Study on Partial Discharge Localization by Ultrasonic Measuring in Power Transformer Based on Particle Swarm Optimization

Luo, Rong; Kai, Bai; Chun, Deng; Liu, Shaoyu; Xu, Guo

doi:10.1109/ichve.2008.4774007

Cited by 8 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A hybrid algorithm which combines PSO with neural network was proposed in [11] to identify PD acoustic signals, a variant of PSO known as Evolutionary PSO was used to determine the relevant parameter of the radial basis function network. Another study in [12] shows that PSO outperforms other traditional algorithms for PD localization in power transformer as it is able to avoid divergent problems. In this work, three machine learning methods, Artificial Neural Network (ANN), Support Vector Machine (SVM) and Adaptive Neuro Fuzzy Inference System (ANFIS) were used as cable fault classification system by classifying PD patterns.…”

Section: Introductionmentioning

confidence: 99%

Optimization of Cable Fault Recognition System Using Particle Swarm Optimization

Raymond¹

2020

IJETER

View full text Add to dashboard Cite

In this paper, a Partial Discharge (PD) based cable fault recognition system has been constructed using Artificial Neural Network (ANN), Support Vector Machine (SVM) and Adaptive Neuro Fuzzy Inference System (ANFIS). The cable fault recognition system can perform well under noise free condition but endures performance deterioration when PD noise contamination is present. Particle Swarm Optimization (PSO) was used to enhance the performance of classifiers under noise contamination. A performance review has been done to compare the optimized and unoptimized cable fault recognition under noise contamination. Results show that PSO optimized cable fault recognition systems perform better compared to unoptimized cable fault recognition systems. Among the optimized cable fault recognition systems, ANN outperforms SVM and ANFIS.

show abstract

Section: Introductionmentioning

confidence: 99%

Optimization of Cable Fault Recognition System Using Particle Swarm Optimization

Raymond¹

2020

IJETER

View full text Add to dashboard Cite

show abstract

“…The phase resolved analysis investigates the PD pattern in relation to the variable frequency AC cycle (Cheng et al, 2008). The voltage phase angle is divided into small equal windows.…”

Section: Competitive Learning For Self Organizing Maps Used In Classimentioning

confidence: 99%

Explaining Diverse Application Domains Analyzed from Data Mining Perspective

Ochoa¹,

Margain²,

Jaramillo³

et al. 2012

Data Mining Applications in Engineering and Medicine

View full text Add to dashboard Cite

Comparison of Competitive Learning for SOM Used in Classification of Partial Discharge

Jaramillo-Vacio¹,

Ochoa

Ríos-Lira

2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Study on Partial Discharge Localization by Ultrasonic Measuring in Power Transformer Based on Particle Swarm Optimization

Cited by 8 publications

References 8 publications

Optimization of Cable Fault Recognition System Using Particle Swarm Optimization

Optimization of Cable Fault Recognition System Using Particle Swarm Optimization

Explaining Diverse Application Domains Analyzed from Data Mining Perspective

Comparison of Competitive Learning for SOM Used in Classification of Partial Discharge

Contact Info

Product

Resources

About