Critical current and n-value prediction of second-generation high temperature superconducting conductors considering the temperature-field dependence based on the back propagation neural network with encoder

Abstract

The qualities of superconducting conductors are usually characterized by their critical current and n-value. In this paper, the critical current and the n-value of the second-generation (2G) high temperature superconducting (HTS) conductors considering the temperature-field dependence are predicted by a back propagation (BP) neural network as J c(B, θ, T) and n(B,θ,T). A correlation exists between the critical current and the n-value, thus in our BP neural network, the tasks of estimating the critical current and the n-value can be carried out in one network. The outputs used to predict the critical current and the n-value share the same hidden layers of the network, and therefore the critical current and the n-value can be calculated simultaneously. The critical current and the n-value of HTS conductors vary for different manufacturers and even for the same manufacturer but different production batches. In our BP network, we use an encoder structure to encode different manufacturers and production batches to ensure that the network can be adapted to the HTS conductors so produced. The predictions on three different samples of HTS conductors are carried out and the results are compared with those obtained from linear interpolation at different temperature-field conditions. In addition to the high accuracy, when compared with the linear interpolation, the proposed network can suppress the fluctuations existing in the experimental data and ensure the prediction results to be more reasonable. The time required for the proposed network to obtain the prediction results of the critical current and the n-value is also discussed, which is within 5 s. Therefore, the proposed network has the potential to be applied to the optimization and analysis of the superconducting related equipment.