针对实验室从事的石油化工科研领域,同时兼顾其他领域的应用。平台采用组件化程序设计方法,设计了一系列具有良好的可重用性、语言无关性、高度开放性的软件组件。
基于平台,快速地定制了高密度聚乙烯装置串级反应优化操作改造系统,系统在实际企业应用取得社会与经济效益,从而证明了平台的通用性、可移植性与定制方面的便捷性。
Process simulation, advanced control and process optimization technologies are the main technical means for promoting the beneficial efficiency in enterprises. Then, building accurate system model is an important premise to realize the optimization. As petrochemical process is very complicated, Intelligence modeling method gets broad application. Thereby, there will be of great value to design and develop an intelligent integrated system based on data-driven, which is included by data processing, modeling and optimization.
In this paper, by comprehensive utilizing chemical engineering, system engineering, computer, automation technology, taking large-scale petrochemical industry procedure of production as background, studying data processing, modeling and optimization technology in petrochemical process, using the component programming, a series of software components are designed with well-reusability, language-irrelevant and highly open-performance, a software system is developed by integrating data processing, modeling and optimization with dynamic chain based on managed heap and multi-thread parallel processing technologies。a modeling and optimization system is suitable for petrochemical process, and the social and economic benefit are obtained from the actual application in the enterprise.
Based on that platform, HDPE Device cascade reaction optimizes operation reforming system has been customized rapidly. It proves applicability and portability of the platform and serviceability in customization.
引文
[1]徐用懋,杨尔辅.石油化工流程模拟、先进控制与过程优化技术的现状与展望[J].工业控制计算机,2001,14(9)：21-27
[2]程志刚.连续蚁群优化算法的研究及其化工应用[D].浙江：浙江大学,2005
[3]傅永峰.软测量建模方法研究及其工业应用[D].浙江：浙江大学,2007
[4]Fortes I, Mora-Lopez L, Morales R, Triguero F. Inductive learning models with missing values[J]. Mathematical and Computer Modelling,2006,44(9):790-806
[5]Zhilin SI. Simple method for outlier detection in fitting experimental data under interval error.Chemometrics and Intelligent Laboratory Systems,2007,88(1):60-68
[6]李初福,陈丙珍,何小荣,邱彤,胡山鹰.用于含过失误差数据稳态检测的改进滤波法[J].清华大学学报(自然科学版),2004,44(9):1160-1162
[7]李杰.暂态与稳态过程的数字滤波[J].自动化与仪表,1996,3：55-56
[8]赵恒平,俞金寿.化工数据预处理及其在建模中的应用[J].华东理工大学学报(自然科学版),2005,31(2)：223-226
[9]许勇刚.基于RBF神经网络的稀土萃取过程组分含量软测量方法研究[D].江西：华东交通大学,2006
[10]Hanseok Ko, Robert H. Baran.Signal detectability enhancement with auto-associative backpropagation networks[J].Neurocomputing,1994,6(2):219-236
[11]Royston Goodacre, Joseph Pygall, Douglas B. Kell.Plant seed classification using pyrolysis mass spectrometry with unsupervised learning:The application of auto-associative and Kohonen artificial neural networks[J].Chemometrics and Intelligent Laboratory Systems,1996,34(1):69-83
[12]Reimann S.On the design of artificial auto-associative neuronal networks[J].Neural Networks,1998,11(4):611-621
[13]Ju Q, Yu ZB, Hao ZC, Ou GX, Zhao J, Liu D.Division-based rainfall-runoff simulations with BP neural networks and Xinanjiang model[J]. Neurocomputing,2009,72:2873-2883
[14]Zhao WX, Chen DZ, Hu SX. Detection of outlier and a robust BP algorithm against outlier[J]. Computers and Chemical Engineering,2004,28:1403-1408
[15]Yu SW, Zhu KJ, Diao FQ. A dynamic all parameters adaptive BP neural networks[J]. Applied Mathematics and Computation,2008,195(1):66-75
[16]Yi JQ, Wang Q, Zhao DB, Wen JT. BP neural network prediction-based variable-period sampling approach for networked control systems[J]. Applied Mathematics and Computation,2007,185(2): 976-988
