Search

Article

x

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

allaPINNs: A physics-informed neural network with improvement of information representation and loss optimization for solving partial differential equations

ZHANG Zhaoyang WANG Qingwang

Citation:

allaPINNs: A physics-informed neural network with improvement of information representation and loss optimization for solving partial differential equations

ZHANG Zhaoyang, WANG Qingwang
cstr: 32037.14.aps.74.20250707
Article Text (iFLYTEK Translation)
PDF
HTML
Get Citation
  • Physics-informed neural networks (PINNs) have recently garnered significant attention as a meshless solution framework for solving partial differential equations (PDEs) in the context of AI-assisted scientific research (AI for Science). However, traditional PINNs exhibit certain limitations. On one hand, their network architecture, typically multilayer perceptrons (MLPs) with unidirectional information transfer, struggles to effectively capture key features embedded in sequential data, resulting in weak information characterization. On the other hand, the loss function of PINNs, a quadratic penalty function embedded with physical constraints, has an unconstrained and infinitely inflated penalty factor that affects the efficiency of the model’s training optimization search. To address these challenges, this paper proposes an improved PINN based on information representation and loss optimization, termed allaPINNs, which aims to enhance the model’s key feature extraction capability and training optimization search ability, thereby improving its accuracy and generalization for solving numerical solutions of PDEs. In terms of information characterization, allaPINNs introduces efficient linear attention (LA) to enhance the model’s ability to identify key features while reducing the computational complexity of dynamic weighting. In terms of loss optimization, allaPINNs reconstructs the objective loss function by introducing the augmented Lagrangian (AL) function, utilizing learnable Lagrangian multipliers and penalty factors to efficiently regulate the interaction of each loss residual term. The feasibility of allaPINNs is validated through four benchmark equations: Helmholtz, Black-Scholes, Burgers, and nonlinear Schrödinger. The results demonstrate that allaPINNs can effectively solve various PDEs of different complexities and exhibit excellent numerical solution prediction accuracy and generalization ability. Compared to the current state-of-the-art PINNs, the predictive accuracy is improved by one to two orders of magnitude.
      Corresponding author: WANG Qingwang, wangqingwang@kust.edu.cn
    • Funds: Project supported by the Young Scientists Fund of the National Natural Science Foundation of China (Grant No. 62201237) and the Major Science and Technology Program of Yunnan Province, China (Grant Nos. 202202AD080013, 202302AG050009).
    [1]

    Jin X, Cai S, Li H, Karniadakis G E 2021 J. Comput. Phys. 426 109951Google Scholar

    [2]

    Roul P, Goura V P 2020 J. Comput. Appl. Math. 363 464Google Scholar

    [3]

    Pu J C, Li J, Chen Y 2021 Chin. Phys. B 30 60202Google Scholar

    [4]

    Cuomo S, Di Cola V S, Giampaolo F, Rozza G, Raissi M, Piccialli F 2022 J. Sci. Comput. 92 88Google Scholar

    [5]

    Samaniego E, Anitescu C, Goswami S, Nguyen-Thanh V M, Guo H, Hamdia K, Zhuang X, Rabczuk T 2020 Comput. Methods Appl. Mech. Eng. 362 112790Google Scholar

    [6]

    Taylor C A, Hughes T J, Zarins C K 1998 Comput. Methods Appl. Mech. Eng. 158 155Google Scholar

    [7]

    Zhang Y 2009 Appl. Math. Comput. 215 524Google Scholar

    [8]

    Van Hoecke L, Boeye D, Gonzalez-Quiroga A, Patience G S, Perreault P 2023 Can. J. Chem. Eng. 101 545Google Scholar

    [9]

    Hasan F, Ali H, Arief H A 2025 Int. J. Appl. Comput. Math. 11 1Google Scholar

    [10]

    Choo Y S, Choi N, Lee B C 2010 Appl. Math. Modell. 34 14Google Scholar

    [11]

