TY - GEN
T1 - Computer Vision-enabled HCPS Assembly Workstations Swarm for Enhancing Responsiveness in Mass Customization
AU - Ling, Shiquan
AU - Guo, Daqiang
AU - Qian, Cheng
AU - Ao, Di
AU - Zhang, Tongda
AU - Rong, Yiming
AU - Huang, George Q.
N1 - Funding Information:
This work was supported in part by Shenzhen Science, Technology and Innovation Commission Support Program KQJSCX20170728162555608), the 2019 Guangdong Special Support Talent Program-Innovation and Entrepreneurship Leading Team (China) (2019BT02S593) and National Key Research and Development Program of China (2018YFB1702803).
Publisher Copyright:
© 2020 IEEE.
PY - 2020/8
Y1 - 2020/8
N2 - Facing fierce competition in mass customization, rapid response to dynamic changes is strategically important for manufactures to increase opportunity of survival in high-mix, low-volume (HMLV) environment. The traditional dedicated manufacturing system for mass production is required to become modular, scalable and reconfigurable for increasing flexibility and responsiveness to cope with the changing market. Motivated by a hybrid assembly cell lines (HACL) in real-life, a distributed assembly cells system, inspired by swarm intelligence (SI) concept and swarm robotics, has been proposed, named swarm assembly system (SAS). In order to apply and reap the benefits of SI to SAS, three main components are designed by referring to swarm robot system and they are human-cyber-physical system holon (HCPS Holon), intelligent assembly workstation (iWorkstation) and operational framework of SAS. Computer vision technologies are employed to monitor and analyze real-time worker status and operation information within the iWorkstation for closed-loop adaptive control. The hybrid operational framework of SAS provides the basis for communication between iWrokstations and global decision making. Several scenarios are designed to show its potential benefits in robustness, reconfigurability and scalability, resulting in enhancing responsiveness in HMLV environment.
AB - Facing fierce competition in mass customization, rapid response to dynamic changes is strategically important for manufactures to increase opportunity of survival in high-mix, low-volume (HMLV) environment. The traditional dedicated manufacturing system for mass production is required to become modular, scalable and reconfigurable for increasing flexibility and responsiveness to cope with the changing market. Motivated by a hybrid assembly cell lines (HACL) in real-life, a distributed assembly cells system, inspired by swarm intelligence (SI) concept and swarm robotics, has been proposed, named swarm assembly system (SAS). In order to apply and reap the benefits of SI to SAS, three main components are designed by referring to swarm robot system and they are human-cyber-physical system holon (HCPS Holon), intelligent assembly workstation (iWorkstation) and operational framework of SAS. Computer vision technologies are employed to monitor and analyze real-time worker status and operation information within the iWorkstation for closed-loop adaptive control. The hybrid operational framework of SAS provides the basis for communication between iWrokstations and global decision making. Several scenarios are designed to show its potential benefits in robustness, reconfigurability and scalability, resulting in enhancing responsiveness in HMLV environment.
KW - computer vision
KW - flexible assembly system
KW - human-cyber-physical system
KW - Mass customization
KW - swarm intelligence
UR - http://www.scopus.com/inward/record.url?scp=85094175487&partnerID=8YFLogxK
U2 - 10.1109/CASE48305.2020.9216907
DO - 10.1109/CASE48305.2020.9216907
M3 - Conference article published in proceeding or book
AN - SCOPUS:85094175487
T3 - IEEE International Conference on Automation Science and Engineering
SP - 214
EP - 219
BT - 2020 IEEE 16th International Conference on Automation Science and Engineering, CASE 2020
PB - IEEE Computer Society
T2 - 16th IEEE International Conference on Automation Science and Engineering, CASE 2020
Y2 - 20 August 2020 through 21 August 2020
ER -