[17]Sadeghi BHM. A BP-neural network predictor model for plastic injection molding process[J]. Journal of Materials Processing Technology,2000,103(3):411-416
[18]Donald K. Wedding Ⅱ, Krzysztof J. Time series forecasting by combining RBF networks, certainty factors, and the Box-Jenkins model[J]. Cios.Neurocomputing,1996,10(2):149-168
[19]Afantitis A, Melagraki G, Makridima K, Alexandridis A, Sarimveis H, Iglessi-Markopoulou O. Prediction of high weight polymers glass transition temperature using RBF neural networks[J]. Journal of Molecular Structure:THEOCHEM,2005,716(3):193-198
[20]Montazer GA, Sabzevari R, Khatir HG. Improvement of learning algorithms for RBF neuralnetworks in a helicopter sound identification system[J].Neurocomputing,71:167-173
[21]Zhang A, Zhang L. RBF neural networks for the prediction of building interference effects[J].Computers & Structures,2004,82(27):2333-2339
[22]Marinaro M, Scarpetta S.On-line learning in RBF neural networks:a stochastic approach[J]. Neural Networks,2000,13(7):719-729
[23]Polat Q, Yildirim T. Genetic optimization of GRNN for pattern recognition without feature extraction[J].Expert Systems with Applications,2008,34(4):2444-2448
[24]Chen TC,Yu CH. Motion control with deadzone estimation and compensation using GRNN for TWUSM drive system[J].Expert Systems with Applications,2009,36(8):10931-10941
[25]韩晓明.Elmari神经网络的应用研究[D].天津：天津大学,2006
[26]Seker S, Ayaz E, Turkcan E. Elman's recurrent neural network applications to condition monitoring in nuclear power plant and rotating machinery[J].Engineering Applications of Artificial Intelligence,2003,16:647-656
[27]Tong XJ, Wang Z, Yu HN. A research using hybrid RBF/Elman neural networks for intrusion detection system secure model[J].Computer Physics Communications,2009,180(10):1795-1801
[28]周志华,陈世福.神经网络集成.计算机学报[J].2002,25(1)：1-8
[29]Krogh A, Vedelsby J. Neural network ensembles, cross validation, and active learning[J]. In: Advances in Neural Information Processing Systems 7, CO:MIT Press, Cambridge, MA,1995: 231-238
[30]Zaier I, Shu C, Ouarda TBMJ., Seidou O, Chebana F. Estimation of ice thickness on lakes using artificial neural network ensembles [J] Journal of Hydrology,2010,383(3):330-340
[31]Martinez-Munoz G, Suarez A. Using boosting to prune bagging ensembles[J].Pattern Recognition Letters,2007,28(1):156-165
[32]苏晓红,郭茂祖,王亚东,张田文.基于偏最小二乘回归分析的混色数据学习算法研究[J].电子学报,2001,29(3)：429-431
[33]Kennedy J, Eberhart R. Particle Swarm Optimization[J]. IEEE Proceedings of IEEE International Conference on Network,1995,14:1942-1948
[34]El-Gallad AI, El-Hawary M, Sallam A. Swarm intelligence for hybrid cost dispatch proble[J]. Canadian Conference
[35]Dorigo M, Blum C.Ant colony optimization theory:a survey[J] Theoretical Computer Science,2005,344 (2-3):243-278
[36]Kanan HR, Faez K. An improved feature selection method based on ant colony optimization (ACO) evaluated on face recognition system[J].Applied Mathematics and. Computation,2008,205(2)
[37]Stutzle T, Dorigo M, Member S. A Short Convergence Proof for a Class of Ant Colony Optimization Algorithms[J].IEEE,2002,6(4):358-365
[38]Aymerich F, Serra M.Optimization of laminate stacking sequence for maximum buckling load using the ant colony optimization (ACO) metaheuristic[J].Composites Part A:Applied Science and Manufacturing,2008,39(2):262-272
[39]Ishibuchi H, Murata T. Single-objective and two-objective genetic algorithms for selecting linguistic rules for pattern classification problems[J]. Turksen. Fuzzy Sets and Systems,1997, 89(2):135-150
