CIESC Journal ›› 2017, Vol. 68 ›› Issue (3): 976-983.DOI: 10.11949/j.issn.0438-1157.20161533

Previous Articles     Next Articles

Prediction of product concentration in glutamate fermentation process using partial least squares and least square support vector machine

ZHENG Rongjian1,2, PAN Feng1   

  1. 1 Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi 214122, Jiangsu, China;
    2 Faculty of Automation, Huaiyin Institute of Technology, Huai'an 223003, Jiangsu, China
  • Received:2016-10-31 Revised:2016-11-07 Online:2017-03-05 Published:2017-03-05
  • Contact: 10.11949/j.issn.0438-1157.20161533
  • Supported by:

    supported by the National Natural Science Foundation of China (61273131),the Graduate Innovation of Jiangsu Province (CXZZ12_0741) and the Fundamental Research Funds for Central Universities (JUDCF12034).

基于PLS-LSSVM的谷氨酸发酵产物浓度预测建模

郑蓉建1,2, 潘丰1   

  1. 1 江南大学轻工过程先进控制教育部重点实验室, 江苏 无锡 214122;
    2 淮阴工学院自动化学院, 江苏 淮安 223003
  • 通讯作者: 郑蓉建,rjmzheng@163.com
  • 基金资助:

    国家自然科学基金项目(61273131);江苏省普通高校研究生科研创新计划项目(CXZZ12_0741);中央高校基本科研业务费专项资金(JUDCF12034)。

Abstract:

Considered that key variables in glutamate fermentation process could not be measured inline, which would make it difficult to control and optimize the fermentation process, a model for glutamate concentration prediction in a 5 L fermentation tank was established on the basis of partial least squares (PLS) and least square support vector machine (LSSVM). PLS was applied first to extract features of input variables, to reduce number of variable dimensions, and to eliminate correlations such that model complexity was simplified and performance was improved. Coupled simulated annealing (CSA) arithmetic was later combined with grid search to determine model parameter values of LSSVM for improved prediction accuracy. Further model simplification was completed by deleting parameters with weak correlation to glutamate concentration. The simplified model was compared to kinetic model in order to select the best model of glutamate fermentation. Experimental results showed that the simplified LSSVM model equipped with CSA parameter optimization outperformed both PLS and kinetic models,which root mean square errors (RMSE) were 1.597, 8.49 and 2.934 respectively. The LSSVM prediction model had excellent performance with high accuracy, so it would be more suitable for online prediction of glutamate concentration and offer an effective guidance for control and optimization of the glutamate fermentation process.

Key words: glutamate, fermentation, prediction, partial least squares, least squares support vector machine, reaction kinetics, model simplification

摘要:

针对谷氨酸发酵过程关键生化参数难以在线检测给发酵优化控制带来困难问题,基于谷氨酸5 L发酵罐发酵过程,建立基于偏最小二乘(PLS)和最小二乘向量机(LSSVM)相结合的谷氨酸浓度预测模型;利用PLS对输入变量进行特征提取降低维数和消除相关性,以简化模型和提高模型精度。为确定谷氨酸发酵最佳预测模型,简化后的预测模型与发酵动力学模型进行比较;实验结果表明,简化后的耦合模拟退火(coupled simulated annealing,CSA)对参数进行优化的LSSVM模型具有最好预测性能,相对PLS预测模型和发酵动力学模型具有明显优势,均方根误差分别为1.597、8.49和2.934,可以为谷氨酸发酵过程操作及时调整及优化控制提供有效指导。

关键词: 谷氨酸, 发酵, 预测, 偏最小二乘, 最小二乘向量机, 反应动力学, 模型简化

CLC Number: