现代电子技术2024，Vol.47Issue(10)：139-142,4.DOI:10.16652/j.issn.1004-373x.2024.10.026
基于深度学习的逆变器电路图像数据智能识别方法
Method of inverter circuit image data intelligent acquisition based on deep learning
摘要
Abstract
When recognizing inverter circuit image data,insufficient feature information extraction can make it difficult to accurately capture key features,resulting in a decrease in the recognition accuracy.On this basis,a method of inverter circuit image data intelligent recognition based on deep learning is proposed.The inverter data acquisition system is used to collect image data of the inverter circuit.The image data is input into a convolutional neural network model,and the features of the data are extracted by means of convolutional kernels.The YOLO(you only look once)algorithm is used for the effective recognition.The CA(coordinate attention)module is used to focus on feature information,and the Detect module is used to output recognition results.The Detect module mainly includes the confidence function and the loss function of the model.In combination of the two modules,the classification box and detection box are used to realize the recognition of the inverter circuit image.The experimental results show that the proposed method has a maximum recognition false alarm rate of only 6%,which is practical.关键词
深度学习/逆变器电路/图像识别/数据特征提取/卷积神经网络/YOLO算法Key words
deep learning/inverter circuit/image recognition/data feature extraction/convolutional neural networks/YOLO algorithm分类
信息技术与安全科学引用本文复制引用
何韦颖,钟健,谌颃..基于深度学习的逆变器电路图像数据智能识别方法[J].现代电子技术,2024,47(10):139-142,4.基金项目
2020年广东省普通高校青年创新人才项目(2020KQNCX13) （2020KQNCX13）
2020年广东省普通高校特色创新项目(2020KTSCX292) （2020KTSCX292）
