摘要
针对复杂的污水处理过程中化学需氧量(COD)难以实现精准、经济测量这一难题,提出一种出水COD浓度预测的模糊建模方法.基于活性污泥法搭建关于出水COD的模糊预测模型,用模糊C均值聚类算法(FCM)对模型进行结构辨识,采用最小二乘法对模型进行参数辨识,并用烟花算法(FWA)对模型的结构和参数进行优化学习.将污水处理仿真基本模型(BSM1)提供的数据在MATLAB平台进行仿真实验,结果表明,采用烟花算法优化后的模糊预测模型对出水COD的预测精度更高,预测效果更好.
It is difficult to achieve accurate and economical measurement of chemical oxygen demand(COD) in complex wastewater treatment processes. A fuzzy modeling method for the prediction of effluent COD concentration was proposed. Firstly, based on the activated sludge method, a fuzzy prediction model for effluent COD was constructed. Then, the fuzzy C-means clustering algorithm(FCM) was used to identify the model, and the model was identified by least squares method. The structure and parameters of the model were optimized by fireworks algorithm(FWA). Finally, the data provided by the sewage treatment simulation basic model(BSM1) was simulated on the MATLAB platform. The experimental results show that the fuzzy prediction model optimized by the fireworks algorithm has higher prediction accuracy and better prediction effect on the effluent COD.
作者
胡赛飞
李明河
HU Saifei;LI Minghe(School of Electrical and Information Engineering,Anhui University of Technology,Ma’anshan,Anhui 243032,China)
出处
《宜宾学院学报》
2019年第12期10-15,共6页
Journal of Yibin University
基金
安徽省科技攻关重大项目（1301041023）
关键词
污水处理
化学需氧量
烟花算法
模糊预测
sewage treatment
chemical oxygen demand
fireworks algorithm
fuzzy prediction
