• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Chen, Jin (Chen, Jin.) | Pu, Wang (Pu, Wang.) (学者:王普) | Kai, Wang (Kai, Wang.)

收录:

CPCI-S

摘要:

Fault monitoring can find out-of-control conditions of equipment operation in a timely manner, which is essential for eliminating faults and for stable operation of industrial systems in batch processes. Many conventional data-driven fault detection methods focus less on the non-Gaussian and Multi-stage characteristics of batch process data, which may result in degradation of monitoring performance. In this paper, a Multi-stage Fourth Order Moment Staked Autoencoder (M-FOM-SAE) is designed to solve the above problems. The proposed method firstly automatically determines the number of clusters and divides the batch process into multiple stages. After that, the FOM-SAE model is established in each sub-stage, which can not only effectively learn the nonlinear features of process data, but also extract the non-Gaussian information. The proposed strategy is applied to real-world industrial processes. Experimental results indicate that it can better capture the non-Gaussian and Multi-stage characteristics of process data, and improve the ability to monitor abnormalities.

关键词:

Batch process Fault monitoring Multi-stage non-Gaussian Stacked Autoencoder

作者机构:

  • [ 1 ] [Chen, Jin]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 2 ] [Pu, Wang]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 3 ] [Kai, Wang]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 4 ] [Pu, Wang]Beijing Key Lab Computat Intelligence & Intellige, Beijing 100124, Peoples R China

通讯作者信息:

  • [Chen, Jin]Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China

查看成果更多字段

相关关键词:

来源 :

PROCEEDINGS OF THE 32ND 2020 CHINESE CONTROL AND DECISION CONFERENCE (CCDC 2020)

ISSN: 1948-9439

年份: 2020

页码: 721-728

语种: 英文

被引次数:

WoS核心集被引频次: 0

SCOPUS被引频次:

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 0

归属院系:

在线人数/总访问数:160/3269224
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司