Abnormal Behavior Recognition Model of Power Grid Based on Multi-Scale Feature Fusion

Artificial intelligence technology is applied to power grid transmission and operation status identification to improve the intelligence level of power inspection. However, the existing grid anomalous behavior recognition model has the problem of unsatisfactory accuracy for small target detection. T...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of physics. Conference series 2023-03, Vol.2456 (1), p.12030
Hauptverfasser: Kong, Qingyu, Zhang, Yi, Du, Zexu, Zhu, Chun, Xiao, Bin
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Artificial intelligence technology is applied to power grid transmission and operation status identification to improve the intelligence level of power inspection. However, the existing grid anomalous behavior recognition model has the problem of unsatisfactory accuracy for small target detection. To address this problem, this paper proposes an abnormal behavior recognition model of power grid based on multi-scale feature fusion. First, the texture feature extraction network with a multi-scale mechanism is constructed to obtain object features. Secondly, the graph relation network between target and background is constructed. Finally, the grid abnormal behavior recognition model based on multi-scale feature fusion is constructed. The model proposed in this article is compared with the existing object recognition model in the simulation of the different datasets. In terms of the evaluation accuracy index, the proposed model is 93.27, which is improved by 2.18%.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/2456/1/012030