Intelligent Sensors for dc Fault Location Scheme Based on Optimized Intelligent Architecture for HVdc Systems

We develop a probabilistic model for determining the location of dc-link faults in MT-HVdc networks using discrete wavelet transforms (DWTs), Bayesian optimization, and multilayer artificial neural networks (ANNs) based on local information. Likewise, feedforward neural networks (FFNNs) are trained...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Sensors (Basel, Switzerland) Ročník 22; číslo 24; s. 9936
Hlavní autori: Yousaf, Muhammad Zain, Tahir, Muhammad Faizan, Raza, Ali, Khan, Muhammad Ahmad, Badshah, Fazal
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Switzerland MDPI AG 16.12.2022
MDPI
Predmet:
Accuracy
Algorithms
Back propagation
Bayes Theorem
Bayesian optimization
Bias
Computer Simulation
Electricity distribution
Levenberg–Marquardt backpropagation
Localization
modular multilevel converter
Neural networks
Neural Networks, Computer
Power
protection sensor
Sensors
Signal processing
Time
Wavelet transforms
modular multilevel converter
Levenberg–Marquardt backpropagation
protection sensor
Bayesian optimization
ISSN:1424-8220, 1424-8220
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:We develop a probabilistic model for determining the location of dc-link faults in MT-HVdc networks using discrete wavelet transforms (DWTs), Bayesian optimization, and multilayer artificial neural networks (ANNs) based on local information. Likewise, feedforward neural networks (FFNNs) are trained using the Levenberg–Marquardt backpropagation (LMBP) method, which multi-stage BO optimizes for efficiency. During training, the feature vectors at the sending terminal of the dc link are selected based on the norm values of the observed waveforms at various frequency bands. The multilayer ANN is trained using a comprehensive set of offline data that takes the denoising scheme into account. This choice not only helps to reduce the computational load but also provides better accuracy. An overall percentage error of 0.5144% is observed for the proposed algorithm when tested against fault resistances ranging from 10 to 485 Ω. The simulation results show that the proposed method can accurately estimate the fault site to a precision of 485 Ω and is more robust.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1424-8220
1424-8220
DOI:10.3390/s22249936