摘要
针对氨氮浓度和硝态氮浓度之间相互耦合,以及常规的PID控制方法难以获得满意控制效果的特点,以溶解氧浓度和内循环流量为操作变量,采用PID神经网络对氨氮浓度和硝态氮浓度进行解耦控制;针对PID神经网络连接权值容易陷入局部最优值,应用免疫算法优化PID神经网络连接权值。仿真结果表明,该方法对污水生化处理系统具有很好的解耦能力和控制品质。
Aiming at the characteristic of the strong coupling between ammonia nitrogen and nitrate nitrogen,and the conventional PID control method is difficult to achieve satisfactory control performance,this paper employed a PID neural network approach to achieve decoupling control for ammonia nitrogen and nitrate nitrogen,where regarded dissolved oxygen concentration and internal circulation flow as the control inputs.PID neural network connection weights were easy to fall into local optimum.In order to solve this problem,proposed the immune algorithm to optimize the connection weights of PID neural network.Simulation results show that the proposed method has a better decoupling capabilities and control quality for biological wastewater treatment system.
出处
《计算机应用研究》
CSCD
北大核心
2011年第11期4097-4099,共3页
Application Research of Computers
基金
广东省自然科学基金资助项目(10151064101000075)
广东省自然科学基金博士启动项目(9451064101002853)
中央高校基本科研业务费专项资金资助项目(20112M0126)
广西教育厅科研基金资助项目(201010LX242)
广西自然科学基金资助项目(2010GXNSFA013126)
关键词
污水生化处理
解耦控制
PID神经网络
免疫优化
biological wastewater treatment
decoupling control
PID neural network
immune optimization