-
近年来,以物理信息神经网络(PINNs)为代表的人工智能计算范式在等离子体数值模拟领域获得了极大关注,但相关研究考虑的等离子体化学体系较为简化,且基于PINNs求解更为复杂的多粒子低温等离子体流体模型的研究还尚处空白。本文提出了一个通用的PINNs框架(源项解耦PINNs,Std-PINNs),用于求解多粒子低温等离子体流体模型。Std-PINNs通过引入等效正离子,并将电流连续性方程替代各粒子输运方程作为物理约束,实现了重粒子输运方程源项与电子密度、平均电子能量的解耦,极大降低了训练复杂度。本文通过两个经典放电案例(低气压氩气辉光放电、大气压氦气辉光放电)展示了Std-PINNs在求解多粒子低温等离子体流体模型的应用,并将结果与传统PINNs和有限元(FEM)模型进行了对比。结果显示,传统PINNs输出了完全错误的训练结果,而Std-PINNs与FEM结果之间的L2相对误差能达到~10-2量级,由此验证了Std-PINNs在模拟多粒子等离子体流体模型的可行性。Std-PINNs为低温等离子体模拟提供了新的思路,并拓展了深度学习方法在复杂物理系统建模中的应用。In recent years, the artificial intelligence computing paradigm represented by physics-informed neural networks (PINNs) has received great attention in the field of plasma numerical simulation. However, the plasma chemical system considered in related research is relatively simplified, and there is still a gap in the research on solving the more complex multi-particle low-temperature fluid model based on PINNs. In more complex chemical systems, the coupling relationships between particle densities as well as between particle densities and mean electron energy become more intricate. Therefore, the applicability of PINNs in dealing with sophisticated reaction systems requires further exploration and improvement. In this work, we propose a general PINNs framework (source term decoupled PINNs, Std-PINNs) for solving multi-particle low-temperature plasma fluid model. By introducing equivalent positive ions and replacing each particle transport equation with the current continuity equation as a physical constraint, Std-PINNs splits the entire solution process into the training processes of two neural networks, realizing the decoupling of the source term of the heavy particle transport equation from the electron density and mean electron energy, which greatly reduces the complexity of neural network training. This paper demonstrates the application of Std-PINNs in solving multi-particle low-temperature plasma fluid models through two classic discharge cases with different complexity of reaction systems (low-pressure argon glow discharge and atmospheric-pressure helium glow discharge) and compares the performance of Std-PINNs with that of conventional PINNs and finite element method (FEM). The results show that the training results output from the traditional PINNs are completely incorrect due to the strong coupling correlation of each physical variable through the source terms of each particle transport equation, while the L2 relative error between Std-PINNs and FEM results can be up to ~10-2 orders of magnitude, thus verifying the feasibility of Std-PINNs in simulating multi-particle plasma fluid models. Std-PINNs expands the application of deep learning methods in modeling complex physical systems and provides new ideas for low-temperature plasma simulations. In addition, this study provides novel insights into the field of artificial intelligence scientific computing: the mathematical form that describes the state of a physical system is not unique. By introducing equivalent physical variables, equations suitable for neural network solutions can be derived and combined with observable data to simplify problems.
