Anzeige
Erschienen in:
2020 | OriginalPaper | Buchkapitel
Research on Construction of Infrared Image Classification Model of Substation Equipment Based on CNN
verfasst von : Kehui Zhou, Zhiwei Liao, Xiaochun Zang
Erschienen in: Proceedings of PURPLE MOUNTAIN FORUM 2019-International Forum on Smart Grid Protection and Control
Verlag: Springer Singapore
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
Infrared Intelligent detection is the key research direction of infrared fault detection of power equipment. However, different types of equipment and different processing purposes lead to a variety of fault detection methods. If the manual method is used to classify the equipment, the efficiency of fault detection will be greatly reduced. In this paper, based on convolutional neural networks, based on RGB and HSV color space conversion, a classification model suitable for infrared images of power equipment is constructed. Firstly, the structure characteristics and training process of CNN are introduced. After that, based on RGB and HSV color space conversion, the infrared image of substation equipment is processed, and the target area of suitable size is extracted to establish network training and test set. Finally, a CNN-based infrared image classification model is established, and its good applicability is verified by case analysis.