基于动态核PCA的复杂废水处理过程在线故障检测  

Online fault detection of complex wastewater treatment process using dynamic kernel PCA

作　　者：刘鸿斌 张昊 景宜[1] 张凤山[2] LIU Hongbin;ZHANG Hao;JING Yi;ZHANG Fengshan(Jiangsu Co-Innovation Center of Efficient Processing and Utilization of Forest Resources, Nanjing Forestry University, Nanjing, Jiangsu 210037, China;Shandong Huatai Paper Industry Co., Ltd., Dongying, Shandong 257335, China)

机构地区：[1]南京林业大学江苏省林业资源高效加工利用协同创新中心,江苏南京210037 [2]山东华泰纸业股份有限公司,山东东营257335

出　　处：《江苏大学学报（自然科学版）》2021年第2期215-220,共6页Journal of Jiangsu University：Natural Science Edition

基　　金：南京林业大学标志性成果培育建设项目(202026)。

摘　　要：为了克服废水处理过程具有较强的非线性及动态特性,研究了基于主成分分析(principal component analysis,PCA)的在线故障检测.首先在PCA的基础上引入核函数,构造核主成分分析(kernel principal component analysis,KPCA)来优化模型结构,再通过嵌入动态模型来构造动态核主成分分析方法(DKPCA),最后对废水处理过程进行在线故障检测.基于某造纸厂废水数据,构建了偏移故障、漂移故障及精度下降故障,并进行仿真.研究结果表明,在偏移故障条件下,相较于PCA和KPCA方法,DKPCA的平方预测误差故障检测率分别提升了96.96%和87.87%,且在漂移故障条件下检测的灵敏度也有明显提升,验证了在废水时变性过程中DKPCA方法在线故障检测的有效性.To overcome the strong nonlinearity and dynamic characteristics,the online fault detection was investigated based on principal component analysis(PCA)in a wastewater treatment process.The kernel principal component analysis(KPCA)was constructed by introducing kernel functions in PCA,and the dynamic kernel principal component analysis(DKPCA)was proposed by embedding dynamic models to achieve online fault detection in the wastewater treatment process.According to the data from the treatment process of a paper mail wastewater,the bias faults,the drift faults and the precision degradation faults were established and simulated.The results show that under the condition of bias faults,compared with PCA and KPCA,the squared prediction error of DKPCA is respectively improved by 96.96%and 87.87%,and the detection sensitivity in drift fault is also improved.The validity of the DKPCA method is verified in online fault detection of wastewater treatment.

关 键 词：废水处理过程 主成分分析 动态过程 非线性过程 故障检测 

分 类 号：X793[环境科学与工程—环境工程]