[1]孙丽娜,黄永红,王应海.基于OPC技术和果蝇优化广义回归神经网络的海洋蛋白酶发酵过程软测量[J].南京理工大学学报(自然科学版),2020,44(04):431-440.[doi:10.14177/j.cnki.32-1397n.2020.44.04.007]
 Sun Lina,Huang Yonghong,Wang Yinghai.Soft sensor for marine protease fermentation process based on OPCtechnology and fruit fly optimization general regression neural network[J].Journal of Nanjing University of Science and Technology,2020,44(04):431-440.[doi:10.14177/j.cnki.32-1397n.2020.44.04.007]
点击复制

基于OPC技术和果蝇优化广义回归神经网络的海洋蛋白酶发酵过程软测量()
分享到:

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

卷:
44卷
期数:
2020年04期
页码:
431-440
栏目:
出版日期:
2020-08-30

文章信息/Info

Title:
Soft sensor for marine protease fermentation process based on OPCtechnology and fruit fly optimization general regression neural network
文章编号:
1005-9830(2020)04-0431-10
作者:
孙丽娜1黄永红2王应海1
1.苏州工业园区职业技术学院 机电工程系,江苏 苏州 215123; 2.江苏大学 电气信息工程学院,江苏 镇江 212013
Author(s):
Sun Lina1Huang Yonghong2Wang Yinghai1
1.Mechatronics Engineering Department,Suzhou Industrial Park Institute of Vocational Technology,Suzhou 215123,China; 2.School of Electrical and Information Engineering,Jiangsu University,Zhenjiang 212013,China
关键词:
海洋蛋白酶 发酵 生物参数 果蝇优化算法 广义回归神经网络 面向过程控制的对象链接与嵌入 软测量
Keywords:
marine protease enzyme fermentation biological variables fruit fly optimization algorithm generalized regression neural network object linking and embeded for process control soft sensor
分类号:
TP273
DOI:
10.14177/j.cnki.32-1397n.2020.44.04.007
摘要:
鉴于海洋生物酶发酵过程中关键生物参数难以实时在线测量的问题,提出了一种基于果蝇优化算法(Fruit fly optimization algorithm,FOA)的广义回归神经网络(Generalized regression neural network,GRNN)与面向过程控制的对象链接与嵌入技术相结合的软测量方法。GRNN的非线性映射能力强、学习速度快,但GRNN的预测性能受平滑因子的影响比较大,因此利用FOA对GRNN的平滑因子进行寻优,以提高模型的泛化能力,采用OPC技术可以实现MATLAB和组态王之间的数据通讯,将预测的关键生物参数值传送给组态王进行实时显示与存储。通过采集海洋蛋白酶发酵过程的实验数据,建立基于FOA优化GRNN的海洋蛋白酶发酵过程关键生物参数(菌体质量浓度、基质质量浓度、酶活)的软测量模型,并与GRNN、BP神经网络、支持向量机(Support vector machine,SVM)进行对比。结果表明,基于FOA优化GRNN的软测量模型对训练样本的拟合能力和对测试样本的预测能力都远远超过GRNN、BP神经网络和SVM,通过OPC技术将MATLAB和组态王进行数据连接,实现了生物参数的实时在线测量,且系统运行的稳定性较好。
Abstract:
Considering the problem that the crucial biological variables in the marine biological enzyme fermentation process are difficult to measure on-line in real time,a soft sensor method based on the fruit fly optimization algorithm(FOA)of generalized regression neural network(GRNN)is proposed which is combined with the OPC technology.GRNN has strong nonlinear mapping ability and fast learning speed,but the prediction performance of GRNN is greatly affected by smoothing factors. Therefore,FOA is used to optimize the smoothing factors of GRNN to improve the generalization ability of the model.The data communication between MATLAB and Kingview can be realized by object linking and embeded for process control(OPC)technology,the predicted key biological parameters are transmitted to Kingview for real-time display and storage.By collecting the experimental data of marine protease fermentation process,a soft sensing model of the key biological parameters(cell concentration,substrate concentration,enzyme activity)in the marine protease fermentation process is established which is based on the optimization of GRNN by FOA,and compared with GRNN,BP neural network and Support Vector Machine(SVM).The results show that the fitting ability to the training samples and the prediction ability to the test samples of the soft sensor model based on the FOA optimized GRNN are far better than GRNN,BP neural network and SVM. Through OPC technology,MATLAB and Kingview are connected to realize the real-time online measurement of biological parameters,and the system has good stability.