    Lawrence N D, Montgomery J 2024 R. Soc. Open Sci. 11 231130Google Scholar

    [12]

    Si Z Z, Wang D L, Zhu B W, Ju Z T, Wang X P, Liu W, Malomed B A, Wang Y Y, Dai C Q 2024 Laser Photonics Rev. 18 2400097Google Scholar

    [13]

    Fang Y, Han H B, Bo W B, Liu W, Wang B H, Wang Y Y, Dai C Q 2023 Opt. Lett. 48 779Google Scholar

    [14]

    Li N, Xu S, Sun Y, Chen Q 2025 Nonlinear Dyn. 113 767Google Scholar

    [15]

    Mouton L, Reiter F, Chen Y, Rebentrost P 2024 Phys. Rev. A 110 022612Google Scholar

    [16]

    Zhu M, Feng S, Lin Y, Lu L 2023 Comput. Methods Appl. Mech. Eng. 416 116300Google Scholar

    [17]

    Li X, Liu Z, Cui S, Luo C, Li C, Zhuang Z 2019 Comput. Methods Appl. Mech. Eng. 347 735Google Scholar

    [18]

    Wang S, Teng Y, Perdikaris P 2021 SIAM J. Sci. Comput. 43 A3055Google Scholar

    [19]

    Chew A W Z, He R, Zhang L 2025 Arch. Comput. Methods Eng. 32 399Google Scholar

    [20]

    Bai J, Rabczuk T, Gupta A, Alzubaidi L, Gu Y 2023 Comput. Mech. 71 543Google Scholar

    [21]

    Son S, Lee H, Jeong D, Oh K Y, Sun K H 2023 Adv. Eng. Inf. 57 102035Google Scholar

    [22]

    方泽, 潘泳全, 戴栋, 张俊勃 2024 物理学报 73 145201Google Scholar

    Fang Z, Pan Y Q, Dai D, Zhang J B 2024 Acta Phys. Sin. 73 145201Google Scholar

    [23]

    Raissi M, Perdikaris P, Karniadakis G E 2019 J. Comput. Phys. 378 686Google Scholar

    [24]

    Hornik K 1991 Neural Networks 4 251Google Scholar

    [25]

    Baydin A G, Pearlmutter B A, Radul A A, Siskind J M 2018 J. Mach. Learn. Res. 18 1

    [26]

    De Ryck T, Mishra S 2024 Acta Numer. 33 633Google Scholar

    [27]

    Karniadakis G E, Kevrekidis I G, Lu L, Perdikaris P, Wang S, Yang L 2021 Nat. Rev. Phys. 3 422Google Scholar

    [28]

    Ren P, Rao C, Liu Y, Wang J X, Sun H 2022 Comput. Methods Appl. Mech. Eng. 389 114399Google Scholar

    [29]

    Lei L, He Y, Xing Z, Li Z, Zhou Y 2025 IEEE Trans. Ind. Inf. 21 5411Google Scholar

    [30]

    Yuan B, Wang H, Heitor A, Chen X 2024 J. Comput. Phys. 515 113284Google Scholar

    [31]

    Wang Y, Sun J, Bai J, Anitescu C, Eshaghi M S, Zhuang X, Rabczuk T, Liu Y 2025 Comput. Methods Appl. Mech. Eng. 433 117518Google Scholar

    [32]

    Li L L, Zhang Y P, Wang G H, Xia K L 2025 Nat. Mach. Intell. 7 1346Google Scholar

    [33]

    Jahani-Nasab M, Bijarchi M A 2024 Sci. Rep. 14 23836Google Scholar

    [34]

    Yu J, Lu L, Meng X, Karniadakis G E 2022 Comput. Methods Appl. Mech. Eng. 393 114823Google Scholar

    [35]

    Jiao Y, Lai Y, Lo Y, Wang Y, Yang Y 2024 Anal. Appl. 22 57Google Scholar

    [36]

