Deep Learning Image-Based Defect Detection in High Voltage Electrical Equipment

The increase in the internal temperature of high voltage electrical instruments is due to a variety of factors, particularly, contact problems; environmental factors; unbalanced loads; and cracks in the high voltage current transformers, voltage transformers, insulators, or terminal junctions. This...

Full description

Bibliographic Details
Main Authors: Irfan Ullah, Rehan Ullah Khan, Fan Yang, Lunchakorn Wuttisittikulkij
Format: Article
Language:English
Published: MDPI AG 2020-01-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/13/2/392
id doaj-06c8d6b777044638bf37f18127f8ff0f
record_format Article
spelling doaj-06c8d6b777044638bf37f18127f8ff0f2020-11-25T01:47:08ZengMDPI AGEnergies1996-10732020-01-0113239210.3390/en13020392en13020392Deep Learning Image-Based Defect Detection in High Voltage Electrical EquipmentIrfan Ullah0Rehan Ullah Khan1Fan Yang2Lunchakorn Wuttisittikulkij3Smart Wireless Communication Ecosystem Research Group, Department of Electrical Engineering, Chulalongkorn University, Bangkok 10330, ThailandDepartment of Information Technology, College of Computer, Qassim University, Al-Mulida 52571, Saudi ArabiaState Key Laboratory of Power Transmission Equipment & System Security and New Technology, School of Electrical Engineering, Chongqing University, Chongqing 400044, ChinaSmart Wireless Communication Ecosystem Research Group, Department of Electrical Engineering, Chulalongkorn University, Bangkok 10330, ThailandThe increase in the internal temperature of high voltage electrical instruments is due to a variety of factors, particularly, contact problems; environmental factors; unbalanced loads; and cracks in the high voltage current transformers, voltage transformers, insulators, or terminal junctions. This increase in the internal temperature can cause unusual disturbances and damage to high voltage electrical equipment. Therefore, early prevention measures of thermal anomalies in equipment are necessary to prevent high voltage equipment failure that might shut down the whole grid system. In this article, we propose a novel non-destructive approach to defect analysis in high voltage equipment by taking advantage of the infrared thermography and the deep learning (DL) approach from the machine learning paradigm. The infrared images of the components were captured using the FLIR T630 without disturbing the operations of the power grid. In the first stage, rich features maps from the convolutional layers of the AlexNet pretrained model were extracted. After feature extraction, the random forest (RF) and support vector machines (SVM) were trained for learning of the defective and non-defective high voltage electrical equipment. In an experimental analysis, the RF optimally learned the separation between defective and non-defective equipment with greater than 96% accuracy, outperforming all the other comparative approaches for deep and nondeep features. The proposed approach based on the RF is reliable and shows its efficacy for fault detection in high voltage electrical equipment.https://www.mdpi.com/1996-1073/13/2/392random forestsupport vector machinehigh voltage electrical equipmentinfrared thermographydefect detectionthermal imagingdeep learning
collection DOAJ
language English
format Article
sources DOAJ
author Irfan Ullah
Rehan Ullah Khan
Fan Yang
Lunchakorn Wuttisittikulkij
spellingShingle Irfan Ullah
Rehan Ullah Khan
Fan Yang
Lunchakorn Wuttisittikulkij
Deep Learning Image-Based Defect Detection in High Voltage Electrical Equipment
Energies
random forest
support vector machine
high voltage electrical equipment
infrared thermography
defect detection
thermal imaging
deep learning
author_facet Irfan Ullah
Rehan Ullah Khan
Fan Yang
Lunchakorn Wuttisittikulkij
author_sort Irfan Ullah
title Deep Learning Image-Based Defect Detection in High Voltage Electrical Equipment
title_short Deep Learning Image-Based Defect Detection in High Voltage Electrical Equipment
title_full Deep Learning Image-Based Defect Detection in High Voltage Electrical Equipment
title_fullStr Deep Learning Image-Based Defect Detection in High Voltage Electrical Equipment
title_full_unstemmed Deep Learning Image-Based Defect Detection in High Voltage Electrical Equipment
title_sort deep learning image-based defect detection in high voltage electrical equipment
publisher MDPI AG
series Energies
issn 1996-1073
publishDate 2020-01-01
description The increase in the internal temperature of high voltage electrical instruments is due to a variety of factors, particularly, contact problems; environmental factors; unbalanced loads; and cracks in the high voltage current transformers, voltage transformers, insulators, or terminal junctions. This increase in the internal temperature can cause unusual disturbances and damage to high voltage electrical equipment. Therefore, early prevention measures of thermal anomalies in equipment are necessary to prevent high voltage equipment failure that might shut down the whole grid system. In this article, we propose a novel non-destructive approach to defect analysis in high voltage equipment by taking advantage of the infrared thermography and the deep learning (DL) approach from the machine learning paradigm. The infrared images of the components were captured using the FLIR T630 without disturbing the operations of the power grid. In the first stage, rich features maps from the convolutional layers of the AlexNet pretrained model were extracted. After feature extraction, the random forest (RF) and support vector machines (SVM) were trained for learning of the defective and non-defective high voltage electrical equipment. In an experimental analysis, the RF optimally learned the separation between defective and non-defective equipment with greater than 96% accuracy, outperforming all the other comparative approaches for deep and nondeep features. The proposed approach based on the RF is reliable and shows its efficacy for fault detection in high voltage electrical equipment.
topic random forest
support vector machine
high voltage electrical equipment
infrared thermography
defect detection
thermal imaging
deep learning
url https://www.mdpi.com/1996-1073/13/2/392
work_keys_str_mv AT irfanullah deeplearningimagebaseddefectdetectioninhighvoltageelectricalequipment
AT rehanullahkhan deeplearningimagebaseddefectdetectioninhighvoltageelectricalequipment
AT fanyang deeplearningimagebaseddefectdetectioninhighvoltageelectricalequipment
AT lunchakornwuttisittikulkij deeplearningimagebaseddefectdetectioninhighvoltageelectricalequipment
_version_ 1725016053450276864