参考文献/References:

[1] 郝建华,袁翠,王跃军,等. 低温碱性蛋白酶QDAPr的生物信息学分析及同源模建[J]. 生物信息学,2006,4(2):62-64.
Hao Jianhua,Yuan Cui,Wang Yuejun,etal. Bioinformatics analysis and homology modeling of low-temperature alkaline protease QDAPr[J]. China Journal of Bioinformatics,2006,4(2):62-64.
[2]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.
Zhao Chao,Li Jun,Dai Kuncheng,et al. Soft sensor modeling for penicillin fermentation process based on adaptive weighted least squares support vector machine[J]. Journal of Nanjing University of Science and Technology,20017,41(1):100-107.
[3]Gupta R,Beg Q K,Lorenz P. Bacterial alkaline proteases:Molecular approaches and industrial applications[J]. Applied Microbiology and Biotechnology,2002,59(1):15-32
[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,2015,39(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,2015,39(4):447-451.
[5]朱湘临,岳海东,孙谧. 基于Bayesian的海洋脂肪酶发酵过程软测量建模[J]. 测控技术,2015,34(11)127-129.
Zhu Xianglin,Yue Haidong,Sun Mi. Soft sensor modeling of marine lipase fermentation process based on Bayesian[J]. Measurement and Control Technology,2015,34(11)127-129.
[6]朱湘临,何裕俊,孙谧,等. 基于SUKF的海洋溶菌酶发酵菌体质量浓度软测量[J]. 江苏大学(自然科学版),2013,34(6):699-703.
Zhu Xianglin,He Yujun,Sun Mi,et al. Soft sensing algorithm of marine lysozyme mycelium fermentation bacteria concentration based on SUKF[J]. Journal of Jiangsu Uiversity(Natural Science Edition),2013,34(6):699-703.
[7]黄丽,孙玉坤,嵇小辅,等. 基于tPSO-BPNN的赖氨酸发酵软测量[J]. 仪器仪表学报,2010,31(10):2317-2321.
Huang Li,Sun Yukun,Ji Xiaofu,et al. Soft sensor of lysine fermentation based on tPSO-BPNN[J]. Chinese Journal of Scientific Instrument,2010,31(10):2317-2321.
[8]王贵成,张敏,汪勇,等. GA-BP网络在谷氨酸菌体质量浓度软测量中的应用[J]. 华东理工大学学报,2007,33(3):410-413.
Wang Guicheng,Zhang Min,Wang Yong,et al. Application of soft-sensing using GA-BPnetwok to germ concentration of glutamic acid[J]. Journal of East China University of Science and Technology,2007,33(3):410-413.
[9]何琴,高建华,刘伟. 广义回归神经网络在烤烟内在质量分析中的应用[J]. 安徽农业大学学报,2005,32(3):406-410.
He Qin,Gao Jianhua,Liu Wei. Application of generalized regression neural network into internal quality evaluation of flue-cured tobaccos[J]. Journal of Anhui Agricultural University,2005,32(3):406-410.
[10]周敏,李世玲. 广义回归神经网络在非线性系统建模中的应用[J]. 计算机测量与控制,2007,15(9):1189-1191.Zhou Min,Li Shiling. Application of GRNN and uniform design to nonlinear system modeling[J]. Computer Measurement and Control,2007,15(9):1189-1191.
[11]兰海涛,李谦,韩春雨. 基于广义回归神经网络的边坡稳定性评价[J]. 岩土力学,2009,30(11):3460-3463.
Lan Haitao,Li Qian,Han Chunyu. Slope stability evaluation based on generalized regression neural network[J]. Rock and Soil Mechanics,2009,30(11):3460-3463.
[12]林喆,兰生,张宇航. 基于广义回归神经网络的油纸绝缘变压器的寿命预测[J]. 高压电器,2015,51(2):125-130.
Lin Zhe,Lan Sheng,Zhang Yuhang. Life prediction of oil paper insulation of transformer based on GRNN neural network[J]. High Voltage Apparatus,2015,51(2):125-130.
[13]张荣标,冯俊,谢志超. 基于广义回归神经网络的COD在线检测方法研究[J]. 仪器仪表学报,2008,29(11):2357-2361.Zhang Rongbiao,Feng Jun,Xie Zhiehao. Study on COD on-line detection method based on general regression neural network[J]. Chinese Journal of Scientific Instrument,2008,29(11):2357-2361.
[14]曹岩枫,徐诚. 基于果蝇算法优化广义回归神经网络的机枪枪管初速衰减建模与预测[J]. 兵工学报,2017,38(1):1-8.
Cao Yanfeng,Xu Cheng. Modeling and prediction of muzzle velocity degradation of machine gun based on FOAGRNN[J]. Acta Armamentarii,2017,38(1):1-8.
[15]聂娜娜,王英博,王铭泽,等. FOA优化GRNN网络的尾矿库安全预测[J]. 中国安全生产科学技术,2014,10(8):39-44.
Nie Nana,Wang Yingbo,Wang Mingze,et al. Safety prediction of mine tailing reservoir based on FOA-GRNN algorithm[J]. Journal of Safety Science and Technology,2014,10(8):39-44.
[16]薛毓强,李宗辉. 基于因果时序网络的FOA-GRNN电网故障诊断方法[J]. 电力系统及其自动化学报,2014,26(11):72-77.
Xue Yuqiang,Li Zonghui. Study on FOA-GRNN fault diagnosis method of power grid based on causal sequential network[J]. Proceedings of the CSU-EPSA,2014,26(11):72-77.
[17]徐联贵,梁岚珍,史颖. 基于OPC 技术的MATLAB与组态王通信模块设计[J]. 工业控制计算机,2007,20(3):26-27.
Xu Liangui,Liang Fengzhen,Shi Ying. Design of OPC based communication between MATLAB and KingView[J]. Industrial Control Computer,2007,20(3):26-27.
[18]张梓琪,黄凌云,李才对,等. 基于组态王与Matlab的液位控制仿真平台构建[J]. 实验室研究与探索,2013,32(9):81-85.
Zhang Ziqi,Huang Lingyun,Li Caidui,et al. Construction of level control system simulation platform based on KINGVIEW and Matlab[J]. Research and Exploration in Laboratory,2013,32(9):81-85.
[19]Pan W C.A new fruit fly optimization algorithm:Taking the financial distress model as an example[J]. Knowledge-Based Systems,2012,26:69-74.
[20]孙丽娜,邓玲黎,刘俊,等. 基于MIV-Elman神经网络的海洋生物酶发酵软测量[J]. 传感器与微系统,2018,37(12):128-130,135.
Sun Lina,Deng Lingli,Liu Jun,et al. Soft measurement of marine biological enzyme fermentationbased on MIV-Elman neural network[J]. Transducer and Microsystem Technologies,2018,37(12):128-130,135.
[21]袁娜,杨鹏,刘作军. 利用平均影响值和概率神经网络的步态识别[J]. 哈尔滨工程大学学报,2015,36(2):181-185.
Yuan Na,Yang Peng,Liu Zuojun. Gait recognition by the mean impact value and probability neural network[J]. Journal of Harbin Engineering University,2015,36(2):181-185.
[22]王玉万,郭正,李季伦. 电导率仪在测定发酵液体积中的应用[J]. 微生物学通报,1993,20(3):185-186.
Wang Yuwan,Guo Zheng,Li Jilun. Application of conductivity meter in the measurement of fermentation liquid volume[J]. Microbiology China,1993,20(30):185-186.