    Yang A, Xu S, Liu H, Li N, Sun Y 2025 Nonlinear Dyn. 113 1523Google Scholar

    [37]

    Li Y, Zhou Z, Ying S 2022 J. Comput. Phys. 451 110884Google Scholar

    [38]

    Jacot A, Gabriel F, Hongler C 2018 32nd Conference on Neural Information Processing Systems (NIPS 2018) Montreal, Canada, December 3–8, 2018 p8570

    [39]

    Xiang Z, Peng W, Liu X, Yao W 2022 Neurocomputing 496 11Google Scholar

    [40]

    Tancik M, Srinivasan P, Mildenhall B, Fridovich-Keil S, Raghavan N, Singhal U, Ramamoorthi R, Barron J, Ng R 2020 34th Conference on Neural Information Processing Systems (NeurIPS 2020) Vancouver, Canada, December 6–12, 2020 p7537

    [41]

    Zhang Z, Wang Y, Tan S, Xia B, Luo Y 2025 Neurocomputing 625 129429Google Scholar

    [42]

    Zhang W, Li H, Tang L, Gu X, Wang L, Wang L 2022 Acta Geotech. 17 1367Google Scholar

    [43]

    Zhang Z, Wang Q, Zhang Y, Shen T, Zhang W 2025 Sci. Rep. 15 10523Google Scholar

    [44]

    Cybenko G 1989 Math. Control Signals Syst. 2 303Google Scholar

    [45]

    Wang C, Ma C, Zhou J 2014 J. Global Optim. 58 51Google Scholar

    [46]

    Yi K, Zhang Q, Fan W, Wang S, Wang P, He H, An N, Lian D, Cao L, Niu Z 2023 Adv. Neural Inf. Process. Syst. 36 76656Google Scholar

    [47]

    Durstewitz D, Koppe G, Thurm M I 2023 Nat. Rev. Neurosci. 24 693Google Scholar

    [48]

    Chang G, Hu S, Huang H 2023 J. Supercomput. 79 6991Google Scholar

    [49]

    Ocal H 2025 Arabian J. Sci. Eng. 50 1097Google Scholar

    [50]

    Wu H C 2009 Eur. J. Oper. Res. 196 49Google Scholar

    [51]

    Curtis F E, Jiang H, Robinson D P 2015 Math. Program. 152 201Google Scholar

    [52]

    Sun D, Sun J, Zhang L 2008 Math. Program. 114 349Google Scholar

    [53]

    Kanzow C, Steck D 2019 Math. Program. 177 425Google Scholar

    [54]

    Rockafellar R T 2023 Math. Program. 198 159Google Scholar

    [55]

    Dampfhoffer M, Mesquida T, Valentian A, Anghel L 2023 IEEE Trans. Neural Networks Learn. Syst. 35 11906Google Scholar

    [56]

    Humbird K D, Peterson J L, McClarren R G 2018 IEEE Trans. Neural Networks Learn. Syst. 30 1286Google Scholar

    [57]

    Zhang Z, Wang Q, Zhang Y, Shen T 2025 Digital Signal Process. 156 104766Google Scholar

    [58]

    Zhou P, Xie X, Lin Z, Yan S 2024 IEEE Trans. Pattern Anal. Mach. Intell. 46 6486Google Scholar

    [59]

    Rather I H, Kumar S, Gandomi A H 2024 Artif. Intell. Rev. 57 226Google Scholar

    [60]

    Thulasidharan K, Priya N V, Monisha S, Senthilvelan M 2024 Phys. Lett. A 511 129551Google Scholar

    [61]

    Son H, Cho S W, Hwang H J 2023 Neurocomputing 548 126424Google Scholar

    [62]

    Song Y, Wang H, Yang H, Taccari M L, Chen X 2024 J. Comput. Phys. 501 112781Google Scholar

  • 图 1  allaPINNs网络结构

    Figure 1.  allaPINNs network structure.

    图 2  使用allaPINNs求解基准方程的预测解和解析解对比结果

    Figure 2.  Comparison of predicted and analytical solutions for solving the benchmark equations using allaPINNs.

