基于3种机器学习模型的污水处理厂出水总氮预测分析  

Predictive Analysis of Effluent Total Nitrogen from Sewage Treatment Plants based on Three Machine Learning Models

作　　者：黄学平[1] 吴留兴 辛攀 邓觅[2] 吴永明 姚忠[2] 赵旭雍[3] 徐欣 HUANG Xueping;WU Liuxing;XIN Pan;DENG Mi;WU Yongming;YAO Zhong;ZHAO Xuyong;XU Xin(School of Civil and Architectural Engineering,Nanchang Institute of Technology,Nanchang 330099,China;Institute of Microbiology,Jiangxi Academy of Sciences,Nanchang 330096,China;Nanchang Xinmiaoyuan Environmental Protection Co.,Ltd.,Nanchang 330038,China)

机构地区：[1]南昌工程学院土木与建筑工程学院,南昌330099 [2]江西省科学院微生物研究所,南昌330096 [3]南昌鑫淼源环保有限公司,南昌330038

出　　处：《能源研究与管理》2023年第2期100-105,126,共7页Energy Research and Management

基　　金：江西省科技创新基地计划(20212BCD42014);江西省科学院省级科技计划项目包干制试点示范项目(2021YSBG10003,2021YSBG22024,2022YSBG22010,2022YSBG22012);江西科技计划项目(20212BBG71002)。

摘　　要：为实现对污水处理厂出水总氮(TN)浓度的准确预测,收集并分析了某污水处理厂的317条实际运行监测数据,将数据进行预处理后,结合关联度较高的进水TN等6项常规水质指标,利用随机森林、KNN及SVR 3种机器学习模型对出水TN进行预测,并将预测值进行对比分析。结果表明:KNN和SVR 2种模型的决定系数分别为0.759和0.723,低于随机森林模型的0.814;KNN与SVR对应的平均绝对比分比误差分别为12.02%和12.49%,相较于随机森林的10.54%更高;KNN与SVR的均方误差分别为1.09和1.26,高于随机森林的0.85。因此,在有一定进水数据的基础上,通过随机森林构建的出水TN预测模型的精度更高,该研究方法能为污水预测提供一种新的尝试。To accurately predict the total nitrogen(TN)concentration of effluent from a sewage treatment plant,collected and analyzed 317 actual operational monitoring data of a sewage treatment plant,upon data pretreatment,in combination with six conventional water quality indexes with high correlation such as inlet TN,three machine learning models of random forest,KNN and SVR were used to predict effluent TN,and the predicted values were compared and analyzed.The results indicate that:The determination coefficients of KNN and SVR were 0.759 and 0.723 respectively,lower than 0.814 of the random forest model.The mean absolute percentage error of KNN and SVR was 12.02%and 12.49%respectively,which was higher than that of random forest(10.54%).The mean square error of KNN and SVR is 1.09 and 1.26 respectively,which is higher than that of random forest(0.85).Therefore,the prediction model of effluent TN built by random forest has a higher accuracy on the basis of certain influent data,and this research method can provide a new attempt for sewage prediction.

关 键 词：污水处理 灰色关联分析 机器学习 总氮 

分 类 号：X522[环境科学与工程—环境工程]