Cable incipient fault identification using restricted Boltzmann machine and stacked autoencoder

Cable incipient fault is an intermittent arc fault, and may evolve into a permanent fault. Due to the short duration of the fault, the conventional overcurrent protection device cannot detect it. A cable incipient fault identification method is proposed in this study, using restricted Boltzmann mach...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IET generation, transmission & distribution Ročník 14; číslo 7; s. 1242 - 1250
Hlavní autoři:	Wang, Ying, Lu, Hong, Xiao, Xianyong, Yang, Xiaomei, Zhang, Wenhai
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	The Institution of Engineering and Technology 14.04.2020
Témata:	arcs (electric) backpropagation belief networks Boltzmann machines cable incipient fault identification method compressed data conventional overcurrent protection device disturbance current waveforms data fault diagnosis feature extraction high identification accuracy identification result intermittent arc fault layer‐by‐layer pre‐training learning (artificial intelligence) neural nets overcurrent protection permanent fault power distribution faults RBM Research Article restricted Boltzmann machine SAE network stacked autoencoder compressed data SAE network fault diagnosis disturbance current waveforms data intermittent arc fault identification result stacked autoencoder conventional overcurrent protection device arcs (electric) power distribution faults layer-by-layer pre-training high identification accuracy Boltzmann machines feature extraction overcurrent protection backpropagation restricted Boltzmann machine permanent fault belief networks learning (artificial intelligence) cable incipient fault identification method RBM neural nets
ISSN:	1751-8687, 1751-8695
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Cable incipient fault is an intermittent arc fault, and may evolve into a permanent fault. Due to the short duration of the fault, the conventional overcurrent protection device cannot detect it. A cable incipient fault identification method is proposed in this study, using restricted Boltzmann machine (RBM) and stacked autoencoder (SAE). Firstly, disturbance current waveforms data is effectively compressed by RBM, which can improve analysis efficiency and obtain the shallow features of the data. Then, the compressed data is used as the input of SAE, and the optimal network parameters are obtained through layer-by-layer pre-training and fine-tuning. Finally, a well-trained SAE network is used to learn deep features from the input data to identify cable incipient fault, and softmax outputs identification result. In addition, the performance of the proposed method is compared with other methods. The accuracy of the proposed method is 98.33/95.62% for simulated data/measured data, and is 1.66/1.09%, 3.33/1.76%, 17.31/28.48% and 40.17/46.1% higher than the accuracies of convolutional neural network, deep belief network, random forest and back propagation neural network, respectively. The results show that the proposed method has high identification accuracy and feasibility.
ISSN:	1751-8687 1751-8695
DOI:	10.1049/iet-gtd.2019.0743