    图 3  使用allaPINNs在$ t = 0,\; 0.3,\; 0.66,\; 0.88 $四个时刻求解非线性Schrödinger方程的振幅快照

    Figure 3.  Snapshots of amplitudes for solving nonlinear Schrödinger equation at four moments $ t = 0,\; 0.3,\; 0.66,\; 0.88 $ using allaPINNs

    图 4  使用allaPINNs求解基准方程的逐点绝对误差分布

    Figure 4.  Pointwise absolute error distributions for solving benchmark equations using allaPINNs.

    图 5  最优拉格朗日乘子$ \lambda_{*} $的频率直方图, 其中Helmholtz方程包含$ \lambda_{1}^{*} $, Black-Scholes方程包含$ \lambda_{1}^{*}{\text{—}}\lambda_{3}^{*} $, Burgers方程包含$ \lambda_{1}^{*} $和$ \lambda_{2}^{*} $, 非线性Schrödinger方程包含$ \lambda_{1}^{*}{\text{—}}\lambda_{6}^{*} $

    Figure 5.  Frequency histogram of the optimal Lagrangian multipliers $ \lambda^{*} $, where the Helmholtz equation contains $ \lambda_{1}^{*} $, the Black-Scholes equation contains $ \lambda_{1}^{*}-\lambda_{3}^{*} $, the Burgers equation contains $ \lambda_{1}^{*}, \;\lambda_{2}^{*} $, and nonlinear Schrödinger equation contains $ \lambda_{1}^{*}-\lambda_{6}^{*} $.

    图 6  惩罚因子σ的学习过程, 其中(a), (b), (c), (d)中的$ \sigma^{*} $分别位于第48665, 49420, 43467和48933轮迭代, 对应的数值分别为2517.21, 35.45, 5.02和52.08

    Figure 6.  Learning process of the penalty factor σ, where $ \sigma^{*} $ for (a), (b), (c), (d) are located at rounds 48665, 49420, 43467, and 48933, corresponding to values of 2517.21, 35.45, 5.02, and 52.08, respectively.

    图 7  allaPINNs在训练过程中的$ L^{2} $相对泛化误差

    Figure 7.  The $ L^{2} $ relative generalization error of allaPINNs during training.

    表 1  allaPINNs模型和当前先进PINNs模型求解四个基准方程实验的$ L^{2} $相对误差对比结果

    Table 1.  Comparison of $ L^{2} $ relative errors between allaPINNs model and current state-of-the-art PINNs model for solving the four benchmark equations.

    物理信息神经求解器
    求解方程 PINNs[23] AL-PINNs[61] f-PICNN[30] KINN[31] allaPINNs (本文)
    Helmholtz 5.63 × 10–2 1.82 × 10–3 2.51 × 10–3 1.08 × 10–3 8.06 × 10–4
    Black-Scholes 7.18 × 10–2 7.41 × 10–3 5.24 × 10–3 4.35 × 10–3 3.48 × 10–4
    Burgers 7.04 × 10–2 3.39 × 10–3 2.49 × 10–3 3.02 × 10–3 8.31 × 10–4
    非线性Schrödinger 2.09 × 10–2 1.55 × 10–3 4.18 × 10–3 1.37 × 10–3 6.71 × 10–4
    DownLoad: CSV

    表 2  allaPINNs模型在不同网络结构和损失函数条件下的平均$ L^{2} $相对误差对比结果

    Table 2.  Comparison of mean $ L^{2} $ relative errors of allaPINNs model with different network structure and loss function conditions.

    网络结构 基准方程平均$ L^{2} $相对误差 损失函数 基准方程平均$ L^{2} $相对误差
    MLPs 7.26 × 10–2 罚函数 8.55 × 10–3
    CNN 3.09 × 10–3 罚函数 (高斯噪声) 1.63 × 10–3
    LA 6.61 × 10–4 AL 6.61 × 10–4
    DownLoad: CSV

    表 B1  各对比模型中超参数配置和求解基准方程时间消耗

    Table B1.  Hyperparameter configuration and time consumption for solving the benchmark equations in each comparison model.

