基于公共特有子空间提取的工业机器人多模式运行过程故障检测方法研究
作者:
作者单位:

1.浙江大学;2.浙江同济科技职业学院;3.浙江钱江机器人有限公司;4.江南大学;5.中国计量大学

作者简介:

通讯作者:

中图分类号:

TP242.2

基金项目:

中国博士后科学基金(2020M671721),国家自然科学基金项目(61903352, 51775485),浙江省自然科学基金(LQ19F030007, LZ20E050002 ),浙江省教育厅项目(Y202044960),浙江同济科技职业学院科研项目 (TRC1904)


Multimode Process Monitoring for Industrial Robots Utilizing Common-specific Information Extraction Strategy
Author:
Affiliation:

1.Zhejiang University;2.Zhejiang tongji vocational college of science and technology;3.Zhejiang Qianjiang Robot Co.,Ltd.;4.Jiangnan University;5.China Jiliang University

Fund Project:

China Postdoctoral Science Foundation(2020M671721), The National Natural Science Foundation of China (61903352,51775485),The Natural Science Foundation of Zhejiang (LQ19F030007, LZ20E050002 ),Project of department of education of Zhejiang Province (Y202044960), Project of Zhejiang Tongji Vocational College of Science and Technology (TRC1904)

  • 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:

    工业机器人运行状态直接影响到最终产品质量,因此有必要对设备运行过程开展监控。本文着重对工业机器人运行数据中存在的不同阶次信息以及多模式等复杂数据特性展开讨论。针对过程中存在的不同阶次信息问题,本文首先通过引入最大交互熵展开与偏最小二乘方法,将原始空间信息分解为高阶和低阶信息,并构建相应隐空间模型来提取高阶与低阶质量相关关系;其次,针对过程中存在的多模式运行问题,本文提出公共—特有信息提取算法,并结合高阶—低阶信息结构,将原始空间信息进一步分解,并构建相应隐空间模型;再次,本文设计在线监控算法,可有效判断过程中存在的模式切换或故障,提高了多模式过程监控算法效果;最后,相关算法在实际工业机器人运行环境中进行了验证,结果表明,本文所提出的算法在设备多模式运行状态监测中的效果相比传统方法有较大优势。

    Abstract:

    Industrial robots have been widely used in modern industry, which indicates that the final product quality highly relies on the operational status of robot equipment. Therefore, it is of high importance to detect the quality-related faults in robot machines where non-linearity and non-stationarity are considered as two crucial characteristics in operating data. In this paper, high order and low order information in process data are discussed in details where a two-step latent variables extraction method is implemented using maximum mutual information and partial least square (PLS). In order to handle multimode process monitoring issue, a common-specific information strategy is designed. Combined with the high order and low order information extraction, the original data are further separated into four subspaces: common high, common low, specific high and specific low order information, respectively. Finally, monitoring performance is further demonstrated on a real mechanical arm where the results shows the superiority of the proposed method.

    参考文献
    相似文献
    引证文献
引用本文
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:2020-07-11
  • 最后修改日期:2021-03-29
  • 录用日期:2021-04-06
  • 在线发布日期: 2021-04-26
  • 出版日期: