Experimental identification of ion cyclotron emission on HL-2A using YOLO neural network algorithm

Abstract Identification of magnetohydrodynamics (MHD) instabilities with neural networks has been extensively applied in the research of magnetically controlled fusion plasmas. Ion Cyclotron Emission (ICE) is a potential fast ion diagnostic method in burning plasmas. To assess ICE as a fast ion diagnostic for International Thermonuclear Experimental Reactor, real-time identification of ICE is required in the fast ion diagnostic flow. In the present work, we employed YOLO (You Only Look Once) to identify core and edge ICE in a large labeled database of HL-2A discharges, achieving a precision of 85.4% and a recall rate of 77.3%. Subsequent improvements to the YOLO model resulted in a noteworthy 8.3% increment in the recall rate. The developed identification method demonstrates significant potential for real-time application in identifying MHD instabilities.