    物理信息神经求解器
    对比指标 PINNs[23] AL-PINNs[61] f-PICNN[30] KINN[31] allaPINNs (本文)
    网络层数 8 8 6 5 5
    神经元数量 200 256 128 80 64
    参数学习率 1 × 10–3 1 × 10–4 1 × 10–4 1 × 10–4 1 × 10–3
    求解Helmholtz时间消耗/s 1476 1520 1529 1606 1513
    求解Black-Scholes时间消耗/s 1538 1585 1604 1714 1624
    求解Burgers时间消耗/s 1519 1574 1593 1636 1588
    求解非线性Schrödinger时间消耗/s 1545 1628 1650 1745 1661
    DownLoad: CSV
  • [1]

    Jin X, Cai S, Li H, Karniadakis G E 2021 J. Comput. Phys. 426 109951Google Scholar

    [2]

    Roul P, Goura V P 2020 J. Comput. Appl. Math. 363 464Google Scholar

    [3]

    Pu J C, Li J, Chen Y 2021 Chin. Phys. B 30 60202Google Scholar

    [4]

    Cuomo S, Di Cola V S, Giampaolo F, Rozza G, Raissi M, Piccialli F 2022 J. Sci. Comput. 92 88Google Scholar

    [5]

    Samaniego E, Anitescu C, Goswami S, Nguyen-Thanh V M, Guo H, Hamdia K, Zhuang X, Rabczuk T 2020 Comput. Methods Appl. Mech. Eng. 362 112790Google Scholar

    [6]

    Taylor C A, Hughes T J, Zarins C K 1998 Comput. Methods Appl. Mech. Eng. 158 155Google Scholar

    [7]

    Zhang Y 2009 Appl. Math. Comput. 215 524Google Scholar

    [8]

    Van Hoecke L, Boeye D, Gonzalez-Quiroga A, Patience G S, Perreault P 2023 Can. J. Chem. Eng. 101 545Google Scholar

    [9]

    Hasan F, Ali H, Arief H A 2025 Int. J. Appl. Comput. Math. 11 1Google Scholar

    [10]

    Choo Y S, Choi N, Lee B C 2010 Appl. Math. Modell. 34 14Google Scholar

    [11]

    Lawrence N D, Montgomery J 2024 R. Soc. Open Sci. 11 231130Google Scholar

    [12]

    Si Z Z, Wang D L, Zhu B W, Ju Z T, Wang X P, Liu W, Malomed B A, Wang Y Y, Dai C Q 2024 Laser Photonics Rev. 18 2400097Google Scholar

    [13]

    Fang Y, Han H B, Bo W B, Liu W, Wang B H, Wang Y Y, Dai C Q 2023 Opt. Lett. 48 779Google Scholar

    [14]

    Li N, Xu S, Sun Y, Chen Q 2025 Nonlinear Dyn. 113 767Google Scholar

    [15]

    Mouton L, Reiter F, Chen Y, Rebentrost P 2024 Phys. Rev. A 110 022612Google Scholar

    [16]

    Zhu M, Feng S, Lin Y, Lu L 2023 Comput. Methods Appl. Mech. Eng. 416 116300Google Scholar

    [17]

    Li X, Liu Z, Cui S, Luo C, Li C, Zhuang Z 2019 Comput. Methods Appl. Mech. Eng. 347 735Google Scholar

    [18]

    Wang S, Teng Y, Perdikaris P 2021 SIAM J. Sci. Comput. 43 A3055Google Scholar

    [19]

    Chew A W Z, He R, Zhang L 2025 Arch. Comput. Methods Eng. 32 399Google Scholar

    [20]

    Bai J, Rabczuk T, Gupta A, Alzubaidi L, Gu Y 2023 Comput. Mech. 71 543Google Scholar

