基于改进PSO-RBFNN的海洋蛋白酶发酵过程软测量

doi:10.11949/j.issn.0438-1157.20170598

化工学报 ›› 2018, Vol. 69 ›› Issue (3): 1221-1227.DOI: 10.11949/j.issn.0438-1157.20170598

基于改进PSO-RBFNN的海洋蛋白酶发酵过程软测量

朱湘临¹, 凌婧¹, 王博¹, 郝建华², 丁煜函¹

1 江苏大学电气信息工程学院, 江苏镇江 212013;
2 中国水产科学研究院黄海水产研究所, 海洋酶与酶工程开放实验室, 山东青岛 266071

收稿日期:2017-06-16 修回日期:2017-11-03 出版日期:2018-03-05 发布日期:2018-03-05
通讯作者: 王博
基金资助:
国家自然科学基金面上项目（41376175）；江苏省自然科学基金项目（BK20140568，BK20151345）；江苏省高校自然科学研究面上项目（14KJB510007）；江苏高校优势学科建设工程资助项目（PAPD）。

Soft-sensing modeling of marine protease fermentation process based on improved PSO-RBFNN

ZHU Xianglin¹, LING Jing¹, WANG Bo¹, HAO Jianhua², DING Yuhan¹

1 College of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, Jiangsu, China;
2 Open Laboratory of Marine Enzyme & Enzyme Engineering, Yellow Sea Fisheries Research Institute, Qingdao 266071, Shandong, China

Received:2017-06-16 Revised:2017-11-03 Online:2018-03-05 Published:2018-03-05
Supported by:
supported by the National Natural Science Foundation of China(41376175) and the Natural Science Foundation of Jiangsu Province(BK20140568, BK20151345).

摘要/Abstract

摘要：

针对海洋蛋白酶（marine protease，MP）发酵过程中某些关键参量难以在线检测，离线测量存在大滞后、易染菌的问题，提出了一种基于改进的粒子群-径向基神经网络（PSO-RBFNN）的MP发酵过程软测量建模方法。首先采用指数下降惯性权重（exponential decreasing inertia weight，EDIW）策略对粒子群算法进行改进，克服了固定惯性权重和自适应惯性权重的粒子群算法易于陷入局部极小，进化后期收敛速度慢以及全局搜索能力弱的缺点；然后，采用改进后的粒子群算法对径向基神经网络连接权值进行在线优化，确定RBFNN拓扑结构；最后，根据MP发酵过程的输入/输出向量构建RBFNN软测量模型。实验仿真结果表明，EDIW策略改进的PSO-RBFNN软测量模型训练时间缩短了40%左右，模型预测精度提高了3%以上。

关键词: 海洋蛋白酶, 改进粒子群算法, 径向基神经网络, 软测量模型

Abstract:

Some key parameters in the fermentation process of marine protease (MP) are difficult to be detected online. There is the existence of large time-delay and easily stained bacteria in off-line measurement. A soft sensor modeling method based on the improved PSO-RBFNN in the MP fermentation process was proposed. Firstly, exponential decreasing inertia weight (EDIW) strategy was used to improve PSO algorithm, and overcome the disadvantages that PSO with fixed inertia weight and adaptive inertia weight is easy to fall into the local minimum, the convergence rate is slow in late evolution and the global search ability is weak. Then the improved PSO algorithm was used to optimize the connection weight of RBFNN, and the RBFNN topology was successively determined. Finally, the RBFNN soft sensor model was constructed according to the input/output vector of MP fermentation process. The simulation results showed that the training time of the EDIW-PSO-RBFNN model was reduced by at least (about) 40%, and the prediction accuracy of model was improved by more than 3%.

Key words: marine protease, improved PSO algorithm, RBF neural network, soft sensing model

中图分类号:

TP301

朱湘临, 凌婧, 王博, 郝建华, 丁煜函. 基于改进PSO-RBFNN的海洋蛋白酶发酵过程软测量[J]. 化工学报, 2018, 69(3): 1221-1227.

ZHU Xianglin, LING Jing, WANG Bo, HAO Jianhua, DING Yuhan. Soft-sensing modeling of marine protease fermentation process based on improved PSO-RBFNN[J]. CIESC Journal, 2018, 69(3): 1221-1227.

