Hıdır Selçuk NOĞAY
High Voltage Breakers are critical components in power systems that protect the system against faults and overloads. For this reason, automatic classification of high voltage breakers by deep learning method is important and necessary. By automatically classifying high voltage breakers, we can make sure they are working properly and identify potential problems before they become major problems. Additionally, deep learning methods can provide accurate and efficient classification, allowing for faster and more reliable maintenance and repair of these critical components. Deep learning approaches that rely on visual data for their contribution to science can improve the accuracy and efficiency of classification tasks, as well as provide insights into key models and properties of high-voltage breakers. By using convolutional neural networks to classify high-voltage breakers, researchers can better understand the different types of breakers and how they work. This can lead to new insights and discoveries in electrical engineering and enable the development of more advanced and efficient power systems. Additionally, the use of convolutional neural networks could also provide practical benefits for industries that rely on power systems. By classifying high voltage breakers accurately and efficiently, it is possible to detect potential faults or problems before they cause downtime or damage to equipment. This can help reduce maintenance costs and increase the reliability and safety of power systems. In this study, convolutional neural networks trained and tested with visual data are used to classify high voltage breakers. With the designed and implemented convolutional neural network model, high voltage breakers are automatically classified with a successful accuracy rate. ORCID NO: 0000-0001-9105-508X

Anahtar Kelimeler: CNN, Transfer Learning, High Voltage Breakers