Ensemble learning and deep learning-based defect detection in power generation plants

One of the key factors driving a country’s economic development and ensuring the sustainability of its industries is the constant availability of electricity. This is normally provided by the national grid. However, the power supply is not always stable in developing countries where new businesses,...

Full description

Saved in:
Bibliographic Details
Main Authors: Atemkeng Marcellin, Osanyindoro Victor, Rockefeller Rockefeller, Hamlomo Sisipho, Mulongo Jecinta, Ansah-Narh Theophilus, Tchakounté Franklin, Fadja Arnaud Nguembang
Format: Article
Language:English
Published: De Gruyter 2024-11-01
Series:Journal of Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1515/jisys-2023-0283
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846171058584944640
author Atemkeng Marcellin
Osanyindoro Victor
Rockefeller Rockefeller
Hamlomo Sisipho
Mulongo Jecinta
Ansah-Narh Theophilus
Tchakounté Franklin
Fadja Arnaud Nguembang
author_facet Atemkeng Marcellin
Osanyindoro Victor
Rockefeller Rockefeller
Hamlomo Sisipho
Mulongo Jecinta
Ansah-Narh Theophilus
Tchakounté Franklin
Fadja Arnaud Nguembang
author_sort Atemkeng Marcellin
collection DOAJ
description One of the key factors driving a country’s economic development and ensuring the sustainability of its industries is the constant availability of electricity. This is normally provided by the national grid. However, the power supply is not always stable in developing countries where new businesses, including the telecommunications industry, are constantly emerging. Therefore, they must rely on generators to ensure their full functionality. These generators rely on fuel to function, and consumption is usually high if not properly monitored. Monitoring is usually done by a (non-expert) human. This can sometimes be a tedious process, as some companies have reported excessively high consumption rates. For anomaly detection in power generating plants, the studies by Mulongo et al. and Atemkeng and Jimoh used the same dataset to train a multilayer perceptron (MLP) and generative adversarial networks (GANs), respectively, achieving an accuracy of 96.1% with MLP and 98.9% with GAN. Through comparative analysis and the use of ensemble learning techniques, we found that ensemble learning models outperform both MLP and GAN as proposed by Mulongo et al. and Atemkeng and Jimoh using the same dataset. Furthermore, we investigated the potential of autoencoders to outperform MLPs, GANs, and ensemble learning models. To this end, we have introduced a label-assisted autoencoder approach for detecting anomalies in power-generating plants. This model includes a labelling assistance module that adjusts the thresholds. Our results indicate that the label-assisted autoencoder outperforms the MLP. However, GANs and all ensemble learning models outperformed the label-assisted autoencoder. Nevertheless, the use of a label-assisted autoencoder offers a distinct advantage in categorizing anomalies based on their severity, a capability not present in ensemble learning models and GANs.
format Article
id doaj-art-a059a9ef84cf4c27b09e17e507eddd1f
institution Kabale University
issn 2191-026X
language English
publishDate 2024-11-01
publisher De Gruyter
record_format Article
series Journal of Intelligent Systems
spelling doaj-art-a059a9ef84cf4c27b09e17e507eddd1f2024-11-11T08:36:35ZengDe GruyterJournal of Intelligent Systems2191-026X2024-11-0133140910.1515/jisys-2023-0283Ensemble learning and deep learning-based defect detection in power generation plantsAtemkeng Marcellin0Osanyindoro Victor1Rockefeller Rockefeller2Hamlomo Sisipho3Mulongo Jecinta4Ansah-Narh Theophilus5Tchakounté Franklin6Fadja Arnaud Nguembang7Department of Mathematics, Rhodes University, P.O. Box 94, 6139 Makhanda, South AfricaDepartment of Mathematical Sciences, African Institute for Mathematical Sciences, P.O. Box 608, Limbe, CameroonDepartment of Mathematical Sciences, African Institute for Mathematical Sciences, P.O. Box 608, Limbe, CameroonDepartment of Statistics, Rhodes University, P.O. Box 94, 6139 Makhanda, South AfricaDepartment of Mathematical Sciences, African Institute for Mathematical Sciences, P.O. Box 608, Limbe, CameroonGhana Space Science