An intelligent system for acoustic inspection of outdoor insulators

El-Hag, Ayman H.; Mukhopadhyay, Shayok; Al-Ali, Kamil; Al-Saleh, AbdulRahman

doi:10.1109/catcon.2017.8280197

Cited by 13 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In general, the literature shows an inadequate amount of work that has been devoted to train deep network architectures to classify and predict pollution levels non-intrusively. All the work done is either focused on applying deep learning models to intrusive measurement techniques [130,131] or applying classical machine learning using non-intrusive techniques [132][133][134][135]. More research is needed to combine deep learning models with non-intrusive approaches for monitoring, particularly those based on radiation type sensors.…”

Section: Contamination Diagnosismentioning

confidence: 99%

Deep Learning in High Voltage Engineering: A Literature Review

et al. 2022

Self Cite

View full text Add to dashboard Cite

Condition monitoring of high voltage apparatus is of much importance for the maintenance of electric power systems. Whether it is detecting faults or partial discharges that take place in high voltage equipment, or detecting contamination and degradation of outdoor insulators, deep learning which is a branch of machine learning has been extensively investigated. Instead of using hand-crafted manual features as an input for the traditional machine learning algorithms, deep learning algorithms use raw data as the input where the feature extraction stage is integrated in the learning stage, resulting in a more automated process. This is the main advantage of using deep learning instead of traditional machine learning techniques. This paper presents a review of the recent literature on the application of deep learning techniques in monitoring high voltage apparatus such as GIS, transformers, cables, rotating machines, and outdoor insulators.

show abstract

Section: Contamination Diagnosismentioning

confidence: 99%

Deep Learning in High Voltage Engineering: A Literature Review

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Insulators are essential components of high-voltage transmission lines, providing insulation and mechanical support. Insulator faults are primarily caused by high leakage current and harsh working conditions [ 1 ], jeopardizing the stability of transmission lines and posing safety risks. Therefore, regular inspection of insulator faults is of significant importance for ensuring the stability of the electrical power system [ 2 ].…”

Section: Introductionmentioning

confidence: 99%

Insulator Defect Detection Based on ML-YOLOv5 Algorithm

Wang,

Zhai,

et al. 2023

Sensors

View full text Add to dashboard Cite

To address the challenges of balancing accuracy and speed, as well as the parameters and FLOPs in current insulator defect detection, we propose an enhanced insulator defect detection algorithm, ML-YOLOv5, based on the YOLOv5 network. The backbone module incorporates depthwise separable convolution, and the feature fusion C3 module is replaced with the improved C2f_DG module. Furthermore, we enhance the feature pyramid network (MFPN) and employ knowledge distillation using YOLOv5m as the teacher model. Experimental results demonstrate that this approach achieved a 46.9% reduction in parameter count and a 43.0% reduction in FLOPs, while maintaining an FPS of 63.6. It exhibited good accuracy and detection speed on both the CPLID and IDID datasets, making it suitable for real-time inspection of high-altitude insulator defects.

show abstract

“…A ocorrência do fenômeno de DPs está associada ao aparecimento de diversos tipos de ondas sonoras (emissões acústicas), ondas eletromagnéticas e sinais de corrente de alta frequência. Dessa forma, diferentes sensores e métodos podem ser utilizados para monitorar as DPs (El-Hag et al, 2017). Os métodos elétricos de detecção são largamente utilizados na indústria e em laboratórios de ensaios para a determinação de DPs em dispositivos submetidos à alta tensão.…”

Section: Introductionunclassified

Medição de Emissões Acústicas Provenientes de Descargas Parciais em Sistema Ponta-Plano e Correlação com o Método Elétrico

Morais

Assis

Nunes

et al. 2022

Proceedings IX Simpósio Brasileiro De Sistemas Elétricos

View full text Add to dashboard Cite

The evaluation of the operating condition of medium and high voltage equipment based on diagnosis of Partial Discharges (PDs), obtained from the measurement of ultrasonic acoustic emissions, has been the object of analysis of many works available in the technical literature. In this sense, this work presents a practical investigation of the occurrence of PDs, detected through acoustic and electrical methods, in a point-flat system subjected to different voltage levels, gaps and environmental conditions. This methodology is adopted to correlate the measured data with the acoustic (unconventional) and electrical (conventional) methods, in order to demonstrate the effectiveness of the former and contribute to obtaining diagnoses with high precision and reliability. The occurrence of PDs signatures, in the time domain for the acoustic and electrical methods, were obtained for the scenarios under analysis, both indicating, with good approximation, the incidence of the phenomenon. The analysis in the frequency domain of the results acquired with the acoustic method also corroborated the diagnosis of PDs in the evaluated scenarios.Resumo: A avaliação da condição de operação de equipamentos de média e alta tensão com base no diagnóstico de Descargas Parciais (DPs), obtidos a partir da medição de emissões acústicas ultrassônicas, vem sendo objeto de pesquisa no Brasil e no exterior. Nesse sentido, este trabalho apresenta os resultados de uma investigação, em laboratório, de DPs detectadas por meio dos métodos acústico e elétrico, em um sistema ponta-plano submetido a diferentes níveis de tensão, espaçamento e condições ambientais. A metodologia apresentada neste artigo foi adotada de modo a favorecer a o estabelecimento de uma correlação entre os dados medidos com os métodos acústico (não convencional) e elétrico (convencional), a fim de demonstrar a efetividade do primeiro e contribuir para a obtenção de diagnósticos com elevada precisão e confiabilidade. As formas de onda de DPs, no domínio do tempo para os métodos acústico e elétrico, foram obtidas para os cenários sob análise, ambos indicando a existência do fenômeno com boa aproximação. Uma análise no domínio da frequência dos sinais aquisitados com o método acústico corroboraram também com os diagnósticos de DPs, para os cenários avaliados.

show abstract

An intelligent system for acoustic inspection of outdoor insulators

Cited by 13 publications

References 6 publications

Deep Learning in High Voltage Engineering: A Literature Review

Deep Learning in High Voltage Engineering: A Literature Review

Insulator Defect Detection Based on ML-YOLOv5 Algorithm

Medição de Emissões Acústicas Provenientes de Descargas Parciais em Sistema Ponta-Plano e Correlação com o Método Elétrico

Contact Info

Product

Resources

About