High impedance fault detection and identification based on pattern recognition of phase displacement computation

Ali, Mohammed A. H.; Bakar, Ab Halim Abu; Tan, Chia Kwang; Arof, Hamzah; Mokhlis, Hazlie

doi:10.1002/tee.22600

Cited by 7 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A recurring concern over the years has been that most of the proposed techniques and methodologies are capable to detect HIFs, but they often confuse fault with normal system events, generating false positives, usually in situations such as switching capacitor banks and energizing transformers [6], [13], [14]. Therefore, it is possible to state that an adequate and permanent solution for HIF detection is still lacking, although many attempts have been made by the scientific community.…”

Section: Introductionmentioning

confidence: 99%

Artificial Neural Networks: Modeling and Comparison to Detect High Impedance Faults

Diefenthäler,

Sausen,

De Campos

et al. 2023

IEEE Access

View full text Add to dashboard Cite

High impedance faults constitute one of the biggest challenges in electrical power systems. In overhead distribution systems, faults are caused by tree branches that touch the electrical grid or by the rupture of energized conductors on low conductivity soils. They are also known as low-current faults, which are not detected by conventional protection systems, compromising the quality of the power supply and causing hazardous risks to the electrical system. This paper aims to address the problem of high impedance faults detection using Artificial Neural Networks: two Multi Layer Perceptron networks, being one Neural Pattern Recognition and another Neural Fitting, and a Convolutional Neural Network. The neural networks are trained and analyzed in scenarios based on a medium-voltage distribution grid model, located in the Basque Country, Spain. The network topologies are implemented, repeatedly trained considering multiple architectures, and validated in other scenarios with different location, time, and duration of the fault using the Matlab software. After, the criteria of accuracy, reliability, security, safety and sensitivity are evaluated. At last, a comparative analysis between them is carried out, and from the results obtained, a superior performance of the Convolutional Neural Network in compared to the Multi Layer Perceptron networks is observed.

show abstract

Section: Introductionmentioning

confidence: 99%

Artificial Neural Networks: Modeling and Comparison to Detect High Impedance Faults

Diefenthäler,

Sausen,

De Campos

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…However, neural network cannot learn during their online operation and wavelet require a deep knowledge of high-low filters and mother wavelet. Pattern recognition has combined with the wavelet transform and then used for detecting the HIF in [24], usually WT used for extracting the fault feature and pattern recognition used for classing the fault [25]. As well as, in [26] Stack-well transform (ST) is used for extracting the fault feature and then pattern recognition for assessing HIF.…”

Section: Introductionmentioning

confidence: 99%

High Impedance Fault Identification in TCSC-Compensated Power Transmission Lines

Musa¹

2021

FJES

View full text Add to dashboard Cite

The conventional distance relaying scheme performs poorly under the presence of Thyristors-controlled series capacitors “TCSC”, and during the high impedance fault “HIF”. TCSC provide a variable impedance during an internal/external fault and HIF is undetectable by the conventional overcurrent relaying due to low-current amplitude with non-linear behavior. Therefore, this paper presents a new Method for identifying the high impedance fault in TCSC-compensated transmission line. It is use the square error ration of the current signals during the fault period and current signals during the safe operating period for extracting the fault. The cumulative sum is being used for enlarging the fault features and then output index is obtained in order to perform the high impedance fault. The proposed method has been tested under different fault circumstances such as multiple fault locations, and multiple fault inception time. Moreover, fault happened nearby the terminal, power flow change, and faults in the presence of noise are also being considered. The test results have shown that the proposed method is good in term of time response, and then it is more appropriate for high impedance fault in TCSC-compensated power line.

show abstract

Flexible and robust communication-assisted protection strategy for distribution networks based on comprehensive feature recognition

Cai

Ping

et al. 2021

International Journal of Electrical Power & Energy Systems

View full text Add to dashboard Cite

High impedance fault detection and identification based on pattern recognition of phase displacement computation

Cited by 7 publications

References 20 publications

Artificial Neural Networks: Modeling and Comparison to Detect High Impedance Faults

Artificial Neural Networks: Modeling and Comparison to Detect High Impedance Faults

High Impedance Fault Identification in TCSC-Compensated Power Transmission Lines

Flexible and robust communication-assisted protection strategy for distribution networks based on comprehensive feature recognition

Contact Info

Product

Resources

About