Title
Real-Time Task Processing For Spinning Cyber-Physical Production Systems Based On Edge Computing
Abstract
With a high-speed, dynamic and continuous yarn manufacturing process, spinning production suffers from different problems of dynamic disturbances such as yarn breakage, machine breakdown, and yarn quality. Processing real-time tasks is critical for tackling these problems, except for satisfying the requirements of mass production. The existing spinning cyber-physical production systems (CPPS), however, rely on a cloud center for centralized processing of real-time tasks. Thus, it becomes increasingly difficult for them to meet real-time requirements. As such, this paper proposes a novel real-time task processing method for spinning CPPS based on edge computing. First, a new hybrid structure of edge computing nodes (ECN) that consists of both 1-1 and N-1 modes is introduced for different types of tasks in spinning CPPS such as fixed tasks, decision-intensive tasks, and data-intensive tasks. Second, a collaboration mechanism is developed for collaborations between ECNs. The mathematical model and algorithms for real-time task processing are provided for a single ECN. Finally, a case study on a real spinning production is conducted. The results of this case study have demonstrated that the proposed method can significantly reduce the processing time of real-time tasks, as well as improve the production flexibility and production efficiency in spinning CPPS. The proposed method could be applied to continuous and batch manufacturing fields with high real-time requirements, such as weaving, chemical fiber production, and the pharmaceutical industry.
Year
DOI
Venue
2020
10.1007/s10845-020-01553-6
JOURNAL OF INTELLIGENT MANUFACTURING
Keywords
DocType
Volume
Edge computing, Real-time task, Resource allocation, CPPS, Spinning
Journal
31
Issue
ISSN
Citations 
8
0956-5515
1
PageRank 
References 
Authors
0.41
0
6
Name
Order
Citations
PageRank
Shiyong Yin191.19
Jinsong Bao2138.04
Jie Zhang312.78
J.X. Li4403113.63
Junliang Wang582.59
Xiaodi Huang634240.33