摘要
为解决污水处理过程出水氨氮和总氮浓度超标问题,提出了一种基于超标抑制策略的多目标优化控制方法。该方法利用长短期记忆网络的时序建模能力,对出水氨氮和总氮浓度建立预测模型,采用基于分解的动态种群多邻域多目标进化算法对水质和能耗进行优化,结合预测模型输出确定硝态氮和溶解氧浓度的最优设定值,并对设定值进行跟踪控制。当水质超标时,采取抑制策略对外回流量及外部碳源加以控制,调节溶解氧浓度并对硝态氮浓度进行二次优化以抑制峰值。所提优化控制方法在基准仿真1号平台进行验证。结果表明,所提方法能够有效抑制氨氮和总氮浓度超标,超标时长及能耗明显低于所对比控制方法。
To solve the problem of exceeding standard concentrations of ammonia nitrogen and total nitrogen in the wastewater treatment process,we propose a multi-objective optimization control method based on an exceeding standard suppression strategy.In the proposed method,we establish a prediction model for effluent ammonia nitrogen and total nitrogen concentrations by utilizing the time-series modeling capability of the long short-term memory network.We optimize the water quality and energy consumption using a dynamic population multi-neighborhood and multi-objective evolutionary algorithm based on decomposition.The optimal set values of nitrate nitrogen and dissolved oxygen concentrations are determined by combining the output of the prediction model,and the set values are tracked and controlled.When the water quality exceeds the standard,we adopt an inhibition strategy to control the external return flow and external carbon sources,adjust the concentration of dissolved oxygen,and optimize the concentration of nitrate nitrogen twice to suppress the peak value.The proposed optimization control method is verified on the Benchmark Simulation Model No.1 platform.The results show that the proposed method can effectively restrain the concentration of ammonia nitrogen and total nitrogen from exceeding the standard and that the exceeding time and energy consumption are significantly lower than the comparison control method.
作者
刘传玉
熊伟丽
LIU Chuanyu;XIONG Weili(School of Internet of Things Engineering,Jiangnan University,Wuxi 214122,China;Key Laboratory of Advanced Process Control for Light Industry(Ministry of Education),Wuxi 214122,China)
出处
《信息与控制》
CSCD
北大核心
2024年第2期250-260,272,共12页
Information and Control
基金
国家自然科学基金项目(61773182)
国家重点研发计划子课题(2018YFC1603705-03)
广东省科技专项资金项目(2020ST010)
江苏高校“青蓝工程”项目
关键词
污水处理过程
超标抑制策略
长短期记忆网络
预测模型
二次优化
wastewater treatment process
exceeding standard suppression strategy
long short-term memory network
prediction model
quadratic optimization
