[1]赵 超,李 俊,戴坤成,等.基于自适应加权最小二乘支持向量机的青霉素发酵过程软测量建模[J].南京理工大学学报(自然科学版),2017,41(01):100.[doi:10.14177/j.cnki.32-1397n.2017.41.01.014]
 Zhao Chao,Li Jun,Dai Kuncheng,et al.Soft sensor modeling for penicillin fermentation process based onadaptive weighted least squares support vector machine[J].Journal of Nanjing University of Science and Technology,2017,41(01):100.[doi:10.14177/j.cnki.32-1397n.2017.41.01.014]
点击复制

基于自适应加权最小二乘支持向量机的青霉素发酵过程软测量建模()
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
41卷
期数:
2017年01期
页码:
100
栏目:
出版日期:
2017-02-28

文章信息/Info

Title:
Soft sensor modeling for penicillin fermentation process based onadaptive weighted least squares support vector machine
文章编号:
1005-9830(2017)01-0100-08
作者:
赵 超李 俊戴坤成王贵评
福州大学 石油化工学院,福建 福州 350108
Author(s):
Zhao ChaoLi JunDai KunchengWang Guiping
School of Chemical Engineering,Fuzhou University,Fuzhou 350108,China
关键词:
加权最小二乘支持向量机 青霉素发酵过程 正态分布 混沌差分进化—模拟退火优化 软测量建模
Keywords:
weighted least squares support vector machines penicillin fermentation process normal distribution function chaos differential evolution simulated annealing soft sensor model
分类号:
TP181
DOI:
10.14177/j.cnki.32-1397n.2017.41.01.014
摘要:
针对生化过程软测量建模过程中样本数据可能包含的测量误差对模型性能的影响,提出一种自适应加权最小二乘支持向量机(Adaptive weighted least squares support vector machine,AWLS-SVM)回归的软测量建模方法。该方法基于最小二乘支持向量机模型,根据样本拟合误差,并结合改进的正态分布赋权规则,自适应地为每个建模样本分配不同的权值,以降低随机误差对模型性能的影响; 同时采用混沌差分进化—模拟退火(Chaos differential evolution simulated annealing,CDE-SA)算法对模型参数进行优化选择,以提高模型的泛化能力。仿真实验表明,AWLS-SVM模型的预测精度及鲁棒性能优于最小二乘支持向量机(Least squares support vector machine,LS-SVM)和加权最小二乘支持向量机(Weighted least squares support vector machine,WLS-SVM)。利用Pensim仿真平台的数据,将AWLS-SVM方法用于青霉素发酵过程软测量建模,获得了较好的效果。
Abstract:
The presence of outliers in sample data can corrupt the model’s performance,giving undesirable results.A novel adaptive weighted least squares support vector machine(AWLS-SVM)regression method is presented for modeling of penicillin fermentation process.In AWLS-SVM,least square support vector machine regression is employed for the sample data to develop model and obtain the sample datum fitting error.According to the fitting error,the adaptive sample weights are obtained via the proposed improved normal distribution weighted scheme.The hybrid chaos differential evolution simulated annealing(CDE-SA)algorithm is proposed to obtain the optimal parameters of the model.The simulation experiment results show that the outliers influencing on the models performance is eliminated in AWLS-SVM,and that the prediction performance is better than those of least squares support vector machine(LS-SVM)and weighted least squares support vector machine(WLS-SVM)method.The AWLS-SVM is applied to develop the soft sensor model for penicillin fermentation process,and the satisfactory result is obtained.

参考文献/References:

