基于DBO-ELM的污水处理过程软测量建模  

Soft Measurement Modeling of Wastewater Treatment Process Based on IDBO-ELM

作　　者：杜先君[1] 姚艳平 钱强 DU Xianjun;YAO Yanping;QIAN Qiang(College of Electrical and Information Engineering,Lanzhou University of Technology,Lanzhou 730050)

机构地区：[1]兰州理工大学电气工程与信息工程学院,兰州730050

出　　处：《舰船电子工程》2024年第7期103-107,共5页Ship Electronic Engineering

摘　　要：针对污水处理过程中出水生化需氧量(Biochemical Oxygen Demand,BOD)等水质参数受其它环境因素的影响较大,难以建立准确测量模型等的问题,提出一种基于改进蜣螂算法(Improved Dung Beetle Optimizer,IDBO)优化极限学习机(Extreme Learning Machine,ELM)的方法对污水出水BOD浓度进行预测。首先,选用随机森林算法(Random Forest Algo-rithm,RFA)对筛选出与BOD相关性较高的因子作为软测量模型的输入变量;其次,引入Tent混沌映射增加DBO算法的种群多样性等问题,利用IDBO算法来优化确定ELM权值分配,以提高ELM网络的预测精度;最后,将设计的IDBO-ELM软测量模型应用于污水处理仿真平台中,并与不同预测模型进行对比。结果表明:论文所设计的IDBO-ELM预测模型得到更高的预测精度和更稳定的网络结构。Aiming at the problem that the biochemical oxygen demand(BOD)and other water quality parameters in the sew-age treatment process are greatly affected by other environmental factors and it is difficult to establish an accurate measurement mod-el,an improved dung beetle optimizer(IDBO)extreme learning machine(ELM)is proposed.The method predicts the BOD concen-tration of effluent.Firstly,the Random Forest Algorithm(RFA)is selected to screen out factors with high correlation with BOD as input variables of the soft measurement model.Secondly,the IDBO algorithm is utilized to optimize and decide the ELM weight allo-cation to improve the prediction accuracy of the ELM network,and the Tent chaos mapping is used to increase the population diver-sity of the DBO method.Finally,the designed IDBO-ELM soft measurement model is applied to the wastewater treatment simulation platform and compared with different prediction models.The results show that the IDBO-ELM prediction model designed in this pa-per obtains higher prediction accuracy and more stable network structure.

关 键 词：软测量模型 ELM 特征选择 IDBO RFA 

分 类 号：O141.4[理学—数学]