請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/90783完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 周逸儒 | zh_TW |
| dc.contributor.advisor | Yi-Ju Chou | en |
| dc.contributor.author | 周儀恩 | zh_TW |
| dc.contributor.author | Yi-En Chou | en |
| dc.date.accessioned | 2023-10-03T17:36:05Z | - |
| dc.date.available | 2023-11-09 | - |
| dc.date.copyright | 2023-10-03 | - |
| dc.date.issued | 2023 | - |
| dc.date.submitted | 2023-08-10 | - |
| dc.identifier.citation | [1] ANSYS, Inc(2009), ANSYS FLUENT 12.0 Theory Guide. (18.3.1 Spatial Discretization)
[2] Boussinesq, J. V. (1877). Essai sur la théorie des eaux courantes. Impr. nationale. [3] Banerjee, S., Krahl, R., Durst, F., & Zenger, C. (2007). Presentation of anisotropy properties of turbulence, invariants versus eigenvalue approaches. Journal of Turbulence, (8), N32. [4] Germano, M., Piomelli, U., Moin, P., & Cabot, W. H. (1991). A dynamic subgrid‐scale eddy viscosity model. Physics of Fluids A: Fluid Dynamics, 3(7), 1760-1765. [5] Gatski, T. B., & Speziale, C. G. (1993). On explicit algebraic stress models for complex turbulent flows. Journal of fluid Mechanics, 254, 59-78. [6] Guo, G. M., Liu, H., & Zhang, B. (2017). Numerical study of active flow control over a hypersonic backward-facing step using supersonic jet in near space. Acta Astronautica, 132, 256-267. [7] Hinton, G., Deng, L., Yu, D., Dahl, G. E., Mohamed, A. R., Jaitly, N., ... & Kingsbury, B. (2012). Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal processing magazine, 29(6), 82-97. [8] Jones, W. P., & Launder, B. E. (1972). The prediction of laminarization with a two-equation model of turbulence. International journal of heat and mass transfer, 15(2), 301-314. [9] Jovic, S., & Driver, D. M. (1994). Backward-facing step measurements at low Reynolds number, Re (sub h)= 5000 (No. NASA-TM-108807). [10] Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014). Large-scale video classification with convolutional neural networks. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (pp. 1725-1732). [11] Leonard, B. P. (1979). A stable and accurate convective modelling procedure based on quadratic upstream interpolation. Computer methods in applied mechanics and engineering, 19(1), 59-98. [12] Lilly, D. K. (1992). A proposed modification of the Germano subgrid‐scale closure method. Physics of Fluids A: Fluid Dynamics, 4(3), 633-635. [13] Le, H., Moin, P., & Kim, J. (1997). Direct numerical simulation of turbulent flow over a backward-facing step. Journal of fluid mechanics, 330, 349-374. [14] Ling, J., Kurzawski, A., & Templeton, J. (2016a). Reynolds averaged turbulence modelling using deep neural networks with embedded invariance. Journal of Fluid Mechanics, 807, 155-166. [15] Ling, J., Jones, R., & Templeton, J. (2016b). Machine learning strategies for systems with invariance properties. Journal of Computational Physics, 318, 22-35. [16] Milano, M., & Koumoutsakos, P. (2002). Neural network modeling for near wall turbulent flow. Journal of Computational Physics, 182(1), 1-26. [17] Prandtl, L. (1925). 