参考文献 30

[1]	CUI H, YANG M, WANG L, et al. Identification of a new marine bacterial strain SD8 and optimization of its culture conditions for producing alkaline protease[J]. Plos One, 2015, 10(12):1-13.
[2]	BOSE A, CHAWDHARY V, KEHARIA H, et al. Production and characterization of a solvent-tolerant protease from a novel marine isolate bacillus tequilensis P15[J]. Annals of Microbiology, 2014, 64(1):343-354.
[3]	LEE H S, KWON K K, KANG S G, et al. Approaches for novel enzyme discovery from marine environments[J]. Current Opinion in Biotechnology, 2010, 21(3):353-357.
[4]	孙谧, 洪义国, 李勃生, 等. 海洋微生物低温酶特性及其在工业中的潜在用途[J]. 渔业科学进展, 2002, 23(3):44-49. SUN M, HONG Y G, LI B S, et al. Characteristic of low-temperature enzyme from marine bacteria and its potential use on the industry[J]. Marine Fisheries Research, 2002, 23(3):44-49.
[5]	朱美虹. 海洋蛋白酶在医药领域的研究进展[J]. 山东化工, 2016, 45(20):60-61. ZHU M H. Research progress on the medical field of marine proteinases[J]. Shandong Chemical Industry, 2016, 45(20):60-61.
[6]	周世水, 丁金国, 姚汝华. 海洋微生物药物的开发和应用[J]. 工业微生物, 2002, 32(2):48-51. ZHOU S S, DING J G, YAO R H. Development and application of marine microbial drugs[J]. Industrial Microbiology, 2002, 32(2):48-51.
[7]	郭琪, 王静雪. 海洋微生物酶的研究概况[J]. 水产科学, 2005, 24(12):41-44. GUO Q, WANG J X. A review:enzymes from marine microorganisms[J]. Fisheries Science, 2005, 24(12):41-44.
[8]	郇惠杰, 钟泓波, 雷芬芬, 等. 产蛋白酶海洋细菌的筛选、鉴定及发酵培养基的研究[J]. 食品工业科技, 2013, 34(24):181-185. HUAN H J, ZHONG H B, LEI F F, et al. Study on isolation and identification of protease-producing marine bacteria and optimization of fermentation medium[J]. Science and Technology of Food Industry, 2013, 34(24):181-185.
[9]	张祁, 宁喜斌. 上海临港海域产蛋白酶海洋细菌的筛选及鉴定[J]. 食品工业科技, 2013, 34(3):192-197. ZHANG Q, NING X B. Isolation and identification of protease producing marine bacteria from Shanghai Lingang sea area[J]. Science and Technology of Food Industry, 2013, 34(3):192-197.
[10]	MUKHERJEE A K, RAI S K. A statistical approach for the enhanced production of alkaline protease showing fibrinolytic activity from a newly isolated gram-negative Bacillus sp. strain AS-S20-I[J]. New Biotechnology, 2011, 28(2):182-189.
[11]	RAJKUMAR R, KOTHILMOZHIAN J, RAMASAMY R. Production and characterization of a novel protease from Bacillus sp. RRM1 under solid state fermentation[J]. Journal of Microbiology & Biotechnology, 2011, 21(21):627-636.
[12]	张丹, 闵伟红, 刘景圣, 等. 响应面法优化蛋白酶菌株发酵条件[J]. 食品科学, 2011, 32(13):248-253. ZHANG D, MIN W H, LIU J S, et al. Response surface optimization of fermentation conditions for protease production by Pichia kudriavzevii Yeast[J]. Food Science, 2011, 32(13):248-253.
[13]	朱湘临, 刘叶飞, 孙谧, 等. 海洋微生物酶反应器智能控制系统的研制[J]. 农业工程学报, 2010, 26(9):185-191. ZHU X L, LIU Y F, SUN M, et al. Development of intelligent control system for bioreactor of marine microbial enzymes[J]. Transactions of the CSAE, 2010, 26(9):185-191.
[14]	房耀维, 余勃, 刘姝, 等. 有机溶剂稳定性蛋白酶发酵动力学研究[J]. 食品科学, 2012, 33(23):240-243. FANG Y W, YU B, LIU S, et al. Fermentation kinetics of organic solvent-stable protease production[J]. Food Science, 2012, 33(23):240-243.
[15]	黄永红, 孙丽娜, 孙玉坤, 等. 海洋蛋白酶发酵过程生物参数的软测量建模[J]. 信息与控制, 2013, 42(4):506-510. HUANG Y H, SUN L N, SUN Y K, et al. Soft sensor modeling based on biological variables of marine protease fermentation process[J]. Information and Control, 2013, 42(4):506-510.
[16]	朱湘临, 杨建宁, 孙谧, 等. 基于非线性核脊回归算法的海洋微生物发酵参数软测量[J]. 化工自动化及仪表, 2011, 38(2):171-175. ZHU X L, YANG J N, SUN M, et al. Soft-sensing of microorganism ferment parameters based on non-linear kernel ridge regression algorithm[J]. Chemical Automation and Instrumentation, 2011, 38(2):171-175.
[17]	黄永红, 宋心雷. 基于贝叶斯LS-SVM的海洋生物酶发酵过程软测量建模[J]. 仪表技术与传感器, 2014, (8):92-94. HUANG Y H, SONG X L. Soft sensor modeling of LS-SVM based on Bayesian criteria for marine protease fermentation process[J]. Instrument Technique and Sensor, 2014, (8):92-94.
[18]	郝建华, 盛军, 孙谧. 人工神经网络在海洋微生物脂肪酶发酵中的应用[J]. 食品科技, 2014, 39(11):27-31. HAO J H, SHENG J, SUN M. Application of arti?cial neural network in marine microbial lipase fermentation[J]. Food Science and Technology, 2014, 39(11):27-31.
[19]	张玲华, 姚绍芹, 解伟超. 基于自适应粒子群优化径向基函数神经网络的语音转换[J]. 数据采集与处理, 2015, 30(2):336-343. ZHANG L H, YAO S Q, XIE W C. Voice conversion based on adaptive particle swarm optimization radial basis function neural network[J]. Journal of Data Acquisition and Processing, 2015, 30(2):336-343.
[20]	杜鑫. 径向基函数神经网络在水动力参数智能模型中的应用[J]. 舰船科学技术, 2017, 39(1A):7-9. DU X. Application of radical basis function neural network in intelligent model of hydrodynamic parameters[J]. Ship Science and Technology, 2017, 39(1A):7-9.
[21]	张煜东, 朱庆, 王水花, 等. 一种径向基函数神经网络的参数求解方法[J]. 计算机测量与控制, 2010, 18(12):2812-2814. ZHANG Y D, ZHU Q, WANG S H, et al. A method for parameter estimation of RBF neural networks[J]. Computer Measurement & Control, 2010, 18(12):2812-2814.
[22]	SHI Y, EBERHART R. Modified particle swarm optimizer[C]//IEEE International Conference on Evolutionary Computation Proceedings, 1998. IEEE World Congress on Computational Intelligence. IEEE Xplore, 1998, 6:69-73.
[23]	LEI K Y, QIU Y, HE Y. A new adaptive well-chosen inertia weight strategy to automatically harmonize global and local search ability in particle swarm optimization[C]//International Symposium on Systems and Control in Aerospace and Astronautics. IEEE, 2006:977-980.
[24]	NICKABADI A, EBADZADEH M M, SAFABAKHSH R. A novel particle swarm optimization algorithm with adaptive inertia weight[J]. Applied Soft Computing Journal, 2011, 11(4):3658-3670.
[25]	黄永红, 孙丽娜, 孙玉坤, 等. 基于动态数据交换技术的海洋蛋白酶发酵过程GD-FNN软测量[J]. 农业工程学报, 2013, 29(19):268-276. HUANG Y H, SUN L N, SUN Y K, et al. Soft sensor of generalized dynamic fuzzy neural network for marine protease fermentation process based on dynamic data exchange[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2013, 29(19):268-276.
[26]	李哲, 田学民. 基于辅助变量KNN分析的软测量建模方法[J]. 化工学报, 2008, 59(4):941-946. LI Z, TIAN X M. Soft sensor modeling method based on secondary variables KNN analysis[J]. Journal of Chemical Industry and Engineering(China), 2008, 59(4):941-946.
[27]	李勇, 邵诚. 一种新的灰关联分析算法在软测量中的应用[J]. 自动化学报, 2006, 32(2):311-317. LI Y, SHAO C. Application of a novel grey relation analysis algorithm to soft sensor[J]. Acta Automatica Sinica, 2006, 32(2):311-317.
[28]	邓聚龙. 灰色系统基本方法[M]. 武汉:华中科技大学出版社, 2005. DENG J L. The Primary Methods of Grey System Theory[M]. Wuhan:Huazhong University of Science and Technology Press, 2005.
[29]	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 L, SUN Y K, JI X F, et al. Soft sensor of lysine fermentation based on tPSO-BPNN[J]. Chinese Journal of Scientific Instrument, 2010, 31(10):2317-2321.
[30]	徐文星, 何骞, 戴波, 等. 自适应混合粒子群约束优化算法及其在软测量模型参数估计中的应用[J]. 化工学报, 2015, 66(1):222-227. XU W X, HE Q, DAI B, et al. Adaptive hybrid particle swarm optimizer for constrained optimization problems and its application in parameter estimation of soft sensing[J].CIESC Journal, 2015, 66(1):222-227.

