• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学 ›› 2023, Vol. 45 ›› Issue (07): 1188-1196.

• 高性能计算 • 上一篇    下一篇

基于云-边协同变分自编码神经网络的设备故障检测方法

刘阳1,2,粟航2,何倩2,申普1,2,刘鹏2   

  1. (1.广西交科集团有限公司广西道路智能交通系统工程技术研究中心,广西 南宁 530007;
    2.桂林电子科技大学广西可信软件重点实验室,广西 桂林 541004)

  • 收稿日期:2023-01-07 修回日期:2023-03-27 接受日期:2023-07-25 出版日期:2023-07-25 发布日期:2023-07-11
  • 基金资助:
    国家自然科学基金(62162018);广西创新驱动重大专项(AA17202024);广西自然科学基金(2019GXNSFGA245004);广西云计算与大数据协同创新基金(YD1901);广西研究生教育创新计划(YCSW2022296);南宁市科学研究与技术开发计划(20201075)

An equipment fault detection method based on cloud-edge collaboration variational autoencoder neural network

LIU Yang1,2,SU Hang2,HE Qian2,SHEN Pu1,2,LIU Peng2   

  1. (1.Guangxi Engineering &Technology Research Center for Intelligent Road Transportation System,
    Guangxi Transportation Science and Technology Group Co.,Ltd.,Nanning 530007;
    2.Guangxi Key Laboratory of Trusted Software,Guilin University of Electronic Technology,Guilin 541004,China)
  • Received:2023-01-07 Revised:2023-03-27 Accepted:2023-07-25 Online:2023-07-25 Published:2023-07-11

摘要: 针对机电设备故障数据整体趋势和多阈值点实际应用,提出了一种基于云-边协同的变分自编码门控循环神经网络VAE-GRU的设备故障检测方法。构建了基于云-边协同的机电设备故障检测系统架构,终端设备层、边缘节点层、云中心层,云中心和边缘节点之间通过协同的方式对机电设备进行故障检测。设计了VAE-GRU模型,通过VAE编码器对输入数据进行采样,利用GRU捕捉时序数据的长期相关性。设计了动态阈值选择算法确定故障检测阈值,针对不同数据集可自动选择最优阈值,提高故障检测精度。实验结果表明,提出的基于云-边协同VAE-GRU设备故障检测方法提高了设备故障检测准确性,降低了处理时延,能保证机电设备稳定运行。

关键词: 云-边协同, 故障检测, 变分自编码, 门控循环神经网络, 机电设备运维

Abstract: In response to the overall trend and practical application of multi-threshold points in electromechanical equipment fault data detection, this paper proposes a cloud-edge collaborative electromechanical equipment fault detection method based on a variational autoencoder with gated recurrent unit (VAE-GRU). A cloud-edge collaborative electromechanical equipment fault detection architecture is structed, including a terminal equipment layer, an edge node layer, and a cloud center layer, in which electromechanical equipment is detected for faults through collaboration between the cloud center and edge nodes. The VAE-GRU model is design, where the input data is sampled by VAE, and GRU is used to capture the long-term correlation of the timing data. A dynamic threshold selection algorithm is used to calculate the fault detection threshold, that can automatically select the optimal threshold for different data sets to improve fault detection accuracy. Experimental results show that the proposed method improves the accuracy of electromechanical equipment fault detection while reducing latency, ensuring the normal and stable operation of electromechanical equipment.

Key words: cloud-edge collaboration, fault detection, variational autoencoder, gated recurrent neural network, electromechanical equipment operation