抗生素发酵过程溶氧浓度模糊PID-神经网络控制器响应特性分析

Response characteristics analysis of a fuzzy-PID neural networks controller used for DO concentration control in antibiotic fermentation

针对抗生素发酵过程溶氧浓度自动控制的需要,建立了三输入双输出模糊PID神-经网络控制器,通过计算机仿真和计算机实时控制,对标度因子取值不同时控制器的响应特性进行了分析,确定了标度因子的初始值(GS=10、GQ=20、Ke=10.0、Kc=2.0、Kh=2.0)及其在线自调整策略。该控制器在对金霉素和卡那霉素发酵过程溶氧浓度自动控制中取得了良好的应用效果。

A fuzzy PID-neural networks controller with 3 inputs and2 outputs was built for DO concentration control in antibiotic fermentation. Through computer simulation and real time control with computer, the analysis of response characteristics of the controller and the determination of the parameters of fuzzy neural networks were performed. The initial values and the policy for self-regulating of those parameters were determined as well. When used in the control of dissolved oxygen in aureomycin and kanamycin fermentation process, the controller ran with a satisfactory result.