Condition Monitoring of Combustion Processes Through Flame Imaging and Kernel Principal Component Analysis

Sun, Duo and Lu, Gang and Zhou, Hao and Yan, Yong (2013) Condition Monitoring of Combustion Processes Through Flame Imaging and Kernel Principal Component Analysis. Combustion Science and Technology, 185 (9). pp. 1400-1413. ISSN 0010-2202. (doi:https://doi.org/10.1080/00102202.2013.798316) (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided)

The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided. (Contact us about this Publication)
Official URL
http://dx.doi.org/10.1080/00102202.2013.798316

Abstract

This article presents a methodology for the diagnosis of abnormal conditions in a combustion process through flame imaging and kernel principal component analysis (KPCA). A digital imaging system is used to capture real-time flame images and radiation signals, from which flame characteristics such as flame area, brightness, non-uniformity, and oscillation frequency are quantified. These characteristics are used as the variables to establish the KPCA model of the combustion process. With the use of Hotelling's T2 and Q statistics, the monitoring of abnormal conditions of the combustion process is achieved. Unlike the traditional principal component analysis (PCA) method, the KPCA method is capable of dealing with nonlinear data via nonlinear mapping, which projects the original nonlinear input space into a high-dimensional linear feature space. The effectiveness of the methodology is demonstrated by applying the approach to processing the data obtained on a 9MWth heavy oil fired combustion test facility. Experimental results obtained show that the KPCA method outperforms the traditional PCA in discriminating between the normal and abnormal combustion conditions, even in cases where the number of training samples is limited.

Item Type: Article
Uncontrolled keywords: Combustion process, Condition monitoring, Digital imaging, Fault detection, Flame monitoring, Hotelling's T2 statistic, KPCA, Q statistic
Subjects: T Technology
Divisions: Faculties > Sciences > School of Engineering and Digital Arts
Faculties > Sciences > School of Engineering and Digital Arts > Instrumentation, Control and Embedded Systems
Depositing User: Tina Thompson
Date Deposited: 22 Oct 2013 09:42 UTC
Last Modified: 25 Oct 2013 11:22 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/35573 (The current URI for this page, for reference purposes)
  • Depositors only (login required):