Predicting Performance of Hall Effect Ion Source Using Machine Learning

Abstract

Accurate performance prediction methods are essential for the development of high-efficiency Hall effect ion sources, which are employed in industries ranging from material surface treatment to spacecraft electric propulsion (known as Hall thrusters). Traditional methods rely on simplified scaling laws and computationally intensive numerical simulations. Herein, a robust machine learning model is introduced that uses a neural network ensemble to predict the performance of Hall effect ion sources based on design parameters such as discharge channel dimensions and magnetic field structure. The neural networks are trained using 18 000 data points generated from numerical simulations with input powers ranging from sub-kW- to kW-class. The accuracy of the developed machine learning model is demonstrated using untrained 700 W- and 1 kW-class Hall effect ion sources, producing results with deviations of less than 10% compared to the experimentally measured thrust and discharge current, thus surpassing the accuracy of conventional scaling laws. As a high-fidelity surrogate for numerical simulations, the proposed prediction tool provides high prediction accuracy and calculation speed, offering an excellent complement to conventional scaling laws and enhancing the understanding of Hall effect ion source performance characteristics.