文章基本信息

标题：Development of K- Means Based SVM Regression (KSVMR) Technique for Boiler Flue Gas Estimation
本地全文：下载
作者：Ramakalyan Ayyagari ; Anantharaman Sivakumar ; Krithivasan Kannan 等
期刊名称：International Journal on Electrical Engineering and Informatics
印刷版ISSN：2085-6830
出版年度：2014
卷号：6
期号：2
DOI：10.15676/ijeei.2014.6.2.10
出版社：School of Electrical Engineering and Informatics
摘要：This paper presents development of a Support Vector Machine (SVM)regression, driven by a Radial Basis Function kernel for obtaining the composition ofboiler flue gas mixtures. The frequency components of various gas mixtures were firstprocessed by Floyd K – Means algorithm and the data with class labels were utilized tobuild a multi-class SVM regression model for discrimination of the flue gas constituentsand subsequent composition finding. The Meta parameters (C, ε and kernel) areoptimized using grid search technique to obtain appropriate support vectors to train thenetwork. After ascertaining the performance of proposed technique through volatileorganic component (VOC) data acquired from quartz crystal microbalance (QCM) typesensors used by earlier researchers, detailed studies have been carried out to study thediscriminating and estimation capability of the proposed technique for real time flue gasdata acquired from two different analyzers namely ORSATR and KANE. Exhaustivestudies clearly indicate the exceptional performance of the proposed SVM model inclassifying and estimating the flue gas components in machine (Analyzer) independentmanner.
关键词：Flue gas mixture; SVM; Grid Technique Prediction error; Feature selection.