基于新型YOLO v5算法的磁悬浮球精确识别  

Accurate identification of magnetic levitation ball based on novel YOLOv5 algorithm

作　　者：马晓东 魏利胜 刘小珲 Ma Xiaodong;Wei Lisheng;Liu Xiaohui(School of Electrical Engineering,Anhui Polytechnic University,Wuhu 241000,China;Shanghai Oushuo Packing Machinery Co.,Ltd.,Shanghai 201417,China)

机构地区：[1]安徽工程大学电气工程学院,芜湖241000 [2]上海欧朔智能包装科技有限公司,上海201417

出　　处：《电子测量与仪器学报》2022年第8期204-212,共9页Journal of Electronic Measurement and Instrumentation

基　　金：安徽省教育厅重大项目(KJ2020ZD39);安徽省检测技术与节能装置重点实验室开放基金项目(DTESD2020A02)资助。

摘　　要：针对磁悬浮控制系统中目标物体定位精度低以及速度慢的问题,提出一种基于YOLOv5(you only look once v5)改进算法来对磁悬浮球进行识别定位。首先,利用Mish损失函数取代YOLOv5原模型中SiLU(sigmoid-weighted linear units)激活函数,以得到准确性更高和泛化能力更强的网络模型;其次,将协同注意力机制融合到YOLOv5算法中,提高模型的特征提取能力;在此基础上,选择CIOU(complete-intersection over union)损失函数替换YOLOv5算法中的GIOU(generalized intersection over union)损失函数来优化训练模型,以提高识别精度。最后,进行了仿真验证,结果表明,改进后的YOLOv5算法与原算法相比,在磁悬浮球目标识别精度由原来的92.4%提高到96.2%,MAP(mean average precision)由原来的88.8%提高到94.3%,从而验证了本文所提方法的有效性和可行性。Aiming at the problems of low positioning accuracy and slow speed of target objects in the magnetic levitation control system, a novel YOLOv5(you only look once v5) algorithm was proposed to identify and locate the magnetic levitation ball. Firstly, by using the Mish loss function to replace the SiLU(sigmoid-weighted linear units) activation function of YOLOv5 model, the higher accuracy and stronger generalization network model could be obtained. Then fusing the coordinate attention module into YOLOv5, the feature extraction capability of the model could be improved. On this basis, the CIOU(complete-intersection over union) loss function was selected to replace the GIOU(generalized intersection over union) loss function to improve the identification accuracy. Finally, the simulation verification was carried out. The results showed that the improved YOLOv5 algorithm could improve the target recognition accuracy of the magnetic levitation ball from 92.4% to 96.2%, and the MAP(mean average precision) from the original 88.8% to 94.3%. Therefore, the effectiveness and feasibility of the proposed method could be verified.

关 键 词：磁悬浮 YOLOv5 新型 注意力机制 CIOU 

分 类 号：TH85.5[机械工程—仪器科学与技术]