and Technology Institute, Ghana Atomic Energy Commission, P.O. Box 80, Accra, GhanaDepartment of SFTI, School of Chemical Engineering and Mineral Industries, University of Ngaoundéré, P.O. Box 454, Ngaoundéré, CameroonDipartimento di Matematica e Informatica, University of Ferrara, Via Saragat 1, I-44122 Ferrara, ItalyOne of the key factors driving a country’s economic development and ensuring the sustainability of its industries is the constant availability of electricity. This is normally provided by the national grid. However, the power supply is not always stable in developing countries where new businesses, including the telecommunications industry, are constantly emerging. Therefore, they must rely on generators to ensure their full functionality. These generators rely on fuel to function, and consumption is usually high if not properly monitored. Monitoring is usually done by a (non-expert) human. This can sometimes be a tedious process, as some companies have reported excessively high consumption rates. For anomaly detection in power generating plants, the studies by Mulongo et al. and Atemkeng and Jimoh used the same dataset to train a multilayer perceptron (MLP) and generative adversarial networks (GANs), respectively, achieving an accuracy of 96.1% with MLP and 98.9% with GAN. Through comparative analysis and the use of ensemble learning techniques, we found that ensemble learning models outperform both MLP and GAN as proposed by Mulongo et al. and Atemkeng and Jimoh using the same dataset. Furthermore, we investigated the potential of autoencoders to outperform MLPs, GANs, and ensemble learning models. To this end, we have introduced a label-assisted autoencoder approach for detecting anomalies in power-generating plants. This model includes a labelling assistance module that adjusts the thresholds. Our results indicate that the label-assisted autoencoder outperforms the MLP. However, GANs and all ensemble learning models outperformed the label-assisted autoencoder. Nevertheless, the use of a label-assisted autoencoder offers a distinct advantage in categorizing anomalies based on their severity, a capability not present in ensemble learning models and GANs.https://doi.org/10.1515/jisys-2023-0283electric gridfuel consumptionautoencoderanomaly detectionpower generating plantsgansensemble learning
spellingShingle Atemkeng Marcellin
Osanyindoro Victor
Rockefeller Rockefeller
Hamlomo Sisipho
Mulongo Jecinta
Ansah-Narh Theophilus
Tchakounté Franklin
Fadja Arnaud Nguembang
Ensemble learning and deep learning-based defect detection in power generation plants
Journal of Intelligent Systems
electric grid
fuel consumption
autoencoder
anomaly detection
power generating plants
gans
ensemble learning
title Ensemble learning and deep learning-based defect detection in power generation plants
title_full Ensemble learning and deep learning-based defect detection in power generation plants
title_fullStr Ensemble learning and deep learning-based defect detection in power generation plants
title_full_unstemmed Ensemble learning and deep learning-based defect detection in power generation plants
title_short Ensemble learning and deep learning-based defect detection in power generation plants
title_sort ensemble learning and deep learning based defect detection in power generation plants
topic electric grid
fuel consumption
autoencoder
anomaly detection
power generating plants
gans
ensemble learning
url https://doi.org/10.1515/jisys-2023-0283
work_keys_str_mv AT atemkengmarcellin ensemblelearninganddeeplearningbaseddefectdetectioninpowergenerationplants
AT osanyindorovictor ensemblelearninganddeeplearningbaseddefectdetectioninpowergenerationplants
AT rockefellerrockefeller ensemblelearninganddeeplearningbaseddefectdetectioninpowergenerationplants
AT hamlomosisipho ensemblelearninganddeeplearningbaseddefectdetectioninpowergenerationplants
AT mulongojecinta ensemblelearninganddeeplearningbaseddefectdetectioninpowergenerationplants
AT ansahnarhtheophilus ensemblelearninganddeeplearningbaseddefectdetectioninpowergenerationplants
AT tchakountefranklin ensemblelearninganddeeplearningbaseddefectdetectioninpowergenerationplants
AT fadjaarnaudnguembang ensemblelearninganddeeplearningbaseddefectdetectioninpowergenerationplants