《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (4): 1235-1243.DOI: 10.11772/j.issn.1001-9081.2021071182

• CCF第36届中国计算机应用大会 (CCF NCCA 2021) • 上一篇    

基于联邦增量学习的工业物联网数据共享方法

刘晶1,2,3, 董志红1, 张喆语1, 孙志刚4, 季海鹏2,3,5()   

  1. 1.河北工业大学 人工智能与数据科学学院,天津 300401
    2.河北省数据驱动工业智能工程研究中心(河北工业大学),天津 300401
    3.天津开发区精诺瀚海数据科技有限公司,天津 300401
    4.长城汽车股份有限公司 天津哈弗分公司,天津 300462
    5.河北工业大学 材料科学与工程学院,天津 300401
  • 收稿日期:2021-07-08 修回日期:2021-09-03 接受日期:2021-09-06 发布日期:2021-09-18 出版日期:2022-04-10
  • 通讯作者: 季海鹏
  • 作者简介:刘晶(1979—),女,内蒙古包头人,研究员,博士,CCF高级会员,主要研究方向:工业人工智能
    董志红(1987—),男,河北邯郸人,硕士研究生,主要研究方向:大数据与智能计算、联邦学习
    张喆语(1997—),男,黑龙江哈尔滨人,硕士研究生,主要研究方向:大数据与智能计算、区块链
    孙志刚(1982—),男,河北保定人,助理工程师,主要研究方向:精益生产制造
  • 基金资助:
    河北省自然科学基金资助项目(F2019202062)

Data sharing method of industrial internet of things based on federal incremental learning

Jing LIU1,2,3, Zhihong DONG1, Zheyu ZHANG1, Zhigang SUN4, Haipeng JI2,3,5()   

  1. 1.School of Artificial Intelligence,Hebei University of Technology,Tianjin 300401,China
    2.Hebei Data Driven Industrial Intelligent Engineering Research Center (Hebei University of Technology),Tianjin 300401,China
    3.Tianjin Development Zone Jingnuo Data Technology Company Limited,Tianjin 300401,China
    4.Tianjin HAVEL Branch,Tianjin Great Wall Motor Company Limited,Tianjin 300462,China
    5.School of Materials Science and Engineering,Hebei University of Technology,Tianjin 300401,China
  • Received:2021-07-08 Revised:2021-09-03 Accepted:2021-09-06 Online:2021-09-18 Published:2022-04-10
  • Contact: Haipeng JI
  • About author:LIU Jing, born in 1979, Ph. D., research fellow. Her research interests include industrial artificial intelligence.
    DONG Zhihong, born in 1987, M. S. candidate. His research interests include big data and intelligent computing, federated learning.
    ZHANG Zheyu, born in 1997, M. S. candidate. His research interests include big data and intelligent computing, blockchain.
    SUN Zhigang, born in 1982, assistant engineer. His research interests include lean manufacturing.
  • Supported by:
    Hebei Natural Science Foundation(F2019202062)

摘要:

针对工业物联网(IIOT)新增数据量大、工厂子端数据量不均衡的问题,提出了一种基于联邦增量学习的IIOT数据共享方法(FIL-IIOT)。首先,将行业联合模型下发到工厂子端作为本地初始模型;然后,提出联邦优选子端算法来动态调整参与子集;最后,通过联邦增量学习算法计算出工厂子端的增量加权,从而使新增状态数据与原行业联合模型快速融合。实验结果表明,在美国凯斯西储大学(CWRU)轴承故障数据集上,所提FIL-IIOT使轴承故障诊断精度达到93.15%,比联邦均值(FedAvg)算法和无增量公式的FIL-IIOT(FIL-IIOT-NI)方法分别提高了6.18个百分点和2.59个百分点,满足了基于工业增量数据的行业联合模型持续优化的需求。

关键词: 工业物联网(IIOT), 联邦学习, 增量学习, 数据不均衡, 优选子端

Abstract:

In view of the large amount of new data in the Industrial Internet Of Things(IIOT) and the imbalance of data at the factory sub-ends, a data sharing method of IIOT based on Federal Incremental Learning (FIL-IIOT) was proposed. Firstly, the industry federation model was distributed to the factory sub-end as the local initial model. Then, the federal sub-end optimization algorithm was proposed to dynamically adjust the participating subset. Finally, the incremental weight of the factory sub-end was calculated through the federal incremental learning algorithm, thereby integrating the new state data with the original industry federation model quickly. Experimental results the Case Western Reserve University (CWRU) bearing failure dataset show that the proposed FIL-IIOT makes the accuracy of bearing fault diagnosis reached 93.15%, which is 6.18 percentage points and 2.59 percentage points higher than those of Federated Averaging (FedAvg) algorithm and FIL-IIOT of Non Increment (FIL-IIOT-NI) method, respectively. The proposed method meets the needs of continuous optimization of industry federation model based on industrial incremental data.

Key words: Industrial Internet Of Things (IIOT), federated learning, incremental learning, data imbalance, optimized sub-end

中图分类号: