摘要
污水处理过程中溶解氧浓度是重要的控制参数,控制过程受各种不可测扰动的影响,传统控制方法很难达到理想的控制效果。针对此问题,提出一种改进型模糊神经网络二自由度内模控制溶解氧策略。利用神经网络整定二自由度内模控制器滤波器参数,并采用神经元活跃度与激活强度在线动态增减规则层神经元,实现规则层神经元动态优化,克服了参数变化和入水干扰对系统的影响,进而实现溶解氧浓度对设定值的完全跟踪以及对不可测扰动的抑制作用。仿真结果表明:该控制器有效解决了非线性对象难以控制的问题,可获得较好的溶解氧浓度控制效果。
The dissolved oxygen concentration in the sewage treatment process is an important control parameter.The control process is affected by various unmeasurable disturbances.The traditional control method is difficult to achieve the desired control effect.For the above problems,an improved fuzzy neural network two degree of freedom internal model control strategy for dissolved oxygen is proposed.It used the neural network to modulate the two degree of freedom internal model controller filter parameters,and used the neuron activity and activation intensity to dynamically increase and decrease the regular layer neurons online to achieve dynamic optimization of the regular layer neurons,overcoming the parameter changes and water ingress interference.Furthermore,the dissolved oxygen concentration could completely track the set value and restrain the unmeasurable disturbances.The simulation results show that the controller effectively solves the problem that the nonlinear object is difficult to control,and can obtain better dissolved oxygen concentration control effect.
作者
马海涛
宁楠
陈兆波
Ma Haitao;Ning Nan;Chen Zhaobo(School of Electrical and Electronic Engineering,Changchun University of Technology,Changchun 130012,Jilin,China;School of Environment and Bioresources,Dalian Minzu University,Dalian 116600,Liaoning,China)
出处
《计算机应用与软件》
北大核心
2020年第10期41-46,90,共7页
Computer Applications and Software
基金
国家自然科学基金项目(51778114)。
关键词
污水处理过程
溶解氧
内模控制
模糊神经网络
Sewage treatment process
Dissolved oxygen
Internal model control
Fuzzy neural network
