Real-Time Calculation of CO₂ Conversion in Radio-Frequency Discharges under Martian Pressure by Introducing Deep Neural Network

In recent years, the in situ resource utilization of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>CO</mi><mn>2</mn></msub></semantics></math></inline-formula> in the Martian atmosphere by low-temperature plasma technology has garnered significant attention. However, numerical simulation is extremely time-consuming for modeling the complex <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>CO</mi><mn>2</mn></msub></semantics></math></inline-formula> plasma, involving tens of species and hundreds of reactions, especially under Martian pressure. In this study, a deep neural network (DNN) with multiple hidden layers is introduced to investigate the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>CO</mi><mn>2</mn></msub></semantics></math></inline-formula> conversion in radio-frequency (RF) discharges at a given power density under Martian pressure in almost real time. After training on the dataset obtained from the fluid model or experimental measurements, the DNN shows the ability to accurately and efficiently predict the various discharge characteristics and plasma chemistry of RF <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>CO</mi><mn>2</mn></msub></semantics></math></inline-formula> discharge even in seconds. Compared with conventional fluid models, the computational efficiency of the DNN is improved by nearly <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mn>10</mn><mn>6</mn></msup></semantics></math></inline-formula> times; thus, a real-time calculation of RF <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>CO</mi><mn>2</mn></msub></semantics></math></inline-formula> discharge can almost be achieved. The DNN can provide an enormous amount of data to enhance the simulation results due to the very high computational efficiency. The numerical data also suggest that the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>CO</mi><mn>2</mn></msub></semantics></math></inline-formula> conversion increases with driving frequency at a fixed power density. This study shows the ability of the DNN-based approach to investigate <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>CO</mi><mn>2</mn></msub></semantics></math></inline-formula> conversion in RF discharges for various applications, providing a promising tool for the modeling of complex non-thermal plasmas.