| GENERAL |
|
|
|
|
Data-Driven Ai- and Bi-Soliton of the Cylindrical Korteweg–de Vries Equation via Prior-Information Physics-Informed Neural Networks |
| Shifang Tian1, Biao Li1*, and Zhao Zhang2 |
1School of Mathematics and Statistics, Ningbo University, Ningbo 315211, China
2Guangdong Provincial Key Laboratory of Nanophotonic Functional Materials and Devices, South China Normal University, Guangzhou 510631, China
|
|
| Cite this article: |
|
Shifang Tian, Biao Li, and Zhao Zhang 2024 Chin. Phys. Lett. 41 030201 |
|
|
|
|
Abstract By the modifying loss function MSE and training area of physics-informed neural networks (PINNs), we propose a neural networks model, namely prior-information PINNs (PIPINNs). We demonstrate the advantages of PIPINNs by simulating Ai- and Bi-soliton solutions of the cylindrical Korteweg–de Vries (cKdV) equation. Numerical experiments show that our proposed model is able not only to simulate these solitons using the cKdV equation, but also to significantly improve its simulation capability. Compared with the original PINNs, the prediction accuracy of our proposed model is improved by one to three orders of magnitude. Moreover, the accuracy of the PIPINNs is further improved by adding the restriction of conservation of energy.
|
|
|
Received: 09 January 2024
Published: 30 March 2024
|
|
| PACS: |
02.30.Ik
|
(Integrable systems)
|
| |
02.60.-x
|
(Numerical approximation and analysis)
|
| |
07.05.Mh
|
(Neural networks, fuzzy logic, artificial intelligence)
|
| |
02.60.Cb
|
(Numerical simulation; solution of equations)
|
|
|
|
|
|
| [1] | Maxon S and Viecelli J 1974 Phys. Fluids 17 1614 |
| [2] | Stepanyants Y A 1981 Wave Motion 3 335 |
| [3] | Nakamura A and Chen H H 1981 J. Phys. Soc. Jpn. 50 711 |
| [4] | Hu W C, Ren J L, and Stepanyants Y 2023 Symmetry 15 413 |
| [5] | Hu W C, Zhang Z, Guo Q, and Stepanyants Y 2024 Chaos 34 013138 |
| [6] | Zhang Z, Hu W C, Guo Q, and Stepanyants Y 2024 Chaos 34 013132 |
| [7] | He K M, Zhang X Y, Ren S Q, and Sun J 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016, pp 770–778 |
| [8] | van den Oord A, Dieleman S, Zen H, Simonyan K, Vinyals O, Graves A, Kalchbrenner N, Senior A, and Kavukcuoglu K 2016 arXiv:1609.03499 [cs.SD] |
| [9] | Heaton J, Goodfellow I, Bengio Y, and Courville A 2018 Genet. Program. Evolvable Mach. 19 305 |
| [10] | Alipanahi B, Delong A, Weirauch M T, and Frey B J 2015 Nat. Biotechnol. 33 831 |
| [11] | Raissi M and Karniadakis G E 2018 J. Comput. Phys. 357 125 |
| [12] | Lorin E and Yang X 2022 Comput. Phys. Commun. 280 108474 |
| [13] | Bihlo A and Popovych R O 2022 J. Comput. Phys. 456 111024 |
| [14] | Jagtap A D, Mao Z P, Adams N, and Karniadakis G E 2022 J. Comput. Phys. 466 111402 |
| [15] | Peng W Q and Chen Y 2022 Physica D 435 133274 |
| [16] | Pu J C and Chen Y 2022 Chaos Solitons & Fractals 160 112182 |
| [17] | Lin S N and Chen Y 2022 J. Comput. Phys. 457 111053 |
| [18] | Tian S F and Li B 2023 Acta Phys. Sin. 72 100202 (in Chinese) |
| [19] | Li J H and Li B 2022 Chaos Solitons & Fractals 164 112712 |
| [20] | Tian S F, Niu Z J, and Li B 2023 Nonlinear Dyn. 111 16467 |
| [21] | Tian S F, Cao C C, and Li B 2023 Results Phys. 52 106842 |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
