2025年04月06日 星期日 首页   |    期刊介绍   |    编 委 会   |    投稿指南   |    期刊订阅   |    统合信息   |    联系我们
计量学报  2024, Vol. 45 Issue (6): 873-880    DOI: 10.3969/j.issn.1000-1158.2024.06.13
  力学计量 本期目录 | 过刊浏览 | 高级检索 |
基于边云协同的数控机床故障诊断联邦学习研究
徐玲艳1,陆艺1,赵静2
1.中国计量大学 计量测试工程学院,浙江 杭州 310018
2.杭州沃镭智能科技股份有限公司,浙江杭州310018
Research on Federated Learning of Numerical Control Machine Fault Diagnosis Based on Edge Cloud Cooperation
XU Lingyan1,LU Yi1,ZHAO Jing2
1. College of Metrology and Measurement Engineering, China Jiliang University, Hangzhou, Zhejiang 310018, China
2. Hangzhou Wolei Intelligent Technology Co. Ltd, Hangzhou, Zhejiang 310018, China
全文: PDF (631 KB)   HTML (1 KB) 
输出: BibTeX | EndNote (RIS)      
摘要 为解决数控机床主轴轴承和刀具在进行故障诊断模型训练时需要大量数据且耗时长的问题,提出一种基于边云协同架构的联邦平均学习故障诊断模型。首先,设计一维卷积神经网络模型架构,在各边缘客户端进行本地模型训练,以减小数据上传规模和分担云服务器端计算压力;其次,在云服务器端基于准确率优化模型聚合算法,改进边缘客户端筛选算法,以加快模型收敛速度,提高模型准确率;再次,在云服务器端搭建基于Kubernetes的KubeEdge边云协同平台,以缩短数据传输的通信时间。实验结果表明,模型在各边缘客户端故障诊断的准确率最终稳定在87.5%左右;且收敛速度、训练时长等方面与对照组相比,均获得优化。
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
徐玲艳
陆艺
赵静
关键词 故障诊断;数控机床;边云协同;联邦学习振动信号    
Abstract:In order to solve the problem when the spindle bearing and cutter fault diagnosis model of NC machine tool is trained, it needs massive data and takes a long time. A federated mean learning fault diagnosis model based on edge-cloud collaborative architecture is proposed. Firstly, one-dimensional convolutional neural network model architecture is designed, and local model training is carried out on each edge client to reduce data upload scale and share computing pressure on cloud server side. Then, the model aggregation algorithm is optimized based on the accuracy on the cloud server side, and the edge client screening algorithm is improved to accelerate the convergence rate and improve the accuracy of the model. Thirdly, the KubeEdge cloud collaborative platform based on Kubernetes is built on the cloud server side to shorten the communication time of data transmission. Finally, the experimental results show that the accuracy of fault diagnosis in each edge client of the model is stable at about 87.5%. Compared with the control group, the convergence speed and training time are optimized.
Key wordsfault diagnosis    numerical control machine    edge cloud cooperation    federal learning    vibration signal
收稿日期: 2022-12-13      发布日期: 2024-06-06
PACS:  TB936  
  TB973  
基金资助:浙江省科技计划项目省级重点研发计划(2021 C01136)
通讯作者: 陆艺(1979-),男,江苏扬州人,中国计量大学副教授,主要从事精密检测技术、汽车零部件自动化测试方面研究。Email: luyi9798paper@163.com     E-mail: luyi9798paper@163.com
作者简介: 徐玲艳(1996-),女,江苏淮安人,中国计量大学在读硕士研究生,研究方向为精密仪器及机械。Email: 619059327@qq.com
引用本文:   
徐玲艳,陆艺,赵静. 基于边云协同的数控机床故障诊断联邦学习研究[J]. 计量学报, 2024, 45(6): 873-880.
XU Lingyan,LU Yi,ZHAO Jing. Research on Federated Learning of Numerical Control Machine Fault Diagnosis Based on Edge Cloud Cooperation. Acta Metrologica Sinica, 2024, 45(6): 873-880.
链接本文:  
http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2024.06.13     或     http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2024/V45/I6/873
京ICP备:14006989号-1
版权所有 © 《计量学报》编辑部
地址:北三环东路18号(北京1413信箱)  邮编:100029 电话:(010)64271480
本系统由北京玛格泰克科技发展有限公司设计开发  技术支持:support@magtech.com.cn