DeepPropNet: an operator learning-based predictor for thermal plasma properties

TL;DR

DeepPropNet is a novel operator learning-based model that accurately and efficiently predicts thermal plasma properties across various conditions, facilitating faster plasma simulations.

Contribution

It introduces DeepPropNet with single-property and multi-property architectures, enabling high-accuracy, scalable plasma property predictions using operator learning.

Findings

Achieves relative L2 errors of 10^-3 to 10^-2 in property predictions.

Demonstrates strong generalization to unseen plasma conditions.

Effectively couples with FVM and PINNs for plasma simulation tasks.

Abstract

Thermal plasma properties play a critical role in plasma simulations and plasma-related applications. However, their strong nonlinear dependence on temperature, pressure, and gas composition makes accurate and efficient evaluation challenging. In this work, an operator learning-based model, termed DeepPropNet, is proposed for fast prediction of thermodynamic and transport properties of thermal plasmas. Two architectures are developed, including a single-property model (S-DeepPropNet) and a Mixture of Experts (MoE)-based multi-property model (MoE-DeepPropNet). The proposed models learn the nonlinear mapping from plasma operating conditions to physical properties based on high-fidelity datasets. The MoE architecture enables efficient multi-property prediction within a unified framework. Predictions are performed for binary SF6-N2 and ternary C4F7N-CO2-O2 mixtures. The results show that the proposed models achieve high accuracy, with relative L2 errors on the order of 10-3 to 10-2, while maintaining strong generalization capability under unseen conditions. The applicability of DeepPropNet is further demonstrated by coupling with finite volume method (FVM) and physics-informed neural networks (PINNs). The results indicate that DeepPropNet provides an efficient and scalable approach for plasma property prediction and plasma simulations.