An Intelligent Monitoring Interface for a Coal-Fired Power Plant Boiler Trips

A power plant monitoring system embedded with artificial intelligence can enhance its effectiveness by reducing the time spent in trip analysis and follow up procedures. Experimental results showed that Multilayered perceptron neural network trained with Levenberg-Marquardt (LM) algorithm achieved t...

Full description

Bibliographic Details
Main Author: Mohd Nistah, Nong Nurnie
Format: Thesis
Published: Curtin University 2018
Online Access:http://hdl.handle.net/20.500.11937/77234
_version_ 1848763831512203264
author Mohd Nistah, Nong Nurnie
author_facet Mohd Nistah, Nong Nurnie
author_sort Mohd Nistah, Nong Nurnie
building Curtin Institutional Repository
collection Online Access
description A power plant monitoring system embedded with artificial intelligence can enhance its effectiveness by reducing the time spent in trip analysis and follow up procedures. Experimental results showed that Multilayered perceptron neural network trained with Levenberg-Marquardt (LM) algorithm achieved the least mean squared error of 0.0223 with the misclassification rate of 7.435% for the 10 simulated trip prediction. The proposed method can identify abnormality of operational parameters at the confident level of ±6.3%.
first_indexed 2025-11-14T11:09:43Z
format Thesis
id curtin-20.500.11937-77234
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T11:09:43Z
publishDate 2018
publisher Curtin University
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-772342019-12-10T05:32:41Z An Intelligent Monitoring Interface for a Coal-Fired Power Plant Boiler Trips Mohd Nistah, Nong Nurnie A power plant monitoring system embedded with artificial intelligence can enhance its effectiveness by reducing the time spent in trip analysis and follow up procedures. Experimental results showed that Multilayered perceptron neural network trained with Levenberg-Marquardt (LM) algorithm achieved the least mean squared error of 0.0223 with the misclassification rate of 7.435% for the 10 simulated trip prediction. The proposed method can identify abnormality of operational parameters at the confident level of ±6.3%. 2018 Thesis http://hdl.handle.net/20.500.11937/77234 Curtin University fulltext
spellingShingle Mohd Nistah, Nong Nurnie
An Intelligent Monitoring Interface for a Coal-Fired Power Plant Boiler Trips
title An Intelligent Monitoring Interface for a Coal-Fired Power Plant Boiler Trips
title_full An Intelligent Monitoring Interface for a Coal-Fired Power Plant Boiler Trips
title_fullStr An Intelligent Monitoring Interface for a Coal-Fired Power Plant Boiler Trips
title_full_unstemmed An Intelligent Monitoring Interface for a Coal-Fired Power Plant Boiler Trips
title_short An Intelligent Monitoring Interface for a Coal-Fired Power Plant Boiler Trips
title_sort intelligent monitoring interface for a coal-fired power plant boiler trips
url http://hdl.handle.net/20.500.11937/77234