基于PGAT模型的氧气顶吹转炉小样本故障诊断
CSTR:
作者:
作者单位:

1. 兰州理工大学 计算机与通信学院,兰州 730050;2. 兰州理工大学 电气工程与信息工程学院,兰州 730050

作者简介:

通讯作者:

E-mail: wjh0615@lut.edu.cn.

中图分类号:

TP277

基金项目:

国家重点研发计划项目(2020YFB1713600);国家自然科学基金项目(61763028,62063020).


Fault diagnosis of small sample of oxygen top-blowing converter based on PGAT model
Author:
Affiliation:

1. College of Computer and Communication,Lanzhou University of Technology,Lanzhou 730050,China;2. College of Electrical and Information Engineering,Lanzhou University of Technology,Lanzhou 730050,China

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对现有的深度学习方法对小样本情况下的故障诊断精度不佳和图神经网络构造图的方式依赖其他算法的问题,提出一种图的构造方法,并基于该方法提出一种基于图注意力机制与先验知识库的PGAT(prior knowledge-graph attention network)模型.将有标签样本和无标签样本按照固定的方式连接在一起,通过引入图注意力机制计算出样本之间的相似程度,使得新加入的样本不依赖于图的拓扑结构,解决图卷积神经网络不易于扩展的问题.在基准数据集和氧气顶吹转炉数据集上的实验表明,在只有少量有效数据的条件下,所提模型相较于其他模型具有更好的故障诊断精度.

    Abstract:

    Aiming at the problems that the existing deep learning methods have poor fault diagnosis accuracy in the case of small samples and the way of constructing graphs of graph neural networks depends on other algorithms, a graph construction method is proposed, and based on this method, a method based on the prior knowledge-graph attention network(PGAT) model of the graph attention mechanism and the prior knowledge base is proposed. The labeled samples and unlabeled samples are connected together in a fixed way, and the similarity between the samples is calculated by introducing the graph attention mechanism, so that the newly added samples do not depend on the topology of the graph, it also solves the problem that graph convolutional neural networks are not easy to expand. Experiments on the benchmark dataset and the oxygen top-blown converter dataset show that with only a small amount of valid data, it has better fault diagnosis accuracy than other models.

    参考文献
    相似文献
    引证文献
引用本文

曹洁,陈泽阳,王进花,等.基于PGAT模型的氧气顶吹转炉小样本故障诊断[J].控制与决策,2023,38(10):2943-2952

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2023-09-19
  • 出版日期: 2023-10-20
文章二维码