ANALYSIS AND DETECTION OF FAULTS IN A COMBINED CYCLE POWER PLANT
Loading...
Date
2025
Journal Title
Journal ISSN
Volume Title
Publisher
National higher scool of technology and engineering-Annaba
Abstract
In order to improve the performance of industrial processes and prevent efficiency losses caused by technical faults in power plants, it is imperative to have a high-performance monitoring system. There are a lot of methods for diagnosing and detecting faults that have been developed, and in our cas we are using a method that combines two main techniques (coupling diagnosis method), based on wavelet decomposition and Wavelet Energy Entropy (WEE) for feature extraction from sensor signals, and Support Vector Machine (SVM) or Random Forest (RF) for fault classification. This work was implemented by MATLAB software, Wavelet Toolbox for signal decomposition, with Machine Learning Toolbox and TreeBagger for classification.