Metal-oxide surge arrester monitoring and diagnosis by self-organizing maps

Lira, George R. S.; Costa, Edson Guedes da; Ferreira, Tarso Vilela

doi:10.1016/j.epsr.2013.11.026

Cited by 14 publications

(11 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The adequacy of the SPD simulation results in this work was validated using the data for three low-voltage arresters provided by Lira et al [49], since this work mainly focuses on lightning protection based on SPDs and uses similar nonlinear arresters. The arresters were exposed to an 8/20 µs, 10 kA impulse current in PSCAD software.…”

Section: Simulation Results Of Casementioning

confidence: 73%

Mitigation of Lightning-Induced Transient Effects on a Hybrid Photovoltaic–Wind System Based on Lightning Protection Standards

et al. 2023

View full text Add to dashboard Cite

Installing surge protection devices in a hybrid photovoltaic (PV)–wind system is essential to guarantee the survival of the system’s components. If the surge arresters are connected without taking into account the recommendations given by standards, the equipment to be protected might be damaged despite the energy coordination of the arresters. In this study, nonlinear surge protective devices (SPDs) are designed for a multi-MW hybrid system based on lightning protection standards with optimised threat level ratings to investigate the mitigation of lightning transients to an acceptable level. The system is implemented using Power System Computer-Aided Design for Electromagnetic Transients including Direct Current (PSCAD/EMTDC) software. It comprises a 2 MW PV farm, a 2 MW wind farm, and a backup energy storage system (ESS), which are all connected to a 132 kV grid via a step-up transformer and a transmission line. The results were obtained at critical system nodes for two standard lightning current surges, i.e., 1/10 µs and 10/350 µs, considering two lightning strike point scenarios with and without a lightning protection system (LPS). The simulation results showed that the connected SPDs could successfully limit the transient overvoltage in the system to an acceptable level. The analysis in this work is crucial for designing, operating, and maintaining a hybrid PV–wind system. It can help to find the potential vulnerability areas within such a system and implement appropriate protection measures since there is no available lightning standard for such systems. Additionally, it assists the system operators in increasing the uptime and dependability of their RE systems, limiting expensive downtime and environmental effects while optimising energy output. Based on the results obtained, recommendations were made for lightning protection developers.

show abstract

Section: Simulation Results Of Casementioning

confidence: 73%

Mitigation of Lightning-Induced Transient Effects on a Hybrid Photovoltaic–Wind System Based on Lightning Protection Standards

et al. 2023

View full text Add to dashboard Cite

show abstract

“…4. Using equation [15] and Fig. 4, it can be calculated that the relative change of I r1 is 0.754, I r3 and I t3 have the same value of 0.578, while I t1 has the value of only 0.014.…”

Section: Change Of Mosa Conditionmentioning

confidence: 99%

“…Besides the listed methods, there are newly developed methods that are based on artificial intelligence [13][14][15][16][17][18]. Each of the mentioned methods, even though widely used and with undeniable advantages, shows a certain number of downsides as well.…”

Section: Introductionmentioning

confidence: 99%

Fuzzy expert system for metal-oxide surge arrester condition monitoring

Dobrić

Žarković

2020

Electr Eng

View full text Add to dashboard Cite

Metal-oxide surge arresters (MOSAs) play an important role in preventing outage situations and thus in preserving the reliability of electric power system. So far, many MOSA monitoring methods have been developed. These methods propose different indicators that are more or less reliable in MOSA monitoring and diagnostics. Another important aspect of these indicators is that each one of them can be determined with a certain estimation error. None of the indicators has been proved to be supreme. Nevertheless, under different conditions, the reliability of these indicators may vary. This paper presents an analysis methodology for reliability of MOSA indicators and proposes a fuzzy logic expert system that overcomes the problem of decision-making in the case when more than one indicator is available. The analysis and verification are done by computer simulations.

show abstract

“…The method used the values of mean, maximal, and harmonic elements of surge arrester leakage current regardless of the voltage level of the power network where they were installed. Lira et al [14] proposed a monitoring method based on the use of selforganizing maps (SOM) artificial neural networks to identify the harmonic features of the total leakage current for a metal-oxide surge arrester. The six fault types, including sealing loss, superficial pollution, varistor degradation, internal humidity, varistors displacement, and non-uniform voltage distribution, were built in the arresters to evaluate the technical capability.…”

Section: Introductionmentioning

confidence: 99%

Application of Deep Learning and Symmetrized Dot Pattern to Detect Surge Arrester Status

Wang

Hung

2022

Applied Sciences

View full text Add to dashboard Cite

Surge arresters primarily restrain lightning and switch surges in the power system to avoid damaging power equipment. When a surge arrester fails, it leads to huge damage to the power equipment. Therefore, this study proposed the application of a convolutional neural network (CNN) combined with a symmetrized dot pattern (SDP) to detect the state of the surge arrester. First, four typical fault types were constructed for the 18 kV surge arrester, including its normal state, aging of the internal valve, internal humidity, and salt damage to the insulation. Then, the partial discharge signal was measured and extracted using a high-speed data acquisition (DAQ) card, while a snowflake map was established by SDP for the features of each fault type. Finally, CNN was used to detect the status of the surge arrester. This study also used a histogram of oriented gradient (HOG) with support vendor machine (SVM), backpropagation neural network (BPNN), and k-nearest neighbors (KNN) for image feature extraction and identification. The result shows that the proposed method had the highest accuracy at 97.9%, followed by 95% for HOG + SVM, 94.6% for HOG + BPNN, and 91.2% for HOG + KNN. Therefore, the proposed method can effectively detect the fault status of surge arresters.

show abstract

Metal-oxide surge arrester monitoring and diagnosis by self-organizing maps

Cited by 14 publications

References 8 publications

Mitigation of Lightning-Induced Transient Effects on a Hybrid Photovoltaic–Wind System Based on Lightning Protection Standards

Mitigation of Lightning-Induced Transient Effects on a Hybrid Photovoltaic–Wind System Based on Lightning Protection Standards

Fuzzy expert system for metal-oxide surge arrester condition monitoring

Application of Deep Learning and Symmetrized Dot Pattern to Detect Surge Arrester Status

Contact Info

Product

Resources

About