-
为解决传统数值模拟方法在蝠鲼三维柔性大变形流场仿真中计算资源与时间上的局限性，本文提出一种基于去噪概率扩散模型的生成式人工智能方法（surf-DDPM），通过输入运动参数变量组，预测蝠鲼表面流场。首先，采用浸入边界法和球函数气体动理学格式（IB-SGKS）建立蝠鲼扑动模态的数值计算方法，获取了在0.3-0.9Hz频率和0.1-0.6倍体长幅值条件下共180组非定常流场数据集。其次，构建了噪声扩散过程的马尔科夫链和去噪生成过程的神经网络模型，并将运动参数与扩散时间步标签嵌入网络，完成模型训练。最后，验证了神经网络超参数对模型预测的影响，并可视化了未参与训练的多扑动姿态压力场和速度场预测结果，进行预报结果准确性、不确定度与预测效率量化分析。结果显示，该模型实现了具有大跨度高维上采样特征的蝠鲼表面流场数据的快速准确预测，预报结果全部位于95%置信区间内，单工况预测相较CFD方法效率提升99.97%。The manta ray is a large marine species that exhibits both highly efficient gliding and agile flapping capabilities. It can autonomously switch between various motion modes, such as gliding, flapping, and group swimming, based on ocean currents and seabed conditions. To address the computational resource and time constraints of traditional numerical simulation methods in modeling the manta ray's 3D large-deformation flow field, this study proposes a novel generative artificial intelligence approach based on a denoising probabilistic diffusion model (surf-DDPM). This method predicts the surface flow field of the manta ray by inputting a set of motion parameter variables. Initially, we establish a numerical simulation method for the manta ray’s flapping mode using the immersed boundary method and the spherical function gas kinetic scheme (IB-SGKS), generating an unsteady flow dataset comprising 180 sets under frequency conditions of 0.3-0.9 Hz and amplitude conditions of 0.1-0.6 body lengths. Data augmentation is then performed. Subsequently, a Markov chain for the noise diffusion process and a neural network model for the denoising generation process are constructed. A pretrained neural network embeds the motion parameters and diffusion time step labels into the flow field data, which are then fed into a U-Net for model training. Notably, a Transformer network is incorporated into the U-Net architecture to enable handling of long-sequence data. Finally, we examine the impact of neural network hyperparameters on model performance and visualize the predicted pressure and velocity fields for multi-flapping postures that were not included in the training set, followed by a quantitative analysis of prediction accuracy, uncertainty, and efficiency. The results demonstrate that the proposed model achieves fast and accurate predictions of the manta ray’s surface flow field, characterized by extensive high-dimensional upsampling. The minimum PSNR and SSIM values of the predictions are 35.931 dB and 0.9524, respectively, with all data falling within the 95% prediction interval. Compared with CFD simulations, the AI model enhances the prediction efficiency of single-condition simulations by 99.97%.
-
Keywords:
- manta rays /
- Fluid Mechanics /
- artificial intelligence /
- flow field prediction
-
[1] Wang L 2007 Ph. D. Dissertation (Nanjing: Hehai University) (in Chinese) [王亮 2007 博士学位论文 (南京: 河海大学)]
[2] Asada T, Furuhashi H 2024 Ocean Engineering 308 118261
[3] Xing C, Yin Z, Xu H, Cao Y, Qu Y, Huang Q 2024 Ocean Engineering 312 119039
[4] Bao T, Cao Y, Cao Y H, Lu Y, Pan G, Huang Q G 2024 Ocean Engineering 309 118377
[5] Dong H, Bozkurttas M, Mittal R, Madden P, Laude G V 2010 Journal of Fluid Mechanics 645 34
[6] Huang Z, Menzer A, Guo J, Dong H 2024 Bioinspir Biomim 19 026004
[7] Wang S, Gao P, Huang Q G, Pan, G, Tian, X 2024 Ocean Engineering 294 116799
[8] Gao P C, Song B, Huang Q G, Tian X S, Pan G, Chu Y, Bai J Y 2024 Ocean Engineering 313 119415
[9] Gao P C, Huang Q G, Pan G, Cao Y, Luo Y 2023 Ocean engineering 278 114389
[10] Miyanawala T P, Li Y, Law Y Z 2024 Ocean Engineering 306 118003
[11] Li G, Zhu H, Jian H 2023 Journal of Hydrology 625 130025
[12] Zhan Q L, Ge Y J, Bai C J 2022 Acta Phys. Sin. 71 225 (in Chinese) [战庆亮, 葛耀君, 白春锦 2022 71 225]
[13] Wang Z, Zhang W 2023 Physics of Fluids 35 025124
[14] Qiu C C, Huang Q G, Pan G 2023 Physics of Fluids 35 017132
[15] Xia Y, Li T, Wang Q, Yue J, Peng B, Yi X 2024 Physics of Fluids 36 103313
[16] Li R, Song B, Chen Y 2024 Ocean Engineering 304 117857
[17] Caraccio P, Marseglia G, Lauria A 2024 Physics of Fluids 36 107120
[18] Qiu C C, Huang Q G, Pan G 2023 Ocean Engineering 281 114555
[19] Gao H, Gao L, Shi Z, Sun D, Sun X 2024 Aerospace Science and Technology 147 108977
[20] Lin H, Jiang X, Deng X 2024 Thinking Skills and Creativity 54 101649
[21] Kartashov N, Vlassis N N 2024 arXiv:2409.14473
[22] Zhao Z, Bai H, Zhu Y, Zhang J, Xu S, Zhang Y 2023 Proceedings of the IEEE/CVF International Conference on Computer Vision 2023 p8082
[23] Ho J, Jain A, Abbeel P 2020 Advances in neural information processing systems 33 6840
[24] Rombach R, Andreas B, Dominik L, Patrick E, Björn O 2022 Proceedings of the IEEE/CVF conference on computer vision and pattern recognition 2022 p10684
[25] Song J, Meng C, Ermon S. 2020 arXiv:2010.02502
[26] Nichol A, Dhariwal P, Ramesh A, Shyam P, Mishkin P, McGrew B 2021 arXiv:2112.10741
[27] Huang L, Zheng C, Chen Y 2024 Physics of Fluids 36(9) 095113
[28] Rybchuk A, Hassanaly M, Hamilton N 2023 Physics of Fluids 35 126604
[29] Gao P C, Tian X, Huang Q G 2024 Physics of Fluids 36 011902
[30] Gao P C, Huang Q G, Pan G 2023 Physics of Fluids 35 061909
[31] Zhang D 2020 Ph. D. Dissertation (Xi’an: Northwestern Polytechnical University) (in Chinese) [张栋 2020 博士学位论文 (西安: 西北工业大学)]
计量
- 文章访问数: 187
- PDF下载量: 10
- 被引次数: 0
下载:
