Real-World Steam Powerplant Boiler Tube Leakage Detection Using Hybrid Deep Learning

The detection of boiler water-wall tube leakage in steam power plants is essential to prevent efficiency loss, unexpected shutdowns, and costly repairs. This study proposes a hybrid deep learning approach that combines convolutional neural networks (CNNs) with a support vector machine (SVM) classifi...

Full description

Saved in:
Bibliographic Details
Main Authors: Salman Khalid, Muhammad Muzammil Azad, Heung Soo Kim
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/12/24/3887
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850060133200035840
author Salman Khalid
Muhammad Muzammil Azad
Heung Soo Kim
author_facet Salman Khalid
Muhammad Muzammil Azad
Heung Soo Kim
author_sort Salman Khalid
collection DOAJ
description The detection of boiler water-wall tube leakage in steam power plants is essential to prevent efficiency loss, unexpected shutdowns, and costly repairs. This study proposes a hybrid deep learning approach that combines convolutional neural networks (CNNs) with a support vector machine (SVM) classifier to allow early and accurate leak detection. The methodology utilizes temperature data from multiple sensors positioned at critical points in the boiler system. The data of each sensor are independently processed by a dedicated CNN model, allowing for the autonomous extraction of sensor-specific features. These features are then fused to create a comprehensive feature representation of the system’s condition, which is analyzed by an SVM classifier to accurately identify leakages. By utilizing the feature extraction capabilities of CNNs and the classification strength of an SVM, this approach effectively identifies subtle operational anomalies that are indicative of potential leaks. The model demonstrates high detection accuracy and minimizes false-positives, providing a robust solution for real-time monitoring and proactive maintenance strategies in industrial systems.
format Article
id doaj-art-0dc0137ceda94500bee4b41c10096d8c
institution DOAJ
issn 2227-7390
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-0dc0137ceda94500bee4b41c10096d8c2025-08-20T02:50:41ZengMDPI AGMathematics2227-73902024-12-011224388710.3390/math12243887Real-World Steam Powerplant Boiler Tube Leakage Detection Using Hybrid Deep LearningSalman Khalid0Muhammad Muzammil Azad1Heung Soo Kim2Department of Mechanical, Robotics and Energy Engineering, Dongguk University-Seoul, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, Republic of KoreaDepartment of Mechanical Engineering, Dongguk University-Seoul, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, Republic of KoreaDepartment of Mechanical, Robotics and Energy Engineering, Dongguk University-Seoul, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, Republic of KoreaThe detection of boiler water-wall tube leakage in steam power plants is essential to prevent efficiency loss, unexpected shutdowns, and costly repairs. This study proposes a hybrid deep learning approach that combines convolutional neural networks (CNNs) with a support vector machine (SVM) classifier to allow early and accurate leak detection. The methodology utilizes temperature data from multiple sensors positioned at critical points in the boiler system. The data of each sensor are independently processed by a dedicated CNN model, allowing for the autonomous extraction of sensor-specific features. These features are then fused to create a comprehensive feature representation of the system’s condition, which is analyzed by an SVM classifier to accurately identify leakages. By utilizing the feature extraction capabilities of CNNs and the classification strength of an SVM, this approach effectively identifies subtle operational anomalies that are indicative of potential leaks. The model demonstrates high detection accuracy and minimizes false-positives, providing a robust solution for real-time monitoring and proactive maintenance strategies in industrial systems.https://www.mdpi.com/2227-7390/12/24/3887steam powerplantboilerleakage detectiondeep learningconvolutional neural networkshybrid approach
spellingShingle Salman Khalid
Muhammad Muzammil Azad
Heung Soo Kim
Real-World Steam Powerplant Boiler Tube Leakage Detection Using Hybrid Deep Learning
Mathematics
steam powerplant
boiler
leakage detection
deep learning
convolutional neural networks
hybrid approach
title Real-World Steam Powerplant Boiler Tube Leakage Detection Using Hybrid Deep Learning
title_full Real-World Steam Powerplant Boiler Tube Leakage Detection Using Hybrid Deep Learning
title_fullStr Real-World Steam Powerplant Boiler Tube Leakage Detection Using Hybrid Deep Learning
title_full_unstemmed Real-World Steam Powerplant Boiler Tube Leakage Detection Using Hybrid Deep Learning
title_short Real-World Steam Powerplant Boiler Tube Leakage Detection Using Hybrid Deep Learning
title_sort real world steam powerplant boiler tube leakage detection using hybrid deep learning
topic steam powerplant
boiler
leakage detection
deep learning
convolutional neural networks
hybrid approach
url https://www.mdpi.com/2227-7390/12/24/3887
work_keys_str_mv AT salmankhalid realworldsteampowerplantboilertubeleakagedetectionusinghybriddeeplearning
AT muhammadmuzammilazad realworldsteampowerplantboilertubeleakagedetectionusinghybriddeeplearning
AT heungsookim realworldsteampowerplantboilertubeleakagedetectionusinghybriddeeplearning