    [21]

    Son S, Lee H, Jeong D, Oh K Y, Sun K H 2023 Adv. Eng. Inf. 57 102035Google Scholar

    [22]

    方泽, 潘泳全, 戴栋, 张俊勃 2024 物理学报 73 145201Google Scholar

    Fang Z, Pan Y Q, Dai D, Zhang J B 2024 Acta Phys. Sin. 73 145201Google Scholar

    [23]

    Raissi M, Perdikaris P, Karniadakis G E 2019 J. Comput. Phys. 378 686Google Scholar

    [24]

    Hornik K 1991 Neural Networks 4 251Google Scholar

    [25]

    Baydin A G, Pearlmutter B A, Radul A A, Siskind J M 2018 J. Mach. Learn. Res. 18 1

    [26]

    De Ryck T, Mishra S 2024 Acta Numer. 33 633Google Scholar

    [27]

    Karniadakis G E, Kevrekidis I G, Lu L, Perdikaris P, Wang S, Yang L 2021 Nat. Rev. Phys. 3 422Google Scholar

    [28]

    Ren P, Rao C, Liu Y, Wang J X, Sun H 2022 Comput. Methods Appl. Mech. Eng. 389 114399Google Scholar

    [29]

    Lei L, He Y, Xing Z, Li Z, Zhou Y 2025 IEEE Trans. Ind. Inf. 21 5411Google Scholar

    [30]

    Yuan B, Wang H, Heitor A, Chen X 2024 J. Comput. Phys. 515 113284Google Scholar

    [31]

    Wang Y, Sun J, Bai J, Anitescu C, Eshaghi M S, Zhuang X, Rabczuk T, Liu Y 2025 Comput. Methods Appl. Mech. Eng. 433 117518Google Scholar

    [32]

    Li L L, Zhang Y P, Wang G H, Xia K L 2025 Nat. Mach. Intell. 7 1346Google Scholar

    [33]

    Jahani-Nasab M, Bijarchi M A 2024 Sci. Rep. 14 23836Google Scholar

    [34]

    Yu J, Lu L, Meng X, Karniadakis G E 2022 Comput. Methods Appl. Mech. Eng. 393 114823Google Scholar

    [35]

    Jiao Y, Lai Y, Lo Y, Wang Y, Yang Y 2024 Anal. Appl. 22 57Google Scholar

    [36]

    Yang A, Xu S, Liu H, Li N, Sun Y 2025 Nonlinear Dyn. 113 1523Google Scholar

    [37]

    Li Y, Zhou Z, Ying S 2022 J. Comput. Phys. 451 110884Google Scholar

    [38]

    Jacot A, Gabriel F, Hongler C 2018 32nd Conference on Neural Information Processing Systems (NIPS 2018) Montreal, Canada, December 3–8, 2018 p8570

    [39]

    Xiang Z, Peng W, Liu X, Yao W 2022 Neurocomputing 496 11Google Scholar

    [40]

    Tancik M, Srinivasan P, Mildenhall B, Fridovich-Keil S, Raghavan N, Singhal U, Ramamoorthi R, Barron J, Ng R 2020 34th Conference on Neural Information Processing Systems (NeurIPS 2020) Vancouver, Canada, December 6–12, 2020 p7537

    [41]

    Zhang Z, Wang Y, Tan S, Xia B, Luo Y 2025 Neurocomputing 625 129429Google Scholar

    [42]

    Zhang W, Li H, Tang L, Gu X, Wang L, Wang L 2022 Acta Geotech. 17 1367Google Scholar

    [43]

    Zhang Z, Wang Q, Zhang Y, Shen T, Zhang W 2025 Sci. Rep. 15 10523Google Scholar

    [44]

    Cybenko G 1989 Math. Control Signals Syst. 2 303Google Scholar

    [45]

    Wang C, Ma C, Zhou J 2014 J. Global Optim. 58 51Google Scholar

    [46]

