基于改进PSO的发酵过程同步串联混合建模

杨强大; 张卫军; 牛大鹏

doi:10.16383/j.aas.2015.c131195

基于改进PSO的发酵过程同步串联混合建模

doi: 10.16383/j.aas.2015.c131195

1.
东北大学材料与冶金学院沈阳 110819;
2.
东北大学信息科学与工程学院沈阳 110819

基金项目:

高等学校博士学科点专项科研基金 (20120042120014),国家自然科学基金 (61304121, 51476024),中央高校基本科研业务费专项资金(N130404024)资助

详细信息

作者简介:
张卫军东北大学教授.主要研究方向为热工过程建模、优化与控制, 系统节能理论与应用. E-mail: zhangwj@smm.neu.edu.cn

通讯作者:
杨强大东北大学讲师.主要研究方向为复杂工业过程建模与优化, 软测量技术.本文通信作者. E-mail: yangqd@smm.neu.edu.cn

计量
- 文章访问数: 1617
- HTML全文浏览量: 54
- PDF下载量: 1011
- 被引次数: 33
出版历程
- 收稿日期: 2013-12-30
- 修回日期: 2014-11-04
- 刊出日期: 2015-03-20

Simultaneous Series Hybrid Modeling for Fermentation Process Based on Improved Particle Swarm Optimization

1.
School of Materials and Metallurgy, Northeastern University, Shenyang 110819;
2.
School of Information Science and Engineering, Northeastern University, Shenyang 110819

Funds:

Supported by Specialized Research Fund for the Doctoral Program of Higher Education (20120042120014), National Natural Science Foundation of China (61304121, 51476024), Fundamental Research Funds for the Central Universities (N130404024)

摘要

摘要: 准确可靠的过程模型是实现发酵过程优化的基础和前提. 对于反应机理复杂的发酵过程,串联混合建模是一种相对有效的建模方法, 但现有方法需要利用插值所得的数据进行中间变量黑箱模型的构建, 较大程度地影响了所建混合模型的泛化性能. 为此,提出一种可将黑箱模型构建问题转化为动态模型参数辨识问题的同步串联混合建模方法, 从而避免了现有方法需利用插值数据来构建黑箱模型的不足; 通过引入多精英学习策略和惯性权重自适应调整策略, 构造了一种改进的粒子群优化(Particle swarm optimization, PSO)算法自适应多精英学习PSO (Adaptive multi-elite learning PSO, AMLPSO)算法,并采用该算法求取黑箱模型的参数; 借鉴均匀设计思想确定黑箱模型的结构. 利用诺西肽分批发酵过程实际生产数据进行实验研究, 结果验证了所提方法的有效性.
- 发酵过程 /
- 同步串联混合建模 /
- 粒子群优化 /
- 算法改进 /
- 均匀设计
Abstract: An accurate and reliable model is the basis and premise for achieving fermentation process optimization. Series hybrid modeling is a relatively more effective method for fermentation process with complex reaction mechanisms, but it needs data obtained from interpolation to develop the black-box models of intermediate variables, which considerably influences the generalization performance of the final hybrid model. Therefore, in this paper, we present a simultaneous series hybrid modeling method, which can transform the black-box model development problem into a dynamic model parameter identification problem, and thus overcome the shortage that existing methods need interpolation data for the development of black-box models. By introducing multi-elite learning and adaptive inertia weight adjustment strategies, an improved particle swarm optimization (PSO) called adaptive multi-elite learning PSO (AMLPSO) is constructed to determine the parameters of black-box models. Uniform design method is used to select the structure of black-box models. Experimental study is carried out based on the practical production data from nosiheptide batch fermentation process, and the results show the effectiveness of the proposed method.
- Fermentation process /
- simultaneous series hybrid modeling /
- particle swarm optimization (PSO) /
- algorithm improvement /
- uniform design

HTML全文

参考文献(31)

