DA-WGAN-SVM-based hydroelectric generating set small sample fault diagnosis method

A hydroelectric generating set small sample fault diagnosis method based on DA-WGAN-SVM comprises the steps of firstly performing generative adversarial network, Wasserstein generative adversarial network and differentiable data enhancement, and then performing fault analysis and diagnosis based on...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: WANG WEIYU, OU SHI, HYUNG GUN-MO, MO FAN, LUO LIJUN, WU SHENGJIN, WEI JIADA, KANG ZHIYUAN, GAO JINLIN, LAI XINGQUAN, WANG SIJIA, LIU YU, MA TENGFEI, TAN WENSHENG
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A hydroelectric generating set small sample fault diagnosis method based on DA-WGAN-SVM comprises the steps of firstly performing generative adversarial network, Wasserstein generative adversarial network and differentiable data enhancement, and then performing fault analysis and diagnosis based on a hydroelectric generating set small sample by using the obtained data, and specifically comprises seven steps for fault analysis and diagnosis. On the basis of a small sample of a hydroelectric generating set, firstly, data enhancement is carried out on an existing training data set by utilizing a micro-enhancement generative adversarial network, the training data set is expanded, and then feature vector extraction is carried out on the data set; and finally, a support vector machine classifier is used for classifying the expanded data set so as to realize fault classification of the hydroelectric generating set, and compared with most traditional methods based on physical models, the method can better adapt to ch