    Yi K, Zhang Q, Fan W, Wang S, Wang P, He H, An N, Lian D, Cao L, Niu Z 2023 Adv. Neural Inf. Process. Syst. 36 76656Google Scholar

    [47]

    Durstewitz D, Koppe G, Thurm M I 2023 Nat. Rev. Neurosci. 24 693Google Scholar

    [48]

    Chang G, Hu S, Huang H 2023 J. Supercomput. 79 6991Google Scholar

    [49]

    Ocal H 2025 Arabian J. Sci. Eng. 50 1097Google Scholar

    [50]

    Wu H C 2009 Eur. J. Oper. Res. 196 49Google Scholar

    [51]

    Curtis F E, Jiang H, Robinson D P 2015 Math. Program. 152 201Google Scholar

    [52]

    Sun D, Sun J, Zhang L 2008 Math. Program. 114 349Google Scholar

    [53]

    Kanzow C, Steck D 2019 Math. Program. 177 425Google Scholar

    [54]

    Rockafellar R T 2023 Math. Program. 198 159Google Scholar

    [55]

    Dampfhoffer M, Mesquida T, Valentian A, Anghel L 2023 IEEE Trans. Neural Networks Learn. Syst. 35 11906Google Scholar

    [56]

    Humbird K D, Peterson J L, McClarren R G 2018 IEEE Trans. Neural Networks Learn. Syst. 30 1286Google Scholar

    [57]

    Zhang Z, Wang Q, Zhang Y, Shen T 2025 Digital Signal Process. 156 104766Google Scholar

    [58]

    Zhou P, Xie X, Lin Z, Yan S 2024 IEEE Trans. Pattern Anal. Mach. Intell. 46 6486Google Scholar

    [59]

    Rather I H, Kumar S, Gandomi A H 2024 Artif. Intell. Rev. 57 226Google Scholar

    [60]

    Thulasidharan K, Priya N V, Monisha S, Senthilvelan M 2024 Phys. Lett. A 511 129551Google Scholar

    [61]

    Son H, Cho S W, Hwang H J 2023 Neurocomputing 548 126424Google Scholar

    [62]

    Song Y, Wang H, Yang H, Taccari M L, Chen X 2024 J. Comput. Phys. 501 112781Google Scholar

