The importance of selecting the optimal number of principal components for fault detection using principal component analysis
Master Thesis
2012
Permanent link to this Item
Authors
Supervisors
Journal Title
Link to Journal
Journal ISSN
Volume Title
Publisher
Publisher
University of Cape Town
Department
License
Series
Abstract
Fault detection and isolation are the two fundamental building blocks of process monitoring. Accurate and efficient process monitoring increases plant availability and utilization. Principal component analysis is one of the statistical techniques that are used for fault detection. Determination of the number of PCs to be retained plays a big role in detecting a fault using the PCA technique. In this dissertation focus has been drawn on the methods of determining the number of PCs to be retained for accurate and effective fault detection in a laboratory thermal system. SNR method of determining number of PCs, which is a relatively recent method, has been compared to two commonly used methods for the same, the CPV and the scree test methods.
Description
Includes summary.
Includes bibliographical references.
Keywords
Reference:
Khwambala, P. 2012. The importance of selecting the optimal number of principal components for fault detection using principal component analysis. University of Cape Town.