Fault detection and diagnosis of thermal power plant using ANN. Case study with review
Samarra Journal of Engineering Science and Research · 2024
DOI: 10.65115/9m3xan53 ↗Kurz gefasst
Fachartikel in der Zeitschrift Samarra Journal of Engineering Science and Research, 2024. Verfasst von Rawaa Jasim und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The paper investigates thermal power plant malfunctions, including line to line, double line to ground, and single line to ground faults leading to system downtime. The research focuses on utilizing Artificial Neural Network (ANN) as an intelligent tool for fault diagnosis in electrical power plants. Among various fault detection methods like Logic Regression, Genetic Algorithm, and Fuzzy Logic, the paper chooses ANN for its pattern recognition, classification, matching, prediction, decision-making, and control capabilities. Despite requiring extensive computational training, ANN is considered an intelligent system. The last part provides a concise overview of electrical stations, particularly thermal power plants, explores common fault types, and introduces ANNs with explanations of the fundamental neuron model. It elaborates on human neurons (BNN) and artificial neurons (ANN) operations, providing examples of ANNs in fault detection from previous literature.
Zitieren
APA
Jasim, R., & Gaeid, K. S. (2024). Fault detection and diagnosis of thermal power plant using ANN. Case study with review. Samarra Journal of Engineering Science and Research. https://doi.org/10.65115/9m3xan53
Vancouver
Jasim R, Gaeid KS. Fault detection and diagnosis of thermal power plant using ANN. Case study with review. Samarra Journal of Engineering Science and Research. 2024. doi:10.65115/9m3xan53
BibTeX
@article{Jasim2024,
author = {Jasim, Rawaa and Gaeid, Khalaf Salloum},
title = {Fault detection and diagnosis of thermal power plant using ANN. Case study with review},
journal = {Samarra Journal of Engineering Science and Research},
year = {2024},
doi = {10.65115/9m3xan53}
}
EUVIMED