###
计算机系统应用英文版:2022,31(5):331-337
本文二维码信息
码上扫一扫!
基于联邦学习的输电塔螺母销钉缺失检测
(1.中国石油大学(华东) 计算机科学与技术学院, 青岛 266580;2.山东鲁软数字科技有限公司, 济南 250001;3.国网山东省电力公司 青岛市黄岛区供电公司, 青岛 266500;4.解放军 9144 部队, 青岛 266102)
Detection of Pin Missing from Nuts of Transmission Tower Based on Federated Learning
(1.College of Computer Science and Technology, China University of Petroleum, Qingdao 266580, China;2.Shandong Luneng Software Technology Co. Ltd., Jinan 250001, China;3.Qingdao Huangdao District Power Supply Company, State Grid Shandong Electric Power Company, Qingdao 266500, China;4.No. 9144 Troops of PLA, Qingdao 266102, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 595次   下载 983
Received:July 27, 2021    Revised:August 20, 2021
中文摘要: 输电塔上的螺母是连接两个或多个输电塔部件之间的媒介, 销钉是确保螺母不脱落的重要保障. 销钉缺失会使各部件之间的连接处存在安全隐患.本文将联邦学习与目标检测算法结合起来, 在保证各地区数据不互通的情况下, 上传局部模型, 经过中心节点生成融合模型, 采用Faster RCNN检测算法对螺母进行检测, 同时用分类网络对螺母进行分类, 最终得出销钉是否缺失. 实验结果表明, 联邦学习融合后的模型比各局部模型在检测任务的mAP上提升3%–6%, 在分类任务的准确率上提升2%–3%.
中文关键词: 联邦学习  深度学习  目标检测  输电塔  销钉
Abstract:The nut on the transmission tower is the medium connecting two or more transmission tower components, and the pin is an important guarantee to ensure that the nut does not fall off. The lack of pins will lead to potential safety hazards at the joints between various components. This study combines the federated learning and target detection algorithm to upload the local model and generate the fusion model through the central node without any data exchange among regions. The detection algorithm Faster RCNN and the classification network are used to detect and classify nuts, respectively. The experimental results show that compared with local models, the fusion model based on federated learning improves the mAP of detection tasks by 3%–6% and the accuracy of classification tasks by 2%–3%.
文章编号:     中图分类号:    文献标志码:
基金项目:国家自然科学基金(62072469); 国家重点科研计划(2018YFE0116700); 山东省自然科学基金(ZR2019MF049); 中央高校基础研究基金(2015020031); 西海岸人工智能技术创新中心建设专项(2019-1-5, 2019-1-6); 上海可信工业控制平台开放项目(TICPSH202003015-ZC).
引用文本:
宋永康,张俊岭,公凡奎,安云云,王冶.基于联邦学习的输电塔螺母销钉缺失检测.计算机系统应用,2022,31(5):331-337
SONG Yong-Kang,ZHANG Jun-Ling,GONG Fan-Kui,AN Yun-Yun,WANG Ye.Detection of Pin Missing from Nuts of Transmission Tower Based on Federated Learning.COMPUTER SYSTEMS APPLICATIONS,2022,31(5):331-337