Hybrid Algorithm Based on Machine Learning and Deep Learning to Identify Ceramic Insulators and Detect Physical Damages
2021 IEEE Conference on Electrical Insulation and Dielectric Phenomena (CEIDP)(2021)
摘要
This work proposes a hybrid algorithm that is based on machine and deep learning algorithms. The paper studied and implemented an Aggregate Channel Feature and Semantic Segmentation to identify the existence of a ceramic insulator in an image, then pass a cropped image to a deep learning classifier to diagnose the insulators’ health status. The Artificial Intelligence networks were developed via a reliable database that consisted of thousands of images. The work concludes with a comparison and evaluation of the performance between the developed object detection techniques.
更多查看译文
关键词
transfer learning,object detection,classification,ceramic insulator
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要