[1]	Shi Zhong-Ping, Pan Feng. Fermentation Process Analysis, Control and Detection Technology (2nd Edition). Beijing: Chemical Industry Press, 2010. 1-10(史仲平, 潘丰. 发酵过程解析、控制与检测技术(第2版). 北京: 化学工业出版社, 2010. 1-10)
[2]	[2] Sharma V, Mishra H N. Unstructured kinetic modeling of growth and lactic acid production by Lactobacillus plantarum NCDC 414 during fermentation of vegetable juices. LWT-Food Science and Technology, 2014, 59(2): 1123-1128
[3]	[3] Wang R F, Koppram R, Olsson L, Franzn C J. Kinetic modeling of multi-feed simultaneous saccharification and co-fermentation of pretreated birch to ethanol. Bioresource Technology, 2014, 172: 303-311
[4]	[4] Dragoi E N, Curteanu S, Galaction A I, Cascaval D. Optimization methodology based on neural networks and self-adaptive differential evolution algorithm applied to an aerobic fermentation process. Applied Soft Computing, 2013, 13(1): 222-238
[5]	[5] Wang J L, Feng X Y, Yu T. A geometric approach to support vector regression and its application to fermentation process fast modeling. Chinese Journal of Chemical Engineering, 2012, 20(4): 715-722
[6]	[6] Setoodeh P, Jahanmiri A, Eslamloueyan R. Hybrid neural modeling framework for simulation and optimization of diauxie-involved fed-batch fermentative succinate production. Chemical Engineering Science, 2012, 81: 57-76
[7]	Chen Jin-Dong, Pan Feng. Hybrid modeling for penicillin fermentation process. CIESC J, 2010, 61(8): 2092-2096 (陈进东, 潘丰. 青霉素发酵过程中的混合建模. 化工学报, 2010, 61(8): 2092-2096)
[8]	[8] James S, Legge R, Budman H. Comparative study of black-box and hybrid estimation methods in fed-batch fermentation. Journal of Process Control, 2002, 12(1): 113-121
[9]	[9] Wang X F, Chen J D, Liu C B, Pan F. Hybrid modeling of penicillin fermentation process based on least square support vector machine. Chemical Engineering Research and Design, 2010, 88(4): 415-420
[10]	Zorzetto L F M, Filho R M, Wolf-Maciel M R. Processing modelling development through artificial neural networks and hybrid models. Computers and Chemical Engineering, 2000, 24(2-7): 1355-1360
[11]	Laursen S , Webb D, Ramirez W F. Dynamic hybrid neural network model of an industrial fed-batch fermentation process to produce foreign protein. Computers and Chemical Engineering, 2007, 31(3): 163-170
[12]	Saraceno A, Curcio S, Calabr V, Iorio G. A hybrid neural approach to model batch fermentation of ricotta cheese whey to ethanol. Computers and Chemical Engineering, 2010, 34(10): 1590-1596
[13]	Beluhan D, Beluhan S. Hybrid modeling approach to on-line estimation of yeast biomass concentration in industrial bioreactor. Biotechnology Letters, 2000, 22(8): 631-635
[14]	Birol G, ndey C, Cinar A. A modular simulation package for fed-batch fermentation: penicillin production. Computers and Chemical Engineering, 2002, 26(11): 1553-1565
[15]	Shukla R, Chand S, Srivastava A K. Batch kinetics and modeling of gibberellic acid production by Gibberella fujikuroi. Enzyme and Microbial Technology, 2005, 36(4): 492-497
[16]	Kennedy J, Eberhart R C. Particle swarm optimization. In: Proceedings of the 1995 IEEE International Conference on Neural Networks. Perth, WA: IEEE, 1995. 1942-1948
[17]	Yang C H, Tsai S W, Chuang L Y, Yang C H. An improved particle swarm optimization with double-bottom chaotic maps for numerical optimization. Applied Mathematics and Computation, 2012, 219(1): 260-279
[18]	Liu Gang, Lao Song-Yang, Yuan Can, Hou Lv-Lin, Tan Dong-Feng. OACRR-PSO algorithm for anti-ship missile path planning. Acta Automatica Sinica, 2012, 38(9): 1528-1537 (刘钢, 老松杨, 袁灿, 侯绿林, 谭东风. 反舰导弹航路规划的OACRR-PSO算法. 自动化学报, 2012, 38(9): 1528-1537)
[19]	Li M S, Huang X Y, Liu H S, Liu B X, Wu Y, Xiong A H, Dong T W. Prediction of gas solubility in polymers by back propagation artificial neural network based on self-adaptive particle swarm optimization algorithm and chaos theory. Fluid Phase Equilibria, 2013, 356(25): 11-17
[20]	Li Yong, Wu Min, Cao Wei-Hua, Lai Xu-Zhi, Wang Chun-Sheng. PSO-BP control algorithm of granulation process based on evaluation and optimization of granularity distribution. Acta Automatica Sinica, 2012, 38(6): 1007-1016(李勇, 吴敏, 曹卫华, 赖旭芝, 王春生. 基于粒度分布评估与优化的制粒过程PSO-BP控制算法. 自动化学报, 2012, 38(6): 1007-1016)
[21]	Sheng Yang, Lai Xu-Zhi, Wu Min. Position control of a planar three-link underactuated mechanical system based on model reduction. Acta Automatica Sinica, 2014, 40(7): 1303-1310 (盛洋, 赖旭芝, 吴敏. 基于模型降阶的平面三连杆欠驱动机械系统位置控制. 自动化学报, 2014, 40(7): 1303-1310)
[22]	Jia D L, Zheng G X, Qu B Y, Khan M K. A hybrid particle swarm optimization algorithm for high-dimensional problems. Computers and Industrial Engineering, 2011, 61(4): 1117-1122
[23]	Sedki A, Ouazar D. Hybrid particle swarm optimization and differential evolution for optimal design of water distribution systems. Advanced Engineering Informatics, 2012, 26(3): 582-591
[24]	Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural Networks, 1989, 2(5): 359-366
[25]	Fang Kai-Tai, Ma Chang-Xing. Orthogonal and Uniform Experimental Design. Beijing: Science Press, 2001. 241-247 (方开泰, 马长兴. 正交与均匀试验设计. 北京: 科学出版社, 2001. 241-247)
[26]	Benazet F, Cartier M, Florent J, Godard C, Jung G, Lunel J, Mancy D, Pascal C, Renaut J, Tarridec P, Theilleux J, Tissier R, Dubost M, Ninet L. Nosiheptide, a sulfur-containing peptide antibiotic isolated from Streptomyces actuosus 40037. Experrentia, 1980, 36(4): 414-416
[27]	Koutinas A A, Wang R, Kookos I K, Webb C. Kinetic parameters of Aspergillus awamori in submerged cultivations on whole wheat flour under oxygen limiting conditions. Biochemical Engineering Journal, 2003, 16(1): 23-34
[28]	Khan N S, Mishra I M, Singh R P, Prasad B. Modeling the growth of Corynebacterium glutamicum under product inhibition in L-glutamic acid fermentation. Biochemical Engineering Journal, 2005, 25(2): 173-178
[29]	Sun J, Fang W, Palade V, Wu X J, Xu W B. Quantum-behaved particle swarm optimization with Gaussian distributed local attractor point. Applied Mathematics and Computation, 2011, 218(7): 3763-3775
[30]	Cvijović D, Klinowski J. Taboo Search: an approach to the multiple minima problem. Science, 1995, 267(5198): 664-666
[31]	Yao X, Liu Y, Lin G M. Evolutionary programming made faster. IEEE Transactions on Evolutionary Computation, 1999, 3(2): 82-102