[40]Hwang SF,He RS. Improving real-parameter genetic algorithm with simulated annealing for engineering problems[J].Advances in Engineering Software, Volume 37, Issue 6, June 2006, Pages 406-418
[41]Chan DY, Ku CY, Li MC. A method to improve integer linear programming problem with branch-and-bound procedure[J].Applied Mathematics and Computation,2006,179(2):484-493
[42]Echols E, Cooper L. Solution of integer linear programming problems by direct search[J], Journal of Association for Computing Machinery,1968,15 (1):75-84
[43]Edward YH, Dennis L. Bricker.On the calculation of true and pseudo penalties in multiple choice integer programming[J].European Journal of Operational Research,1991,55(2):228-236
[44]Edward YH, Dennis L. Bricker.Computational comparison on the partitioning strategies in multiple choice integer programming[J].European Journal of Operational Research,88(1):182-202
[45]Pan PQ, Pan Y. A phase approach for the generalized simplex algorithm[J].Computer and Mathematics with Applications 2001 (42):1455-1464
[46]Domingos M. Cardoso, Joao CN.On the use of duality and pricing criteria in the generalized-simplex method[J].International Transactions in Operational Research,1995,2(1):107-116
[47]Kamoun A, Jaziri M, Chaabouni M.The use of the simplex method and its derivatives to the on-line optimization of the parameters of an injection moulding process[J].Chemometrics and Intelligent Laboratory Systems,2009,96(2):117-122
[48]Qiang X, Arthur Jutan. Continuous optimization using a dynamic simplex method[J].Chemical Engineering Science,2003,58(16):3817-3828
[49]Klabjan D.Subadditive approaches in integer programming[J].European Journal of Operational Research,183(2):525-545
[50]Gupta R, Bandopadhyaya L,Puri MC. Ranking in quadratic integer programming problems[J]. European Journal of Operational Research,1996,95(1):231-236
[51]Huang SM, Tsai CF, Huang PC. Component-based software version management based on a Component-Interface Dependency Matrix[J]. Journal of Systems and Software,2009, 82(3):382-399
[52]Grunske L. Early quality prediction of component-based systems-A generic framework[J]. Journal of Systems and Software,2007,80(5):678-686
[53]Xie F, Yang G, Song X. Component-based hardware/software co-verification for building trustworthy embedded systems[J]. Journal of Systems and Software,2007,80(5):643-654
[54]He HS, Larsen DR, Mladenoff DJ. Exploring component-based approaches in forest landscape modeling[J].Environmental Modeling & Software,2002,17(6):519-529
[55]杨卫,施伯乐.xML流管理研究综述[J].计算机研究与发展,2009,46(10)：1721-1728
[2]程志刚.连续蚁群优化算法的研究及其化工应用[D].浙江：浙江大学,2005
[3]傅永峰.软测量建模方法研究及其工业应用[D].浙江：浙江大学,2007
[4]Fortes I, Mora-Lopez L, Morales R, Triguero F. Inductive learning models with missing values[J]. Mathematical and Computer Modelling,2006,44(9):790-806
[5]Zhilin SI. Simple method for outlier detection in fitting experimental data under interval error.Chemometrics and Intelligent Laboratory Systems,2007,88(1):60-68
[6]李初福,陈丙珍,何小荣,邱彤,胡山鹰.用于含过失误差数据稳态检测的改进滤波法[J].清华大学学报(自然科学版),2004,44(9):1160-1162
[7]李杰.暂态与稳态过程的数字滤波[J].自动化与仪表,1996,3：55-56
[8]赵恒平,俞金寿.化工数据预处理及其在建模中的应用[J].华东理工大学学报(自然科学版),2005,31(2)：223-226
[9]许勇刚.基于RBF神经网络的稀土萃取过程组分含量软测量方法研究[D].江西：华东交通大学,2006
[10]Hanseok Ko, Robert H. Baran.Signal detectability enhancement with auto-associative backpropagation networks[J].Neurocomputing,1994,6(2):219-236
