Transmission Line Fault Classification Based on Dynamic State Estimation and Support Vector Machine

Xie, Jiahao; Meliopoulos, A. P. Sakis; Xie, Boqi

doi:10.1109/naps.2018.8600658

“…The acquisition rates less than 2 kHz could negatively impact the capturing of real-time picture of a transmission line due to low refresh rate, while the acquisition rates more than 5 kHz gets limited due to the increased need for computation. The measurement vector the voltages and currents from the terminals of the transmission line and is represented as z in (7).…”

Section: A Application Of Advsensmentioning

confidence: 99%

“…The detailed concept of this scheme along with its capabilities to improve zone protection, detection, and self-healing against hidden failures are discussed in [2]. The DSE-based protection is based on a generalized concept and has been applied to the protection of series compensated transmission line [6], transmission line fault classification [7], and several other components.…”

Section: Introductionmentioning

confidence: 99%

Transmission Line Protection Using Dynamic State Estimation and Advanced Sensors: Experimental Validation

Srivastava

¹

,

Tuấn

²

,

Steen

³

et al. 2023

IEEE Trans. Power Delivery

View full text Add to dashboard Cite

This paper presents the experimental validation of a protection scheme for a transmission line based on dynamic state estimation along with the practical application of advanced sensors in this protection scheme. The scheme performs dynamic state estimation with high-frequency measurements provided by the sensors, assesses the operating condition (i.e., health) of the transmission line in real-time, and thereby determines the tripping signal whenever a fault is detected. The validation was carried out in two steps, first with simulation studies for a three-phase fault and then with the experimental implementation using a physical scaled-down model of a power system consisting of transmission lines, transformers, and loads. The simulation and validation results have shown that the scheme performs adequately in both normal and fault conditions. In the fault case with the experimental setup, the scheme could correctly detect the fault and send the trip signal to the line's circuit breakers with a total fault clearing time of approximately 65 milliseconds which is comparable to conventional protection methods. The average processing time for a measurement sample block is 12.5 milliseconds. The results demonstrate that this scheme and the sensors would work for transmission line protection which can avoid relay coordination and settings issues.

show abstract

“…The acquisition rates less than 2 kHz could negatively impact the capturing of real-time picture of a transmission line due to low refresh rate, while the acquisition rates more than 5 kHz gets limited due to the increased need for computation. The measurement vector includes the voltages and currents from the terminals of the transmission line and is represented as z in (7).…”

Section: Application Of Advsensmentioning

confidence: 99%

Transmission Line Protection Using Dynamic State Estimation and Advanced Sensors: Experimental Validation

Srivastava,

Tuan,

Steen

et al. 2023

2023 IEEE Power &Amp; Energy Society General Meeting (PESGM)

0

View full text Add to dashboard Cite

This paper presents the experimental validation of a protection scheme for a transmission line based on dynamic state estimation along with the practical application of advanced sensors in this protection scheme. The scheme performs dynamic state estimation with high-frequency measurements provided by the sensors, assesses the operating condition (i.e., health) of the transmission line in real-time, and thereby determines the tripping signal whenever a fault is detected. The validation was carried out in two steps, first with simulation studies for a three-phase fault and then with the experimental implementation using a physical scaled-down model of a power system consisting of transmission lines, transformers, and loads. The simulation and validation results have shown that the scheme performs adequately in both normal and fault conditions. In the fault case with the experimental setup, the scheme could correctly detect the fault and send the trip signal to the line's circuit breakers with a total fault clearing time of approximately 65 milliseconds which is comparable to conventional protection methods. The average processing time for a measurement sample block is 12.5 milliseconds. The results demonstrate that this scheme and the sensors would work for transmission line protection which can avoid relay coordination and settings issues.

show abstract

“…This transition facilitates the seamless integration of various distributed energy resources such as solar, wind, and tidal energy, along with advanced metering and communication infrastructures. In transmission lines, occurrences of power outages are significantly attributed to unpredictable and irregular faults [1]- [5]. Power system faults are unavoidable and cannot be ignored.…”

Section: Introduction a Research Motivationmentioning

confidence: 99%

Fault Detection and Classification in Ring Power System With DG Penetration Using Hybrid CNN-LSTM

Alhanaf,

Farsadi,

Balik

2024

IEEE Access

7

0

View full text Add to dashboard Cite

A modern electric power system integrated with advanced technologies such as sensors and smart meters is referred to as a "smart grid," aimed at enhancing electrical power delivery efficiency and reliability. However, fault location and prediction can become challenging when dynamic fault currents from renewable energy sources are present.To address these challenges, three unique deep learning models that make use of Deep Neural Networks (DNN) have been proposed. CNN, LSTM, and Hybrid CNN-LSTM are deep learning models. Line faulty identification (LF), fault classification (FC), and fault location estimate (FL) are the subjects on which they concentrate. These models analyze data gathered both pre and post faults occur in order to enhance decision making. Signals including the voltage and current were fed into these models from many different locations across the test networks. Once the 1D CNN has extracted characteristics from the gathered signals, LSTM uses these features to make accurate estimations and identify faults. Complex data are compatible with this method in terms of optimal outcomes. Using training and testing data from transmission line failure simulations, the proposed approaches were evaluated on the IEEE 6-bus and IEEE 9-bus systems. The tests encompassed a range of fault classes, locations, and ground fault resistances at various locations. Distributed Generator (DG) resources were additionally included in the system architecture and changes in the topology of the networks were considered in terms of location and number of DG resources .The results demonstrated that the proposed algorithms outperformed contemporary technologies in terms of detection, classification, and location accuracy. They demonstrated high accuracy and robustness in their performance.

show abstract

Transmission Line Fault Classification Based on Dynamic State Estimation and Support Vector Machine

Cited by 16 publications

References 8 publications

Transmission Line Protection Using Dynamic State Estimation and Advanced Sensors: Experimental Validation

Transmission Line Protection Using Dynamic State Estimation and Advanced Sensors: Experimental Validation

Transmission Line Protection Using Dynamic State Estimation and Advanced Sensors: Experimental Validation

Fault Detection and Classification in Ring Power System With DG Penetration Using Hybrid CNN-LSTM

Contact Info

Product

Resources

About