DeepONet-based fast calculation of net emission coefficients of arc plasmas

The radiation transport and the corresponding radiation coefficients of switching arcs play a crucial role in understanding the arc extinguishing process. To develop a simpler and more efficient method for calculating net emission coefficients (NEC), this paper proposes a fast calculation model of NEC based on spectral radiation theory and Deep Operator Network (DeepONet). This model takes gas mixing proportions, temperatures, pressures, and arc radius as input, and predicts NEC at given conditions without time-consuming and complex calculation. To validate the performance of the proposed model, we take SF<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">6</inf>-N<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> arc plasma as an example and calculate NEC under different conditions. The results demonstrate that the proposed DeepONet-based model significantly enhances computational efficiency and accuracy for NEC calculation compared to traditional methods while exhibiting strong generalization capability. Furthermore, it reveals that in the DeepONet-based model, the complexity of the trunk network has a more pronounced effect on computational accuracy than that of the branch network, highlighting the importance of optimizing the trunk network structure to improve overall computational performance.