施引文献

期刊类型引用(7)

1.	刘玉杰，崔凯凯，韩维，李樾. 基于IPSO的舰载机出动离场规划研究. 系统工程与电子技术. 2024(04): 1337-1345 . 百度学术
2.	邓剑波，马瑞，胡振文，陈可，杨海晶，杨旭. 基于改进粒子群算法的冷热电联供微网优化调度. 电力科学与技术学报. 2018(02): 35-42 . 百度学术
3.	毛琪波，余震虹，王相淳. 嵌入列维变异的混合动态粒子群算法. 计算机工程与应用. 2017(08): 132-136+239 . 百度学术
4.	夏禹，吴朋. 带基因交换和动态网格的多目标粒子群优化算法. 信息与控制. 2017(05): 593-600 . 百度学术
5.	毛琪波，余震虹，王相淳. 基于改进PSO算法的红外气体传感器温度补偿. 红外技术. 2016(06): 499-504 . 百度学术
6.	陈伟，贾立. 间歇过程PSO-SQP混合优化算法研究. 仪器仪表学报. 2016(02): 339-347 . 百度学术
7.	秦天牧，吕游，杨婷婷，刘吉臻. SCR烟气脱硝系统自适应混合动态模型. 仪器仪表学报. 2016(12): 2844-2850 . 百度学术