-
Keywords:
- physics-informed neural networks /
- low-temperature plasma /
- source term decoupled /
- fluid model
-
[1] Sanito R C, You S J, Wang Y F 2021 J. Environ. Manage. 288 112380
[2] Cheng H, Xu J, Li X, Liu D, Lu X 2020 Phys. Plasmas. 27 063514
[3] Han Z J, Murdock A T, Seo D H, Bendavid A 2018 2D Mater. 5 032002
[4] Lazarou C, Belmonte T, Chiper A S, Georghiou G E 2016 Plasma Sources Sci. Technol. 25
[5] Guikema J, Miller N, Niehof J, Klein M, Walhout M 2000 Phys. Rev. Lett. 85 3817
[6] Fang Z, Wang X, Shao T, Zhang C 2017 IEEE Trans. Plasma Sci. 45 310
[7] Trelles J P 2016 J. Phys. D: Appl. Phys. 49 393002
[8] Purwins H G 2011 IEEE Trans. Plasma Sci. 39 2112
[9] Zhang Y, Ning W, Dai D, Wang Q 2019 Plasma Sci. Technol. 21 074003
[10] Wang Q, Zhou X, Dai D, Huang Z, Zhang D 2021 Plasma Sources Sci. Technol. 30 05LT01
[11] Wang Q, Ning W, Dai D, Zhang Y 2020 Plasma Process. Polym. 17 e1900182
[12] Zhang Y, Ning W, Dai D, Wang Q 2019 Plasma Sources Sci. Technol. 28 104001
[13] Biel W, Albanese R, Ambrosino R, Ariola M, Berkel M V, Bolshakova I, Brunner K J, Cavazzana R, Cecconello M, Conroy S, Dinklage A, Duran I, Dux R, Eade T, Entler S, Ericsson G, Fable E, Farina D, Figini L, Finotti C, Franke Th, Giacomelli L, Giannone L, Gonzalez W, Hjalmarsson A, Hron M, Janky F, Kallenbach A, Kogoj J, König R, Kudlacek O, Luis R, Malaquias A, Marchuk O, Marchiori G, Mattei M, Maviglia F, De Masi G, Mazon D, Meister H, Meyer K, Micheletti D, Nowak S, Piron Ch, Pironti A, Rispoli N, Rohde V, Sergienko G, El Shawish S, Siccinio M, Silva A, da Silva F, Sozzi C, Tardocchi M, Tokar M, Treutterer W, Zohm H 2019 Fus. Eng. Des. 146 465
[14] Lazarou C, Belmonte T, Chiper A S, Georghiou G E 2016 Plasma Sources Sci. Technol. 25 055023
[15] Reddy J N 1993 New York 27 14
[16] Eymard R, Gallouët T, Herbin R 2000 Handb. Numer. Anal. 7 713
[17] Bogaerts A, Tu X, Whitehead J C, Centi G, Lefferts L, Guaitella O, Azzolina-Jury F, Kim H H, Murphy A B, Schneider W F 2020 J. Phys. D: Appl. Phys. 53 443001
[18] Neyts E C 2016 Plasma Chem. Plasma Process. 36 185
[19] Mei D, Zhu X, Wu C, Ashford B, Williams P T, Tu X 2016 Appl. Catal. B 182 525
[20] Yi Y, Li S, Cui Z, Hao Y, Zhang Y, Wang L, Liu P, Tu X, Xu X, Guo H 2021 Appl. Catal. B 296 120384
[21] Raissi M, Perdikaris P, Karniadakis G E 2019 J. Comput. Phys. 378 686
[22] Raissi M, Yazdani A, Karniadakis G E 2020 Science 367 1026
[23] De Florio M, Schiassi E, Ganapol B D, Furfaro R 2021 Phys. Fluids 33 047110
[24] Arzani A, Wang J X, D’Souza R M 2021 Phys. Fluids 33 071905
[25] Kawaguchi S, Takahashi K, Ohkama H, Satoh K 2020 Plasma Sources Sci. Technol. 29 025021
[26] Cai S, Wang Z, Wang S, Perdikaris P, Karniadakis G E 2021 J. Heat Transfer 143 102719
[27] Laubscher R 2021 Phys. Fluids 33 087101
[28] Mathews A, Francisquez M, Hughes J W, Hatch D R, Zhu B, Rogers B N 2021 Phys. Rev. E 104 025205