  • [1] SUN Kangsheng, HAN Chao, QIN Haifeng, GU Tao, LI Wei, YU Cheng. Fast generation algorithm of high-quality holograms based on attention convolutional neural network. Acta Physica Sinica, 2025, 74(8): 084203. doi: 10.7498/aps.74.20241713
    [2] WANG Xiang, ZHOU Yishen, ZHANG Xuange, CHEN Xihao. Convolutional network single-pixel imaging with fusion attention mechanism. Acta Physica Sinica, 2025, 74(8): 084202. doi: 10.7498/aps.74.20250010
    [3] LI Jun, SU Jin, HAN Xiaoxiang, ZHU Weijie, YANG Ruixia, ZHANG Haiyang, YAN Xiang’an, ZHANG Yunjie, WANG Feiran. Research on pulse transmission dynamics in optical fiber based on intelligent algorithms. Acta Physica Sinica, 2025, 74(6): 060201. doi: 10.7498/aps.74.20241473
    [4] LIU Ming, ZHANG Siqi, LI Hong. Dynamic analysis of shortcut to adiabaticity based on physical information neural network. Acta Physica Sinica, 2025, 74(11): 114204. doi: 10.7498/aps.74.20250147
    [5] WANG Yuduo, CHEN Jiaxin, LI Biao. Solving nonlinear Schrödinger equations and parameter discovery via extended mixed-training physics-informed neural networks. Acta Physica Sinica, 2025, 74(16): 160201. doi: 10.7498/aps.74.20250422
    [6] Fang Ze, Pan Yong-Quan, Dai Dong, Zhang Jun-Bo. Physics-informed neural networks based on source term decoupled and its application in discharge plasma simulation. Acta Physica Sinica, 2024, 73(14): 145201. doi: 10.7498/aps.73.20240343
    [7] Tian Shi-Fang, Li Biao. Solving complex nonlinear problems based on gradient-optimized physics-informed neural networks. Acta Physica Sinica, 2023, 72(10): 100202. doi: 10.7498/aps.72.20222381
    [8] Fang Bo-Lang, Wang Jian-Guo, Feng Guo-Bin. Calculation of spot entroid based on physical informed neural networks. Acta Physica Sinica, 2022, 71(20): 200601. doi: 10.7498/aps.71.20220670
    [9] Huang Wei-Jian, Li Yong-Tao, Huang Yuan. Prediction of chaotic time series using hybrid neural network and attention mechanism. Acta Physica Sinica, 2021, 70(1): 010501. doi: 10.7498/aps.70.20200899
    [10] Huang Liang, Li Jian-Yuan. Modeling and failure monitor of Li-ion battery based on single particle model and partial difference equations. Acta Physica Sinica, 2015, 64(10): 108202. doi: 10.7498/aps.64.108202
    [11] Li Huan, Wang You-Guo. Noise-enhanced information transmission of a non-linear multilevel threshold neural networks system. Acta Physica Sinica, 2014, 63(12): 120506. doi: 10.7498/aps.63.120506
    [12] Sudao Bilige, Wang Xiao-Min, Wuyun Morigen. Application of the symmetry classification to the boundary value problem of nonlinear partial differential equations. Acta Physica Sinica, 2014, 63(4): 040201. doi: 10.7498/aps.63.040201
    [13] He Yu-Bo, Lin Xiao-Yan, Dong Xiao-Liang. Use of lattice Boltzmann method to simulate 2-D partial differential equation. Acta Physica Sinica, 2013, 62(19): 194701. doi: 10.7498/aps.62.194701
    [14] Hou Xiang-Lin, Zhai Zhong-Hai, Zheng Li, Liu Tie-Lin. Layered optimization algorithm about a kind of nonlinear partial differential equation with initial-boundary value problem. Acta Physica Sinica, 2012, 61(1): 010201. doi: 10.7498/aps.61.010201
    [15] Hou Xiang-Lin, Zheng Xi-Jian, Zhang Liang, Liu Tie-Lin. Study on derivation and optimization algorithm about thin plate bending large deformation higher-order nonlinear partial differential equations. Acta Physica Sinica, 2012, 61(18): 180201. doi: 10.7498/aps.61.180201
    [16] Liu Tie-Lin, Zhai Zhong-Hai, Hou Xiang-Lin. Study and application of optimization algorithm about nonlinear partial differential equations with boundary value problem. Acta Physica Sinica, 2011, 60(9): 090202. doi: 10.7498/aps.60.090202
    [17] Xie Yuan-Xi, Tang Jia-Shi. A note on paper “a simple fast method in finding the analytical solutions to a class of nonlinear partial differential equations”. Acta Physica Sinica, 2005, 54(3): 1036-1038. doi: 10.7498/aps.54.1036
    [18] Xie Yuan-Xi, Tang Jia-Shi. A simple fast method in finding the analytical solutions to a class of nonlinear partial differential equations. Acta Physica Sinica, 2004, 53(9): 2828-2830. doi: 10.7498/aps.53.2828
    [19] Lu Jing, Yan Jia-Ren. . Acta Physica Sinica, 2002, 51(7): 1428-1433. doi: 10.7498/aps.51.1428
    [20] . Acta Physica Sinica, 1963, 19(8): 538-540. doi: 10.7498/aps.19.538
Metrics
  • Abstract views:  647
  • PDF Downloads:  23
  • Cited By: 0
Publishing process
  • Received Date:  30 May 2025
  • Accepted Date:  20 July 2025
  • Available Online:  08 August 2025
  • Published Online:  20 September 2025
  • /

    返回文章
    返回