[1] Monroy I,Villez K,Graells M,et al.Fault diagnosis of a benchmark fermentation process:a comparative study of feature extraction and classification techniques[J].Bioprocess and Biosystems Engineering,2012,35(5):689-704.
[2]Sivapathasekaran C,Sen R.Performance evaluation of an ANN-GA aided experimental modeling and optimization procedure for enhanced synthesis of marine biosurfactant in a stirred tank reactor[J].Journal of Chemical Technology and Biotechnology,2013,88(5):794-799.
[3]Nasr N,Hafez H,Naggar M,et al.Application of artificial neural networks for modeling of biohydrogen production[J].International Journal of Hydrogen Energy,2013,38(8):3189-3195.
[4]于霜,刘国海,梅从立,等.生物发酵过程中VIP优化神经网络逆系统的软测量方法[J].南京理工大学学报,2015,34(4):447-451.Yu Shuang,Liu Guohai,Mei Congli,et al.VIP optimal neural network inverse system soft sensing method in bio-fermentation process[J].Journal of Nanjing University of Science and Technology,2015,34(4):447-451.
[5]Peng Jiansheng,Meng Fanmei,Ai Yuncan.Time-dependent fermentation control strategies for enhancing synthesis of marine bacteriocin 1701 using artificial neural network and genetic algorithm[J].Bioresource Technology,2013,138(6):345-352.
[6]Vapnik V N.The nature of statistical learning theory[M].New York:Springer,1999.
[7]Cortes C,Vapnik V N.Support-vector networks[J].Machine Learning,1995,20(3):273-297.
[8]Ouyang Haibin,Li Steven,Zhang Ping,et al.Model penicillin fermentation by least squares support vector machine with tuning based on amended harmony search[J].International Journal of Biomathematics,2015(3):175-204.
[9]王博,孙玉坤,嵇小辅,等.基于PSO-SVM逆的赖氨酸发酵过程软测量[J].化工学报,2012,63(9):3000-3007.
Wang Bo,Sun Yukun,Ji Xiaofu,et al.Soft-sensor modeling for lysine fermentation processes based on PSO-SVM inversion[J].CIESC Journal,2012,63(9):3000-3007.
[10]Liu Guohai,Zhou Dawei,Xu Haixia,et al.Model optimization of SVM for a fermentation soft sensor[J].Expert systems with Applications,2010,37(4):2708-2713.
[11]刘国海,周大为,徐海霞,等.基于SVM的微生物发酵过程软测量建模研究[J].仪器仪表学报,2009,30(6):1228-1232.
Liu Guohai,Zhou Dawei,Xu Haixia,et al.Soft sensor modeling using SVM in fermentation process[J].Chinese Journal of Scientific Instrument,2009,30(6):1228-1232.
[12]顾燕萍,赵文杰,吴占松.最小二乘支持向量机的算法研究[J].清华大学学报(自然科学版),2010,50(7):1063-1066.
Gu Yanping,Zhao Wenjie,Wu Zhansong.Least squares support vector machine algorithm[J].J Tsinghua Univ(Sci & Tech),2010,50(7):1063-1066.
[13]刘毅,王海清.基于LS-SVM和Pensim仿真平台的青霉素发酵过程建模[J].化学反应工程与工艺,2006,22(3):252-258.
Liu Yi,Wang Haiqing.Modelling of the penicillin fermentation process via LS-SVM based on Pensim simulator[J].Chemical Reaction Engineering and Technology,2006,22(3):252-258.
[14]熊伟丽,姚乐,徐保国.混沌最小二乘支持向量机及其在发酵过程建模中的应用[J].化工学报,2013,64(12):4585-4591.
Xiong Weili,Yao Le,Xu Baoguo.Chaos least squares support vector machine and its application on fermentation process modeling[J].CIESC Journal,2013,64(12):4585-4591.
[15]Suykens J A K,De Brabanter J,Lukas L,et al.Weighted least squares support vector machines:robustness and sparse approximation[J].Neurocom-puting,2002,48(1-4):85-105.
[16]熊伟丽,王肖,陈敏芳,等.基于加权LS-SVM的青霉素发酵过程建模[J].化工学报,2012,63(9):2913-2919.
Xiong Weili,Wang Xiao,Chen Minfang,et al.Modeling for penicillin fermentation process based on weighted LS-SVM[J].CIESC Journal,2012,63(9):2913-2919.
[17]樊晓雪.最小二乘支持向量机的参数选择[D].保定:河北大学自动化学院,2012.
[18]Blum,Christian.Swarm intelligence:Introduction and applications[M].London:Springer,2010.
[19]Birol G,Undey C,Cinar A.A modular simulation package for fed-batch fermentation:penicillin production[J].Computers and Chemical Engineering,2002,26(11):1553-1565.
[20]Undey C,Tatara E,Cinar A.Intelligent real-time performance monitoring and quality prediction for batch/fed-batch cultivations[J].Journal of Biotechnology,2004,108(1):61-77.

备注/Memo

备注/Memo:
收稿日期:2016-03-24 修回日期:2016-06-08
基金项目:国家自然科学基金(60804027; 61374133); 福州大学科研基金(FZU-022335; 600338; 600567); 高校博士点专项科研基金(20133314120004)
作者简介:赵超(1976-),男,博士,副教授,主要研究方向:过程优化、最优控制,E-mail:seasky76@163.com。
引文格式:赵超,李俊,戴坤成,等.基于自适应加权最小二乘支持向量机的青霉素发酵过程软测量建模[J].南京理工大学学报,2017,41(1):100-107.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2017-02-28