Switchgear Condition Assessment and Lifecycle Management: Standards, Failure Statistics, Condition Assessment, Partial Discharge Analysis, Maintenance Approaches, and Future Trends

The damaging effects of corona faults have made them a major concern in metal-clad switchgear, requiring extreme caution during operation. Corona faults are also the primary cause of flashovers in medium-voltage metal-clad electrical equipment. The root cause of this issue is an electrical breakdown of the air due to electrical stress and poor air quality within the switchgear. Without proper preventative measures, a flashover can occur, resulting in serious harm to workers and equipment. As a result, detecting corona faults in switchgear and preventing electrical stress buildup in switches is critical. Recent years have seen the successful use of Deep Learning (DL) applications for corona and non-corona detection, owing to their autonomous feature learning capability. This paper systematically analyzes three deep learning techniques, namely 1D-CNN, LSTM, and 1D-CNN-LSTM hybrid models, to identify the most effective model for detecting corona faults. The hybrid 1D-CNN-LSTM model is deemed the best due to its high accuracy in both the time and frequency domains. This model analyzes the sound waves generated in switchgear to detect faults. The study examines model performance in both the time and frequency domains. In the time domain analysis (TDA), 1D-CNN achieved success rates of 98%, 98.4%, and 93.9%, while LSTM obtained success rates of 97.3%, 98.4%, and 92.4%. The most suitable model, the 1D-CNN-LSTM, achieved success rates of 99.3%, 98.4%, and 98.4% in differentiating corona and non-corona cases during training, validation, and testing. In the frequency domain analysis (FDA), 1D-CNN achieved success rates of 100%, 95.8%, and 95.8%, while LSTM obtained success rates of 100%, 100%, and 100%. The 1D-CNN-LSTM model achieved a 100%, 100%, and 100% success rate during training, validation, and testing. Hence, the developed algorithms achieved high performance in identifying corona faults in switchgear, particularly the 1D-CNN-LSTM model due to its accuracy in detecting corona faults in both the time and frequency domains.

Section: Theoretical Study and Methodsmentioning

confidence: 99%

“…Furthermore, switchgear is typically classified into low, medium, and high voltage groups and is primarily constructed using insulating mediums such as air or oil [ 3 ]. It is crucial to closely monitor the performance and condition of switchgear during operation.…”

Section: Introductionmentioning

confidence: 99%

Detection of Corona Faults in Switchgear by Using 1D-CNN, LSTM, and 1D-CNN-LSTM Methods

Alsumaidaee

Yaw

Koh

et al. 2023

“…Considering the various phenomena that manifest the symptoms of failure modes in switchgear, such as the increase in temperature as the electrical connections deteriorate, the effect of increased humidity on the deterioration of insulation, and the development of partial discharges, which are also indicative of various deteriorations of switchgear operation, the need to measure various parameters is obvious. For example, a study was performed to analyze failure phenomena and characteristics, while also highlighting the complex relationships among cause, effect, and failure modes in switchgear [ 28 ].…”

Section: Expansion Of the Types Of Measurement Sensorsmentioning

confidence: 99%

Switchgear Digitalization—Research Path, Status, and Future Work

Kaštelan

Vujović

Krčum

et al. 2022

To keep pace with global energy efficiency trends and, in particular, emission reduction targets in the maritime sector, both onshore and maritime power distribution systems need to be adapted to the relevant new technologies and concepts. As an important link in the distribution chain, medium-voltage switchgear (MV) is expected to be stable and reliable while operating as efficiently as possible. Failures of MV equipment, while rare because the equipment must be safe to handle and use, have far-reaching consequences. The consequences of such failures, whether to the shore or marine power system, present risks to the entire power plant, so an accurate assessment of equipment condition is required to identify potential failures early. The solution is an emerging concept of digital switchgear, where the implementation of sensor technology and communication protocols enables effective condition monitoring, and the creation of a database that, when combined with machine learning algorithms, enables predictive maintenance and/or fault detection. This paper presents, step by step, the previous challenges, the current research (divided into predictive maintenance, condition monitoring, and fault detection categories), and the future directions in this field. The use of artificial intelligence is discussed to eliminate the disadvantage of manually interpreting operational data, and recommendations for future work are formulated, such as the need to standardize test procedures and data sets to train and compare different algorithms before they are used in practice.

“…High-voltage switchgear is an important type of transmission and distribution equipment, and its operational safety directly affects the reliability of the power system [ 1 ]. Partial discharge is the main cause of insulation deterioration and insulation failure of switchgear [ 2 ].…”

Section: Introductionmentioning

confidence: 99%

Analysis of Electromagnetic Properties of New Graphene Partial Discharge Sensor Electrode Plate Material

Zhang

2022

Advanced sensing and measurement technology is the key to realizing the transparent power grid and electric internet of things. Meanwhile, sensors, as an indispensable part of the smart grid, can monitor, collect, process, and transmit various types of data information of the power system in real-time. In this way, it is possible to further control the power system. Among them, partial discharge (PD) sensors are of great importance in the fields of online monitoring of insulation condition, intelligent equipment control, and power maintenance of power systems. Therefore, this paper intends to focus on advanced sensing materials and study new materials for the improvement for partial discharge sensors. As two-dimensional material, graphene is introduced. The electromagnetic properties of graphene partial discharge sensor electrode plate material are analyzed theoretically. By studying the influence of different chemical potential, relaxation time, temperature, and frequency, we obtain the changing curve of conductivity, dielectric constant, and refractive index. A linear regression model based on the least-squares method was developed for the three electromagnetic properties. Finally, the simulation and experiment verified that the graphene partial discharge sensor has better absorption of the partial discharge signal. This study can apply to the design of graphene partial discharge sensors.