Intelligent estimation of critical current density of ReBCO superconductors exposed to irradiations for fusion energy applications: first machine learning study

This paper presents the first intelligent estimator model of the critical current of HTS tapes exposed to Gamma or Neutron radiations using machine learning (ML) techniques. A comprehensive benchmarking analysis of 10 ML methods has been conducted to determine the best ML models for each type of radiation. To ensure the generalisability of the models, databases of experimental measurements were collected by an extensive review of 90 published papers in literature, covering 4 and 9 different ReBCO tapes for Gamma and Neutron irradiation tests, respectively. The results demonstrated that the cascade-forward neural network (CFNN) excels for both Gamma and Neutron irradiation prediction models. For Gamma irradiation model, the CFNN model’s performance in terms of goodness of fit and relative error was 99.979% and 0.2675%, respectively. For Neutron irradiation model, these metrics have shown a performance of 99.972% and 4.68%. The findings of this paper will advance modelling of superconductors in terms of understanding their behaviour after irradiation for fusion applications.