赖氨酸发酵过程关键变量多模型软测量建模及其在线监控系统设计  

Multi-model soft sensor modeling and online monitoring system design of key variables in lysine fermentation process

作　　者：朱熀秋[1] 王星宇 王博[1] ZHU Huangqiu;WANG Xingyu;WANG Bo(School of Electrical and Information Engineering,Jiangsu University,Zhenjiang,Jiangsu 212013,China)

机构地区：[1]江苏大学电气信息工程学院,江苏镇江212013

出　　处：《江苏大学学报（自然科学版）》2021年第6期694-701,共8页Journal of Jiangsu University：Natural Science Edition

基　　金：国家自然科学基金资助项目(41376175);江苏省自然科学基金资助项目(BK20140568,BK20151345);镇江市重点研发项目(SH2017002);江苏高校优势学科建设工程项目(PAPD)。

摘　　要：针对目前赖氨酸生产过程中发酵产物品质参量难以实时测量,现有软测量模型精度不高、鲁棒性差的问题,提出了一种基于ISCA-LSSVR的赖氨酸发酵过程多模型软测量方法.首先,利用改进的满意聚类算法(ISCA)将样本数据集划分为c个子集;其次,利用最小二乘支持向量回归机(LSSVR)对每个子集分别构建子模型;随后,利用粒子群优化算法和退火算法协同优化模型参数;然后,加权融合各子模型输出得到最终系统输出;最终,设计了由上位机数据处理模块和下位机数据采集模块共同组成的赖氨酸发酵过程关键变量的智能实时监控系统.试验仿真结果表明,相较于传统单一LSSVR预测模型,ISCA-LSSVR模型对产物、基质、菌体质量浓度的预测精度分别提高了5.01%、3.62%和6.78%,模型泛化能力得到了较大提高.To solve the problems that the quality variables of fermentation products in the lysine production process were difficult to measure in real time and the existing soft measurement models had low accuracy and poor robustness,a multi-model soft measurement method was proposed based on an improved satisfactory clustering algorithm and the least squares support vector regression(ISCA-LSSVR)for lysine fermentation process.The sample data set was divided into c subsets by ISCA,and LSSVR machine was used to construct sub-models for each subset separately.The particle swarm optimization algorithm and the annealing algorithm were used to collaboratively optimize the model parameters,and the output of each sub-model was weighted and fused to obtain the final system output.The intelligent real-time monitoring system for key variables in lysine fermentation process was designed with the upper computer data processing module and the lower computer data acquisition module.The experimental simulation results show that compared with the traditional single LSSVR prediction model,by the ISCA-LSSVR model,the mass concentration prediction accuracies of product,substrate and cell are respectively increased by 5.01%,3.62%and 6.78%,and the generalization ability is greatly improved.

关 键 词：赖氨酸 最小二乘支持向量机 聚类算法 软测量 多模型 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TQ922.3[自动化与计算机技术—控制科学与工程]