Skip to main content
Article
Vision Sensor based Action Recognition for Improving Efficiency and Quality under the Environment of Industry 4.0
Procedia CIRP
  • Zipeng Wang
  • Ruwen Qin, Missouri University of Science and Technology
  • Jihong Yan
  • Chaozhong Guo
Abstract

In the environment of industry 4.0, human beings are still an important influencing factor of efficiency and quality which are the core of product life cycle management. Hence, monitoring and analyzing humans' actions are essential. This paper proposes a vision sensor based method to evaluate the accuracy of operators' actions. Each action of operators is recognized in real time by a Convolutional Neural Network (CNN) based classification model in which hierarchical clustering is introduced to minimize the effects of action uncertainty. Warnings are triggered when incorrect actions occur in real time and applications of action analysis of workers on a reducer assembling line show the effectiveness of the proposed method. The research is expected to provide a guidance for operators to correct their actions to reduce the cost of quality defects and improve the efficiency of workforce.

Meeting Name
26th CIRP Conference on Life Cycle Engineering, LCE 2019 (2019: May 7-9, Lafayette, IN)
Department(s)
Engineering Management and Systems Engineering
Keywords and Phrases
  • Action recognition,
  • Convolutional neural network,
  • Hierarchical clustering,
  • Real-time monitoring
Document Type
Article - Conference proceedings
Document Version
Final Version
File Type
text
Language(s)
English
Rights
© 2019 The Authors, All rights reserved.
Creative Commons Licensing
Creative Commons Attribution-Noncommercial-No Derivative Works 4.0
Publication Date
5-1-2019
Citation Information
Zipeng Wang, Ruwen Qin, Jihong Yan and Chaozhong Guo. "Vision Sensor based Action Recognition for Improving Efficiency and Quality under the Environment of Industry 4.0" Procedia CIRP Vol. 80 (2019) p. 711 - 716 ISSN: 2212-8271
Available at: http://works.bepress.com/ruwen-qin/132/