基于PCA-PSO-SVM的造纸污水处理过程故障诊断方法  

Fault Diagnosis Method of Papermaking Wastewater Treatment Process Based on PCA-PSO-SVM

作　　者：李炳锐 李荣昌 LI Bingrui;LI Rongchang(Outopei Technology(Zhuhai)Co.,Ltd.,Zhuhai,Guangdong 519000,China;Jiangmen Qiandong Industrial Co.,Ltd.,Jiangmen,Guangdong 529000,China)

机构地区：[1]欧拓飞科技(珠海)有限公司,广东珠海519000 [2]江门市千东实业有限公司,广东江门529000

出　　处：《自动化应用》2023年第21期244-247,共4页Automation Application

摘　　要：为了提高造纸污水处理过程故障诊断的准确性,本文提出了一种基于PCA-PSO-SVM的造纸污水处理过程故障诊断方法。采用PCA提取了造纸污水处理过程故障的主元,以确定造纸污水处理过程故障诊断模型的输入量;采用PSO算法优化了SVM的惩罚系数和核系数,建立PSO-SVM造纸污水处理过程故障诊断模型;采用某大型造纸厂造纸废水数据进行仿真实验,并与其他故障诊断方法对比。结果表明,本文所提造纸污水处理过程故障方法的正确率为95%,明显高于其他方法,验证了本文方法的正确性和实用性。In order to improve the accuracy of fault diagnosis in papermaking wastewater treatment process,this paper proposes a fault diagnosis method for papermaking wastewater treatment process based on PCA-PSO-SVM.PCA was used to extract the principal components of faults in the papermaking wastewater treatment process,in order to determine the input of the fault diagnosis model for the papermaking wastewater treatment process.The penalty coefficient and kernel coefficient of SVM were optimized using PSO algorithm,and a fault diagnosis model for paper wastewater treatment process using PSOSVM was established.Simulation experiments were conducted using data from a large paper mill's papermaking wastewater,and comparisons were made with other fault diagnosis methods.The results show that the accuracy rate of the fault diagnosis method proposed in this paper for papermaking wastewater treatment process is 95%,which is significantly higher than other methods,verifying the correctness and practicality of the method proposed in this paper.

关 键 词：造纸污水处理 故障诊断 主成分分析 粒子群优化算法 支持向量机 

分 类 号：P427[天文地球—大气科学及气象学]