基于LS-SVM模糊推理的谷氨酸发酵过程流加控制  

Optimized control of glutamic acid fermentation process based on fuzzy inference of LS-SVM

作　　者：王鲜芳[1,2] 杜志勇[3] 潘丰[1] 

机构地区：[1]江南大学通信与控制工程学院自动化研究所,江苏无锡214122 [2]河南科技学院信息工程系,河南新乡453003 [3]河南机电高等专科学校,河南新乡453002

出　　处：《计算机应用研究》2009年第4期1386-1388,共3页Application Research of Computers

基　　金：国家“863”计划资助项目(2006AA020301-11)

摘　　要：针对发酵过程发酵阶段具有模糊性的特点,提出了采用最小二乘支持向量机(least square support vectormachines,LS-SVM)提取并简化模糊规则的推理优化控制方法。利用能够在线测量的物理量,如CO2生成速率和NH3的添加量等,在线判定发酵过程所处的阶段,然后依据加权平均的方法确定各个时刻葡萄糖的流加策略,完成了对分段连续流加补料的稳定控制。通过实际应用,证明了该方法的有效性。According to the characteristics of fuzzy during the stage of fermentation process, a fuzzy inference method based on least squares support vector machines is proposed, which can be distilled and simplified the fuzzy rule. Utilizing the on line measurement of physical quantities such as C02 production rate and the amount of NH3, and so on, to determine online the stage fermentation process, and then the glucose-plus strategy is obtained based on the method of weighted average every time, the stability control of the sub-fed-batch continuous is completed. The effectiveness of the method is proved by practical appli- cation.

关 键 词：模糊推理 最小二乘支持向量机 优化控制 发酵过程 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]