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

作     者：Andrey SHASHKOV Mikhail TYUSHEV Alexander LOVTSOV Dmitry TOMILIN Dmitrii KRAVCHENKO Andrey SHASHKOV;Mikhail TYUSHEV;Alexander LOVTSOV;Dmitry TOMILIN;Dmitrii KRAVCHENKO

作者机构：JSC'Keldysh Research Center'8 Onezhskaya St.Moscow 125438Russia 

出 版 物：《Plasma Science and Technology》 (等离子体科学和技术（英文版）)

年 卷 期：2022年第24卷第6期

页      面：148-156页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 081104[工学-模式识别与智能系统] 082701[工学-核能科学与工程] 0827[工学-核科学与技术] 0714[理学-统计学（可授理学、经济学学位）] 0835[工学-软件工程] 0701[理学-数学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Hall thruster anomalous conductivity machine learning Bayesian optimization Gaussian process electric propulsion 

摘      要：The problem of determining the electron anomalous conductivity profile in a Hall thruster,when its operating parameters are known from the experiment,is *** 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 *** axial 1D3V hybrid model was used to calculate the operating parameters with parametrically set *** 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 *** 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 *** local plasma parameters were calculated and compared to the measured ones for four different operating *** results show the qualitative *** agreement between calculated and measured local parameters can be improved with a more accurate model of plasma-wall interaction.