TY - GEN
T1 - An AI-based Multi-objective Optimization Approach for Monitoring Manufacturing Processes
AU - Ghahramani, Mohammadhossein
AU - Qiao, Yan
AU - Zhou, Meng Chu
AU - Wu, Nai Qi
N1 - Funding Information:
This work was supported by in part by National Natural Science Foundation of China under Grant 61803397 and in part by the Science and Technology development fund (FDCT) of Macau under Grant 01112017/A.
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Recently, considerable effort has been devoted to applying new techniques such as Artificial Intelligence (AI) and machine learning in manufacturing systems. Implementing effi-cient fault detection and diagnosis procedure for manufacturing systems can provide manufacturers with significant advantages, e.g., enhancing product quality and yield while reducing cost. Maximizing efficiency and controlling costs is the goal of every operation. Optimization methods like Evolutionary Algorithms can be considered for modeling manufacturing operational procedures using datasets whose contents are populated by various sensors and other data sources. Embracing AI to empower organizations to analyze data can lead to efficient and intelligent automation. In this paper, we propose a hybrid model for monitoring manufacturing operations based on a multi-objective approach. This model considers different conflicting objectives that should be minimized simultaneously. Our goal is to provide an advanced methodology for exploring manufacturing processes and to gain perspective on production status. It enables manufacturers to access the effectiveness of predictive technologies and respond well to any disruptive trends.
AB - Recently, considerable effort has been devoted to applying new techniques such as Artificial Intelligence (AI) and machine learning in manufacturing systems. Implementing effi-cient fault detection and diagnosis procedure for manufacturing systems can provide manufacturers with significant advantages, e.g., enhancing product quality and yield while reducing cost. Maximizing efficiency and controlling costs is the goal of every operation. Optimization methods like Evolutionary Algorithms can be considered for modeling manufacturing operational procedures using datasets whose contents are populated by various sensors and other data sources. Embracing AI to empower organizations to analyze data can lead to efficient and intelligent automation. In this paper, we propose a hybrid model for monitoring manufacturing operations based on a multi-objective approach. This model considers different conflicting objectives that should be minimized simultaneously. Our goal is to provide an advanced methodology for exploring manufacturing processes and to gain perspective on production status. It enables manufacturers to access the effectiveness of predictive technologies and respond well to any disruptive trends.
UR - http://www.scopus.com/inward/record.url?scp=85127553773&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85127553773&partnerID=8YFLogxK
U2 - 10.1109/ICCSI53130.2021.9736241
DO - 10.1109/ICCSI53130.2021.9736241
M3 - Conference contribution
AN - SCOPUS:85127553773
T3 - 2021 International Conference on Cyber-Physical Social Intelligence, ICCSI 2021
BT - 2021 International Conference on Cyber-Physical Social Intelligence, ICCSI 2021
A2 - Wang, Jiacun
A2 - Tang, Ying
A2 - Wang, Fei-Yue
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 International Conference on Cyber-Physical Social Intelligence, ICCSI 2021
Y2 - 18 December 2021 through 20 December 2021
ER -