基于改进PSO-RBFNN的海洋蛋白酶发酵过程软测量

Soft-sensing modeling of marine protease fermentation process based on improved PSO-RBFNN

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献 30

相关文章 6

编辑推荐

Metrics

本文评价

[1]	耿志强, 陈杰, 韩永明. 基于模糊RBF神经网络的乙烯装置生产能力预测[J]. 化工学报, 2016, 67(3): 812-819.
[2]	王钧炎;黄德先. 基于混合差分进化算法的软测量时延参数估计[J]. CIESC Journal, 2008, 59(8): 2058-2064.
[3]	金宁德;赵鑫;郑华;陈景霞. 油井伞集流油气水三相流流动参数的软测量方法 [J]. CIESC Journal, 2006, 57(12): 2847-2853.
[4]	鄂加强, 王耀南, 梅炽. 铜精炼过程铜液温度软测量模型及应用 [J]. 化工学报, 2006, 57(1): 203-209.
[5]	陈彦泽, 丁信伟, 喻建良. 重力热管振荡传热特性RBF神经网络动态建模 [J]. 化工学报, 2005, 56(5): 890-893.
[6]	孔薇;杨杰. 基于径向基神经网络的聚丙烯熔融指数预报 [J]. CIESC Journal, 2003, 54(8): 1160-1163.