Three-Real-Time Architecture of Industrial Automation Based on Edge Computing
Weibin Su, Yun Liu, Du Yi, Dong Yingguo, Mingbo Pan, Gang Xu · 2019
In recent years, Deep Learning has promoted the rapid development of artificial intelligence and penetrated into various fields, but the massive data transmission of Artificial Intelligence (AI) training in network will affect the real-time performance of the system. As is known to all, real-time performance is very important in industrial field, especially in motion control. If the system is responding slowly, it cannot receive or send data acquisition and control commands on time. Finally, this will hinder the popularization of AI technology in the field of industrial automation. In this paper, we present a Three-Real-Time architecture, it involves real-time hardware network, real-time operating system and real-time scheduling virtualization layer. We hope to conceive a new industrial edge computing model after instead a traditional industrial controllers. Thus, the application of artificial intelligence technology in industrial automation can be thoroughly solved.