相似文献/References:

[1]孙东平.灵芝液体发酵产纤维素酶的提取及性质分析[J].南京理工大学学报(自然科学版),2006,(03):356.
 SUN Dong-ping.Extract and Analysis of Cellulase Produced by Ganoderma Lucidum’s Liquid Fermentation[J].Journal of Nanjing University of Science and Technology,2006,(04):356.
[2]彭新华,陆才正,杨瑛.快速堆肥的可控技术及温控模型研究[J].南京理工大学学报(自然科学版),1992,(02):80.
[3]王启开,孙崇凯.微生物活细胞固定化技术在发酵废水厌氧处理中的应用[J].南京理工大学学报(自然科学版),1987,(02):154.
[4]孙东平,张继东,周伶俐,等.木醋杆菌1.1812发酵产细菌纤维素的研究[J].南京理工大学学报(自然科学版),2005,(05):101.
 SUN Dong-ping~,ZHANG Ji-dong~,ZHOU Ling-li~,et al.Production of Bacterial Cellulose with Acetobacter Xylinum1.1812 Fermentation[J].Journal of Nanjing University of Science and Technology,2005,(04):101.

备注/Memo

备注/Memo:
收稿日期:2019-11-09 修回日期:2020-04-22
基金项目:国家“863”计划重点科技项目(2011AA09070301); 江苏省自然科学基金(BK20151345)
作者简介:孙丽娜(1986-),女,讲师,主要研究方向:复杂过程的智能检测与控制,E-mail:sunln525@163.com; 通讯作者:黄永红(1970-),女,博士,教授,主要研究方向:微生物反应过程的智能检测与优化控制。
引文格式:孙丽娜,黄永红,王应海. 基于OPC技术和果蝇优化广义回归神经网络的海洋蛋白酶发酵过程软测量[J]. 南京理工大学学报,2020,44(4):431-440.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2020-08-30