[11]Royston Goodacre, Joseph Pygall, Douglas B. Kell.Plant seed classification using pyrolysis mass spectrometry with unsupervised learning:The application of auto-associative and Kohonen artificial neural networks[J].Chemometrics and Intelligent Laboratory Systems,1996,34(1):69-83
[12]Reimann S.On the design of artificial auto-associative neuronal networks[J].Neural Networks,1998,11(4):611-621
[13]Ju Q, Yu ZB, Hao ZC, Ou GX, Zhao J, Liu D.Division-based rainfall-runoff simulations with BP neural networks and Xinanjiang model[J]. Neurocomputing,2009,72:2873-2883
[14]Zhao WX, Chen DZ, Hu SX. Detection of outlier and a robust BP algorithm against outlier[J]. Computers and Chemical Engineering,2004,28:1403-1408
[15]Yu SW, Zhu KJ, Diao FQ. A dynamic all parameters adaptive BP neural networks[J]. Applied Mathematics and Computation,2008,195(1):66-75
[16]Yi JQ, Wang Q, Zhao DB, Wen JT. BP neural network prediction-based variable-period sampling approach for networked control systems[J]. Applied Mathematics and Computation,2007,185(2): 976-988
[17]Sadeghi BHM. A BP-neural network predictor model for plastic injection molding process[J]. Journal of Materials Processing Technology,2000,103(3):411-416
[18]Donald K. Wedding Ⅱ, Krzysztof J. Time series forecasting by combining RBF networks, certainty factors, and the Box-Jenkins model[J]. Cios.Neurocomputing,1996,10(2):149-168
[19]Afantitis A, Melagraki G, Makridima K, Alexandridis A, Sarimveis H, Iglessi-Markopoulou O. Prediction of high weight polymers glass transition temperature using RBF neural networks[J]. Journal of Molecular Structure:THEOCHEM,2005,716(3):193-198
[20]Montazer GA, Sabzevari R, Khatir HG. Improvement of learning algorithms for RBF neuralnetworks in a helicopter sound identification system[J].Neurocomputing,71:167-173
[21]Zhang A, Zhang L. RBF neural networks for the prediction of building interference effects[J].Computers & Structures,2004,82(27):2333-2339
[22]Marinaro M, Scarpetta S.On-line learning in RBF neural networks:a stochastic approach[J]. Neural Networks,2000,13(7):719-729
[23]Polat Q, Yildirim T. Genetic optimization of GRNN for pattern recognition without feature extraction[J].Expert Systems with Applications,2008,34(4):2444-2448
[24]Chen TC,Yu CH. Motion control with deadzone estimation and compensation using GRNN for TWUSM drive system[J].Expert Systems with Applications,2009,36(8):10931-10941
[25]韩晓明.Elmari神经网络的应用研究[D].天津：天津大学,2006
[26]Seker S, Ayaz E, Turkcan E. Elman's recurrent neural network applications to condition monitoring in nuclear power plant and rotating machinery[J].Engineering Applications of Artificial Intelligence,2003,16:647-656
[27]Tong XJ, Wang Z, Yu HN. A research using hybrid RBF/Elman neural networks for intrusion detection system secure model[J].Computer Physics Communications,2009,180(10):1795-1801
[28]周志华,陈世福.神经网络集成.计算机学报[J].2002,25(1)：1-8
[29]Krogh A, Vedelsby J. Neural network ensembles, cross validation, and active learning[J]. In: Advances in Neural Information Processing Systems 7, CO:MIT Press, Cambridge, MA,1995: 231-238
[30]Zaier I, Shu C, Ouarda TBMJ., Seidou O, Chebana F. Estimation of ice thickness on lakes using artificial neural network ensembles [J] Journal of Hydrology,2010,383(3):330-340
[31]Martinez-Munoz G, Suarez A. Using boosting to prune bagging ensembles[J].Pattern Recognition Letters,2007,28(1):156-165
[32]苏晓红,郭茂祖,王亚东,张田文.基于偏最小二乘回归分析的混色数据学习算法研究[J].电子学报,2001,29(3)：429-431
[33]Kennedy J, Eberhart R. Particle Swarm Optimization[J]. IEEE Proceedings of IEEE International Conference on Network,1995,14:1942-1948
