| 应用YOLOv4-tiny算法实现保护压板智能校核 |
| |
| 引用本文： | 杨宗源,侯进,周浩然,郝彦超,文志龙,李天宇.应用YOLOv4-tiny算法实现保护压板智能校核[J].科学技术与工程,2022,22(2):570-576. |
| |
| 作者姓名： | 杨宗源 侯进 周浩然 郝彦超 文志龙 李天宇 |
| |
| 作者单位： | 西南交通大学 |
| |
| 基金项目： | 国家重点基础研究发展计划(2014CB845800);四川省科技计划项目(2020SYSY0016) |
| |
| 摘 要： | 目前继电保护压板的巡检校核仍以人工为主,为提高其工作的效率,提出了一种智能实时校核方法.该方法首先使用YOLOv4-tiny算法对压板的投退状态进行预测,然后使用腾讯开源的ncnn前向推理框架,对YOLO模型进行优化,最后将模型移植到移动端,使用手机软件完成压板校核.经测试,模型的均值平均精度达到99.13％,平均预测...
|
| 关 键 词： | 保护压板 智能校核 YOLOv4-tiny ncnn模型 移动端 |
| 收稿时间： | 2021/8/10 0:00:00 |
| 修稿时间： | 2021/10/30 0:00:00 |
Application of YOLOv4-tiny algorithm for intelligent calibration of protection platens |
| |
| Yang Zongyuan,Hou Jin,Zhou Hanran,Hao Yanchao,Wen Zhilong,Li Tianyu.Application of YOLOv4-tiny algorithm for intelligent calibration of protection platens[J].Science Technology and Engineering,2022,22(2):570-576. |
| |
| Authors: | Yang Zongyuan Hou Jin Zhou Hanran Hao Yanchao Wen Zhilong Li Tianyu |
| |
| Institution: | Southwest Jiaotong University |
| |
| Abstract: | At present, the inspection and calibration of relay protection platens is still mainly manual. To improve the efficiency of its work, an intelligent real-time verification method is proposed. The method first uses the YOLOv4-tiny algorithm to predict the throwback state of the pressure plate, then uses Tencent"s open-source NCNN forward inference framework to optimize the YOLO model, and finally transplants the model to the mobile terminal to complete the platens calibration using the APP. After testing, the mean average accuracy of the model reaches 99.13%, the average prediction speed reaches 30 FPS, and can effectively solve the influence of environmental factors such as reflection and shading, which can significantly improve the efficiency of inspection work. |
| |
| Keywords: | protected platens intelligent real-time calibration yolov4-tiny ncnn mobile |
|
| 点击此处可从《科学技术与工程》浏览原始摘要信息 |
| 点击此处可从《科学技术与工程》下载免费的PDF全文 |
|
