节点文献

基于双向LSTM的气动回路故障诊断方法研究

Research on Fault Diagnosis Method of Pneumatic Circuit Used Bidirectional LSTM Neural Network

  • 推荐 CAJ下载
  • PDF下载
  • 不支持迅雷等下载工具,请取消加速工具后下载。

【作者】 LEU VAN KIEN孙瑜陈丽娟方美张敏

【Author】 LEU VAN KIEN;SUN Yu;CHEN Lijuan;FANG Mei;ZHANG Min;School of Automation,Nanjing University of Science and Technology;

【机构】 南京理工大学自动化学院

【摘要】 论文提出一种基于双向LSTM的气动回路故障诊断方法,使用AMESim软件建立某生产线的气动回路仿真模型,模拟气动回路的单重故障和多重故障,记录仿真数据,制作该气动回路的故障诊断数据集,在Matlab环境下建立双向LSTM网络架构进行气动回路故障诊断实验与分析,结果表明双向LSTM模型在多重故障识别的正确率高于LSTM模型以及传统的诊断方法。

【Abstract】 This paper presents a fault diagnosis method of pneumatic circuit based on bidirectional LSTM. AMESim software is used to establish the simulation model of pneumatic circuit of a production line,the single fault and multiple fault of pneumatic circuit are simulated,the simulation data is recorded,a fault diagnosis data set of the pneumatic circuit is made,and the bidirectional LSTM network architecture is established in Matlab environment for the pneumatic circuit fault diagnosis experiment and analysis. The results show that the accuracy of bidirectional LSTM model is higher than that of LSTM model and traditional diagnosis methods.

【关键词】 气动回路故障诊断BiLSTMMatlab
【Key words】 pneumatic circuitfault diagnosisBiLSTMMatlab
  • 【文献出处】 计算机与数字工程 ,Computer & Digital Engineering , 编辑部邮箱 ,2022年02期
  • 【分类号】TH138
  • 【下载频次】221
节点文献中: 

本文链接的文献网络图示:

本文的引文网络