[34]El-Gallad AI, El-Hawary M, Sallam A. Swarm intelligence for hybrid cost dispatch proble[J]. Canadian Conference
[35]Dorigo M, Blum C.Ant colony optimization theory:a survey[J] Theoretical Computer Science,2005,344 (2-3):243-278
[36]Kanan HR, Faez K. An improved feature selection method based on ant colony optimization (ACO) evaluated on face recognition system[J].Applied Mathematics and. Computation,2008,205(2)
[37]Stutzle T, Dorigo M, Member S. A Short Convergence Proof for a Class of Ant Colony Optimization Algorithms[J].IEEE,2002,6(4):358-365
[38]Aymerich F, Serra M.Optimization of laminate stacking sequence for maximum buckling load using the ant colony optimization (ACO) metaheuristic[J].Composites Part A:Applied Science and Manufacturing,2008,39(2):262-272
[39]Ishibuchi H, Murata T. Single-objective and two-objective genetic algorithms for selecting linguistic rules for pattern classification problems[J]. Turksen. Fuzzy Sets and Systems,1997, 89(2):135-150
[40]Hwang SF,He RS. Improving real-parameter genetic algorithm with simulated annealing for engineering problems[J].Advances in Engineering Software, Volume 37, Issue 6, June 2006, Pages 406-418
[41]Chan DY, Ku CY, Li MC. A method to improve integer linear programming problem with branch-and-bound procedure[J].Applied Mathematics and Computation,2006,179(2):484-493
[42]Echols E, Cooper L. Solution of integer linear programming problems by direct search[J], Journal of Association for Computing Machinery,1968,15 (1):75-84
[43]Edward YH, Dennis L. Bricker.On the calculation of true and pseudo penalties in multiple choice integer programming[J].European Journal of Operational Research,1991,55(2):228-236
[44]Edward YH, Dennis L. Bricker.Computational comparison on the partitioning strategies in multiple choice integer programming[J].European Journal of Operational Research,88(1):182-202
[45]Pan PQ, Pan Y. A phase approach for the generalized simplex algorithm[J].Computer and Mathematics with Applications 2001 (42):1455-1464
[46]Domingos M. Cardoso, Joao CN.On the use of duality and pricing criteria in the generalized-simplex method[J].International Transactions in Operational Research,1995,2(1):107-116
[47]Kamoun A, Jaziri M, Chaabouni M.The use of the simplex method and its derivatives to the on-line optimization of the parameters of an injection moulding process[J].Chemometrics and Intelligent Laboratory Systems,2009,96(2):117-122
[48]Qiang X, Arthur Jutan. Continuous optimization using a dynamic simplex method[J].Chemical Engineering Science,2003,58(16):3817-3828
[49]Klabjan D.Subadditive approaches in integer programming[J].European Journal of Operational Research,183(2):525-545
[50]Gupta R, Bandopadhyaya L,Puri MC. Ranking in quadratic integer programming problems[J]. European Journal of Operational Research,1996,95(1):231-236
[51]Huang SM, Tsai CF, Huang PC. Component-based software version management based on a Component-Interface Dependency Matrix[J]. Journal of Systems and Software,2009, 82(3):382-399
[52]Grunske L. Early quality prediction of component-based systems-A generic framework[J]. Journal of Systems and Software,2007,80(5):678-686
[53]Xie F, Yang G, Song X. Component-based hardware/software co-verification for building trustworthy embedded systems[J]. Journal of Systems and Software,2007,80(5):643-654
[54]He HS, Larsen DR, Mladenoff DJ. Exploring component-based approaches in forest landscape modeling[J].Environmental Modeling & Software,2002,17(6):519-529
[55]杨卫,施伯乐.xML流管理研究综述[J].计算机研究与发展,2009,46(10)：1721-1728