基于人工蜂群算法的支持向量回归建模及其在污水处理中的应用  

Research on Support Vector Regression Modeling Based on Artificial Bee Colony Algorithm and Its Application in Sewage Wastewater Treatment

作　　者：李明珠[1] LI Mingzhu(Haikou University of Economics,Haikou Hainan 571127,China)

机构地区：[1]海口经济学院,海南海口571127

出　　处：《信息与电脑》2024年第6期32-34,共3页Information & Computer

基　　金：海南省自然科学基金资助“面向污水处理的自适应软测量建模和监测方法研究”(项目编号:623QN256)。

摘　　要：污水处理过程具有大时滞、非线性、多扰动等特点,运行过程中存在生化需氧量(Biochemical Oxygen Demand,BOD)等重要水质参数难以实时测量问题,软测量技术为解决该问题提供了有效方法。对此,文章提出基于人工蜂群算法的支持向量回归(Support Vector Regression,SVR)建模方法。该方法利用蜂群算法对支持向量机的参数gamma和C进行寻优,找到使均方误差最小的超参数组合,以提高模型预测精度。同时,利用加州大学欧文分校(University of California Irvine,UCI)数据库中的污水生产数据验证该方法的有效性,结果表明该方法的实际应用效果好,可为工业生产中难以测量变量的监测提供技术支持。The sewage treatment process has the characteristics of large time delay,nonlinearity,and multiple disturbances.During operation,important water quality parameters such as biochemical oxygen demand(BOD)are difficult to measure in real time.Soft measurement technology provides an effective method to solve this problem.This paper proposes a Support Vector Regression(SVR)modeling method based on the bee colony optimization algorithm.This method uses the bee colony algorithm to optimize the parameter gamma and C of the support vector machine,find the hyperparameter combination that minimizes the mean square error,and thereby improve the model prediction accuracy.At the same time,sewage production data from University of Californialrvine database is used to verify the effectiveness of the method,the results show that the practical application of the method is good,and can provide technical support for the monitoring of difficult to measure variables in industrial production.

关 键 词：支持向量回归(SVR) 人工蜂群算法 污水处理 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]