Identification of Acoustic Signals of Internal Electric Discharges on Glass Insulator under Variable Applied Voltage

Al-geelani, Nasir A.; Piah, M. A. M.; Saeh, Ibrahim; Othman, N. A.; Muhamedin, F. L.; Kasri, N. F.

doi:10.11591/ijece.v6i2.pp827-834

Cited by 7 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among non-intrusive sensors, acoustic emission (AE) sensors are mostly preferred for detecting PD, corona, and surface discharges. Additionally, there are studies in which AE sensor is used to detect internal discharges on controlled samples [4]. RF antennas are also capable of detecting different types of defects like AE sensors.…”

Section: Introductionmentioning

confidence: 99%

A Study on the Ability of Different Non-Intrusive Sensors for Diagnosing Outdoor Insulator Defects

Kumru

Lutfi

El-Hag

et al. 2023

2023 IEEE Electrical Insulation Conference (EIC)

View full text Add to dashboard Cite

Insulators' failures caused by any type of defect may result in serious technical and economic losses. In particular, contamination flashovers due to excessive pollution and humidity are one of the main problems encountered in power systems. Moreover, other types of defects like surface crack and internal void are other common examples of outdoor insulator defects that may lead to insulator failure. In this regard, detecting the defect using a non-intrusive method is important in terms of energy continuity and monitoring efficiency. Both vision (regular, IR and UV camera) and emission (RF, ultrasonic, and acoustic) based sensors have been deployed in the field to detect these defects. It has been reported that each sensor has certain pros and cons in terms of its ability to detect the different defects. Therefore, it is essential to investigate and compare the sensing performance of non-intrusive sensors for different defects. In this study, an ultrasonic sensor (20 -100 kHz), an RF antenna (0.53 -3 GHz) and an IR camera were used to detect dry band arcing, corona and surface discharge. All three sensors along with the standard partial discharge measurement system were used simultaneously for each measurement. The results show that sensing performance of the three sensors varies depending on the defect type.

show abstract

Section: Introductionmentioning

confidence: 99%

A Study on the Ability of Different Non-Intrusive Sensors for Diagnosing Outdoor Insulator Defects

Kumru

Lutfi

El-Hag

et al. 2023

2023 IEEE Electrical Insulation Conference (EIC)

View full text Add to dashboard Cite

show abstract

Vibration data feature extraction and deep learning-based preprocessing method for highly accurate motor fault diagnosis

Jang

Noh

Kim³

et al. 2022

Journal of Computational Design and Engineering

View full text Add to dashboard Cite

The environmental regulations on vessels being strengthened by the International Maritime Organization (IMO) has led to a steady growth in the eco-friendly ship market. Related research is being actively conducted, including many studies on the maintenance and predictive maintenance of propulsion systems (including electric motors, rotating bodies) in electric propulsion vessels. The present study intends to enhance the artificial intelligence-based failure diagnosis rate for electric propulsion vessel propulsion systems. To verify the proposed AI-based failure diagnosis algorithm for electric motors, this study utilized the vibration data of mechanical equipment (electric motors) in an urban railway station. Securing and preprocessing high-quality data is crucial for improving the failure diagnosis rate, in addition to the performance of the diagnostic algorithm. However, the conventional wavelet transform method, which is generally used for machine signal processing, has a disadvantage of data loss when the data distribution is abnormal or skewed. This study, to overcome this shortcoming, proposes an AI-based DAE method that can remove noise while maintaining data characteristics for signal processing of mechanical equipment. This study preprocessed vibration data by using the DAE method, and extracted significant features from the data through the feature extraction method. The extracted features were utilized to train the one-class support vector machine model and to allow the model to diagnose the failure. Finally, the F-1 score was calculated by using the failure diagnosis results, and the most meaningful feature extraction method was determined for the vibration data. In addition, this study compared and evaluated the preprocessing performance based on the DAE and the wavelet transform methods.

show abstract

Application of Machine Learning in Discharge Classification

Brar

El-Hag

2020

2020 IEEE Conference on Electrical Insulation and Dielectric Phenomena (CEIDP)

View full text Add to dashboard Cite

Identification of Acoustic Signals of Internal Electric Discharges on Glass Insulator under Variable Applied Voltage

Cited by 7 publications

References 12 publications

A Study on the Ability of Different Non-Intrusive Sensors for Diagnosing Outdoor Insulator Defects

A Study on the Ability of Different Non-Intrusive Sensors for Diagnosing Outdoor Insulator Defects

Vibration data feature extraction and deep learning-based preprocessing method for highly accurate motor fault diagnosis

Application of Machine Learning in Discharge Classification

Contact Info

Product

Resources

About