华东理工大学学报（自然科学版）2017，Vol.43Issue(5)：684-691,8.DOI:10.14135/j.cnki.1006-3080.2017.05.013
IFA和FA联合方法在化工过程监控中的应用
A Combined Method of Independent Factor Analysis and Factor Analysis for Chemical Process Monitoring
摘要
Abstract
Many industrial process variables have the characteristics of non-Gaussian and Gaussian mixture distribution.Independent factor analysis (IFA) algorithm utilizes one dimension Gaussian mixture model to approximate any factor distribution such that it can address the problem of the Gaussian and nonGaussian mixture.Although the variational IFA with given factors can reduce the modeling-time,it still takes a lot of time to determine an optimal number.Especially,an inappropriate number may make the information of partial factors be remained in the residuals of the observed variables,which will result in the poor monitoring performance on the GSPE index.Aiming at the above problem in the application of IFA,this paper proposes a combined method of IFA and FA.Firstly,FA algorithm is used in determining the independent factor number so as to reduce the modelling time of IFA.And then,FA is further utilized to reprocess the residual of IFA so that the remained partial factors' information in residual can be fully employed.Finally,the monitoring experiment in the Tennessee-Eastman (TE) process and the ethylene cracking furnace verifies the validity of the proposed method.关键词
因子分析/独立因子分析/改进的综合监控指标/噪声空间指标/非高斯Key words
factor analysis/independent factor analysis/modified synthesis target/noise subspace index/non-Gaussia分类
信息技术与安全科学引用本文复制引用
丁英涛,程辉,王振雷,梅华,赵亮..IFA和FA联合方法在化工过程监控中的应用[J].华东理工大学学报（自然科学版）,2017,43(5):684-691,8.基金项目
国家自然科学基金(61134007,21376077,21303102) （61134007,21376077,21303102）
上海市研发平台建设项目(13DZ2295300) （13DZ2295300）
上海市自然科学基金(16ZR1407300) （16ZR1407300）