[29] Zhong L, Gu Q, Wu B 2020 Comput. Phys. Commun. 257 107496
[30] Zhong L, Wu B, Wang Y 2022 Phys. Fluids 34 087116
[31] Wan J, Wang Q, Dai D, Ning W 2019 Phys. Plasmas 26 103510
[32] Wang Q, Ning W, Dai D, Zhang Y, Ouyang J 2019 J. Phys. D: Appl. Phys. 52 205201
[33] Wang Q, Ning W, Dai D, Zhang Y 2020 Plasma Process. Polym. 17 1900182
[34] Glorot X, Bengio Y 2010 Proceedings of the 13th International Conference on Artificial Intelligence and Statistics Sardinia, Italy, May 13—15, 2010 pp249–256
[35] Liu D C, Nocedal J 1989 Math. Program. 45 503
[36] Kingma D P, Ba J L 2014 arXiv:1412.6980 [cs.LG]
[37] Wang S, Yu X, Perdikaris P 2022 J. Comput. Phys. 449 110768
[38] Hagelaar G J M, Kroesen G M W 2000 J. Comput. Phys. 159 1
[39] Blickle V, Speck T, Lutz C, Seifert U, Bechinger C 2007 Phys. Rev. Lett. 98 210601
[40] Hagelaar G J M, Pitchford L C 2005 Plasma Sources Sci. Technol. 14 722
[41] Wang Q, Economou D J, Donnelly V M 2006 J. Appl. Phys. 100 023301
[42] Dyatko N A, Ionikh Y Z, Kochetov I V, Marinov D L, Meshchanov A V, Napartovich A P, Petrov F B, Starostin S A 2008 J. Phys. D: Appl. Phys. 41 055204
[43] Deloche R, Monchicourt P, Cheret M, Lambert F 1976 Phys. Rev. A 13 1140
[44] Hagelaar G J M, De Hoog F J, Kroesen G M W 2000 Phys. Rev. E 62 1452
[45] Hassé H R, Cook W R 1931 Philos. Mag. J. Sci. 12 554
[46] Shrestha A K, Shrestha R, Baniya H B, Tyata R B, Subedi D P, Wong C S 2014 relation 2 1
[47] Wang Q, Ning W, Dai D, Zhang Y, Ouyang J 2019 J. Phys. D: Appl. Phys. 52 205201
[48] Wang Q, Dai D, Ning W, Zhang Y 2021 J. Phys. D: Appl. Phys. 54 115203
[49] Mathews A, Francisquez M, Hughes J W, Hatch D R, Zhu B, Rogers B N 2021 Phys. Rev. E 104 025205
[50] Tochikubo F, Shirai N, Uchida S 2011 Appl. Phys. Express 4 056001
[51] Zhang Y, Ning W, Dai D, Wang Q 2019 Plasma Sources Sci. Technol. 28 075003
[52] Pitchford L C, Alves L L, Bartschat K, Biagi S F, Bordage M, Bray I, Brion C E, Brunger M J, Campbell L, Chachereau A, Chaudhury B, Christophorou L G, Carbone E, Dyatko N A, Franck C M, Fursa D V., Gangwar R K, Guerra V, Haefliger P, Hagelaar G J M, Hoesl A, Itikawa Y, Kochetov I V., McEachran R P, Morgan W L, Napartovich A P, Puech V, Rabie M, Sharma L, Srivastava R, Stauffer A D, Tennyson J, de Urquijo J, van Dijk J, Viehland L A, Zammit M C, Zatsarinny O, Pancheshnyi S 2017 Plasma Process. Polym. 14 1600098
[53] Zhu X M, Pu Y K 2009 J. Phys. D: Appl. Phys. 43 015204
[54] Riccardi C, Barni R 2012 Chem. Kinet. 10 38396
[55] Liu D X, Iza F, Wang X H, Ma Z Z, Rong M Z, Kong M G 2013 Plasma Sources Sci. Technol. 22 055016
[56] Zhu M, Zhong A, Dai D, Wang Q, Shao T, Ostrikov K K 2022 J. Phys. D: Appl. Phys. 55 355201
[57] Pietanza L D, Guaitella O, Aquilanti V, Armenise I, Bogaerts A, Capitelli M, Colonna G, Guerra V, Engeln R, Kustova E 2021 Eur. Phys. J. D 75 237
计量
- 文章访问数: 93
- PDF下载量: 3
- 被引次数: 0