Machine learning-based method to adjust electron anomalous conductivity profile to experimentally measured operating parameters of Hall thruster

Abstract

The problem of determining the electron anomalous conductivity profile in a Hall thruster, when its operating parameters are known from the experiment, is considered. To solve the problem, we propose varying the parametrically set anomalous conductivity profile until the calculated operating parameters match the experimentally measured ones in the best way. The axial 1D3V hybrid model was used to calculate the operating parameters with parametrically set conductivity. Variation of the conductivity profile was performed using Bayesian optimization with a Gaussian process (machine learning method), which can resolve all local minima, even for noisy functions. The calculated solution corresponding to the measured operating parameters of a Hall thruster in the best way proved to be unique for the studied operating modes of KM-88. The local plasma parameters were calculated and compared to the measured ones for four different operating modes. The results show the qualitative agreement. An agreement between calculated and measured local parameters can be improved with a more accurate model of plasma-wall interaction.