[3K01-06] Sensing and Data Transmission

[3K06] Development of Site Parameter Monitoring System with Edge Computer

*Yuichi Nakashige¹, Yuji Tetsutani¹, Yuki Kawai¹ (1. MHI)

Keywords:SMEc, Remote Monitoring System, Edge Computer, Deep Learning

we propose a method using SMEc, which combines camera images with deep learning, as a remote monitoring system for field instruments in plant operation. By the needle position estimation logic, a recognition rate of 99% or more could be obtained within the target accuracy of 1 scale error. It was also confirmed from the response evaluation test that the dynamic behavior had sufficient follow-up. Therefore, we believe that the introduction of SMEc has given us the prospect of realizing a system in which "Introduction of systems without modification of actual machines", "Collecting field data in narrow areas", "Data transmission with low communication capacity and low power consumption" and "Reduction of health hazards to operators" can be expected.