Assessment of PD severity in gas-insulated switchgear with an SSAE

Scientific partial discharge (PD) severity evaluation is highly important to the safe operation of gas-insulated switchgear. However, describing PD severity with only a few statistical features such as discharge time and discharge amplitude is unreliable. Hence, a deep-learning neural network model...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IET science, measurement & technology Ročník 11; číslo 4; s. 423 - 430
Hlavní autoři:	Tang, Ju, Jin, Miao, Zeng, Fuping, Zhang, Xiaoxing, Huang, Rui
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	The Institution of Engineering and Technology 01.07.2017
Témata:	computerised instrumentation deep‐learning neural network model discharge amplitude discharge time encoding feature extraction gas insulated switchgear learning (artificial intelligence) neural nets partial discharge measurement partial discharge severity assessment PD severity assessment Research Article soft‐max classifier SSAE stacked sparse autoencoder statistical analysis supervised fine‐tuning method support vector machine algorithm unsupervised greedy layer‐wise pre‐training method SSAE partial discharge severity assessment deep-learning neural network model unsupervised greedy layer-wise pre-training method computerised instrumentation encoding soft-max classifier gas-insulated switchgear discharge amplitude partial discharge measurement stacked sparse autoencoder support vector machine algorithm feature extraction discharge time PD severity assessment statistical analysis learning (artificial intelligence) gas insulated switchgear neural nets supervised fine-tuning method
ISSN:	1751-8822, 1751-8830
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Scientific partial discharge (PD) severity evaluation is highly important to the safe operation of gas-insulated switchgear. However, describing PD severity with only a few statistical features such as discharge time and discharge amplitude is unreliable. Hence, a deep-learning neural network model called stacked sparse auto-encoder (SSAE) is proposed to realise feature extraction from the middle layer with a small number of nodes. The output feature that is almost similar to the input PD information is produced in the model. The features extracted from PD data are then fed into a soft-max classifier to be classified into one of four defined PD severity states. In addition, unsupervised greedy layer-wise pre-training and supervised fine-tuning are utilised to train the SSAE network during evaluation. Results of testing and simulation analysis show that the features extracted by the SSAE model effectively characterise PD severity. The performance of the SSAE model, which possesses an average assessment accuracy of up to 92.2%, is better than that of the support vector machine algorithm based on statistical features. According to the tested number of SSAE layers and features and the training sample size, the SSAE model possesses good expansibility and can be useful in practical applications.
ISSN:	1751-8822 1751-8830
DOI:	10.1049/iet-smt.2016.0326