欢迎访问机床与液压官方网站!

咨询热线:020-32385312 32385313 RSS EMAIL-ALERT
基于SO-LSTM的立柱液压系统故障诊断方法研究
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

基金项目:

国家科技重大专项子课题(2019zx04055-001-014); 2020年天津市科委企业科技特派员项目(20YDTPJC00840)


Research on Fault Diagnosis Method of Column Hydraulic System Based on SO-LSTM
Author:
Affiliation:

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:

    针对目前无法快速、准确地诊断矿用立柱液压系统故障等问题,在建立仿真模型分析单一故障机制的基础上,基于优化算法提出多种故障诊断方法。将立柱物理模块与立柱液压系统模块相结合,建立立柱液压系统仿真模型;基于Simulink分析单一故障的影响,基于蛇优化LSTM神经网络建立诊断模型;最后,根据实际数据进行模型的实例验证。结果表明:蛇优化LSTM模型对液压立柱故障仿真数据识别率达到99.5%,对液压立柱故障真实数据识别率达到97%,与模型仿真数据的预测精度仅相差2.5%,预测精度较高,达到了预期目标。

    Abstract:

    Aiming at the problem that the hydraulic system fault of mine column cannot be diagnosed quickly and accurately at present,a variety of fault diagnosis methods were proposed based on the optimization algorithm and establishing simulation model to analyze single fault mechanism.The column hydraulic system simulation model was established by combining the column physical module with the column hydraulic system module.The influence of single fault was analyzed based on Simulink,and the diagnostic model was established based on snake optimized LSTM (SO-LSTM) neural network.Finally,the model was verified by an example according to the actual data.The results show that using snake optimized LSTM neural network,the recognition rate of the hydraulic column fault simulation data is 99.5%,and the recognition rate of the real hydraulic column fault data is 97%,which is only 2.5% lower than the prediction accuracy of the model simulation data.The prediction accuracy is high,and the expected target is achieved.

    参考文献
    相似文献
    引证文献
引用本文

郗涛,董蒙蒙,王莉静,张建业.基于SO-LSTM的立柱液压系统故障诊断方法研究[J].机床与液压,2024,52(8):196-201.
XI Tao, DONG Mengmeng, WANG Lijing, ZHANG Jianye. Research on Fault Diagnosis Method of Column Hydraulic System Based on SO-LSTM[J]. Machine Tool & Hydraulics,2024,52(8):196-201

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: 2024-04-29
  • 出版日期: 2024-04-28