Insulator fault diagnosis based on multi-objectives multilevel thresholding method and boost particle swarm optimization

Fault diagnosis of the insulator is significant to keep the stable operation of the power systems. However, the fault point of insulator is hard to detect which makes the fault diagnosis accuracy is low. To fill this gap, a boost particle swarm optimization (PSO) is proposed for the threshold select...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of information technology (Singapore. Online) Jg. 17; H. 7; S. 4029 - 4050
Hauptverfasser: Shuai, Wang, Yusof, Yuhanis
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Singapore Springer Nature Singapore 01.09.2025
Springer Nature B.V
Schlagworte:
Algorithms
Artificial Intelligence
Color imagery
Computer Imaging
Computer Science
Fault diagnosis
Genetic algorithms
Image Processing and Computer Vision
Image segmentation
Infrared imagery
Machine Learning
Methods
Neighborhoods
Optimization algorithms
Original Research
Pareto optimum
Particle swarm optimization
Pattern Recognition and Graphics
Satellite imagery
Signal to noise ratio
Software Engineering
Vision
Infrared Image
Particle swarm optimization
Insulator diagnostic
Multi objectives optimization
ISSN:2511-2104, 2511-2112
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Fault diagnosis of the insulator is significant to keep the stable operation of the power systems. However, the fault point of insulator is hard to detect which makes the fault diagnosis accuracy is low. To fill this gap, a boost particle swarm optimization (PSO) is proposed for the threshold selection of multi-level threshold image segmentation. The adaptive weight and tent chaotic map are used to boost the optimal ability of PSO. And the nine-dimension Otsu (9DOtsu) fitness function is proposed to obtain the optimal threshold of three channel of color images. Moreover, the 9DOtsu converts into multi object problems (MOPs). Finally, the BPSO optimizes 9DOtsu and obtains the fault state of the insulator. The satellite images, nature images and complex insulator infrared images are selected as the test images. Experimental results illustrate that BPSO obtains an excellent performance with compared algorithms in peak signal to noise ratio (PSNR), feature similarity (FSIM), Hypervolume (HV) and CPU time. In addition, the fault diagnosis accuracy of the proposed method has significant improvement than other algorithms. The proposed method obtains fault state of the insulator to ensure the stable operation of power systems.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2511-2104
2511-2112
DOI:10.1007/s41870-023-01243-5