Speaker
Description
Real-time measurement of the fusion power released from Deuterium-Tritium (DT) plasmas remains one of the the most challenging technical aspects of magnetic confinement fusion.
Recently, during the second DT campaign at JET, a novel method was developed to measure fusion power with gamma-ray spectrometers detecting gamma-rays released by the secondary, radiative branch of the DT fusion reaction. Expanding on this previous work, a machine learning algorithm was developed to estimate DT fusion power at ITER by use of the Radial Gamma-Ray Spectrometer (RGRS) measurements, as well as the magnetic equilibrium as an additional source of information.
The algorithm was trained and tested on a set of 75 simulations of ITER DT plasma scenarios. By testing the algorithm by repeated 5-fold cross-validation, the average deviation of the estimated fusion power from the reference was found to be 0.32\%, while the relative error had a standard deviation of 0.97%. When statistical fluctuations were included in the analysis, the lowest measurable fusion power resulted to be around 30 MW, making the RGRS suitable for the fusion power measurement requirements at ITER.
