Plasma Electron Density Estimation Using Backpropagation Neural Network

Abstract

It is important to study the electron density distribution of plasma sheath to inhibit the blackout phenomenon of reentry vehicle. In this article, we propose a new method to predict the electron density distribution based on a backpropagation neural network (BPNN). We build a dataset based on the hybrid matrix method of computational electromagnetics (EMs) and train a three-layer network to map the relationship between EM wave propagation characteristics and electron density. This method is more accurate than the traditional plasma diagnosis method and reduces the complicated measurement process. Experimental results show that the neural network method has a performance with an average error of less than 3% and can reduce twice the training time using multicore CPU than low computing capability graphics card. This study sheds new light on electron density diagnosis to find more accurate and effective methods.