7. Bericht über Untersuchungen zur ausgebildeten Turbulenz. ZAMM‐Journal of Applied Mathematics and Mechanics/Zeitschrift für Angewandte Mathematik und Mechanik, 5(2), 136-139. [18] Pope, S. B. (1975). A more general effective-viscosity hypothesis. Journal of Fluid Mechanics, 72(2), 331-340. [19] Piirto, M., Saarenrinne, P., Eloranta, H., & Karvinen, R. (2003). Measuring turbulence energy with PIV in a backward-facing step flow. Experiments in fluids, 35, 219-236. [20] Smagorinsky, J. (1963). General circulation experiments with the primitive equations: I. The basic experiment. Monthly weather review, 91(3), 99-164. [21] Simpson, R. L. (1989). Turbulent boundary-layer separation. Annual Review of Fluid Mechanics, 21(1), 205-232. [22] Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., Van Den Driessche, G., ... & Hassabis, D. (2016). Mastering the game of Go with deep neural networks and tree search. nature, 529(7587), 484-489. [23] Tracey, B., Duraisamy, K., & Alonso, J. (2013, January). Application of supervised learning to quantify uncertainties in turbulence and combustion modeling. In 51st AIAA aerospace sciences meeting including the new horizons forum and aerospace exposition (p. 259). [24] Tracey, B. D., Duraisamy, K., & Alonso, J. J. (2015). A machine learning strategy to assist turbulence model development. In 53rd AIAA aerospace sciences meeting (p. 1287). [25] Wilcox, D. C. (1988). Reassessment of the scale-determining equation for advanced turbulence models. AIAA journal, 26(11), 1299-1310. [26] Wu, J., Xiao, H., Sun, R., & Wang, Q. (2019). Reynolds-averaged Navier–Stokes equations with explicit data-driven Reynolds stress closure can be ill-conditioned. Journal of Fluid Mechanics, 869, 553-586. [27] Zhang, Z. J., & Duraisamy, K. (2015). Machine learning methods for data-driven turbulence modeling. In 22nd AIAA computational fluid dynamics conference (p. 2460). | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/90783 | - |
| dc.description.abstract | 本研究旨在開發一基於機器學習的紊流模型，延續前人的研究採用張量基底神經網路，透過擴展張量基底神經網路的輸入特徵，以提高模型在紊流建模中的準確性。過去的張量基底神經網路使用了5個張量不變性作為輸入特徵，這5個輸入特徵皆與平均流場有關。然而，我們認為單純依靠這些與平均流場相關的特徵無法充分準確地預測整個流場，因此我們引入一新的概念，考慮流場中的幾何效應，而流線函數和速度位勢是與流場的幾何特徵相關的量，它們能夠描述流場的全域特徵。因此，我們在原有的張量不變性輸入層中添加了流線函數和速度位勢作為額外的輸入特徵。本研究選擇後向階流場作為應用案例，並使用ANSYS FLUENT求解器生成了不同雷諾數 (Re_h=424, 441, 458) 的流場案例，我們將Re_h=424和458 這兩組流場資訊用於張量基底神經網路的訓練，以預測Re_h=441的案例。在先驗測試(priori test)中本研究所預測的雷諾應力藉由平均預測的結果消除了過度擬合的問題，然而雖無法與大尺度渦流模擬模型(LES)模擬的結果完全相同，但其大致變化的趨勢都能有效地捕捉到，而在後驗測試(posteriori test)中，本文藉由神經網路所預測的雷諾應力透過雷諾平均納維爾-斯托克斯模型(RANS)求解器計算而得到的平均流場與大尺度渦流模擬模型(LES)模擬的結果非常接近，像是通過階梯後的回流區或是自由流等流場特徵，藉由加入流線函數和速度位勢作為額外的輸入，本文成功地提高張量基底神經網路在紊流建模中的準確性。 | zh_TW |
| dc.description.abstract | The aim of this study is to develop a machine learning-based turbulence modeling, building upon previous research using tensor-basis neural network (TBNN), to enhance the accuracy of the model in turbulence modeling by extending the input features of TBNN. Previous research has utilized TBNN with five tensor invariants as input features, all related to the mean flow field. However, relying solely on these mean flow-related features may insufficient for accurately predict the entire flow field. Therefore, we introduce a new concept by considering the geometric effects in the flow field. Stream function and velocity potential are quantities associated with the geometric features of the flow field, which can describe global characteristics of the flow. To enhance the accuracy of TBNN in turbulent flow modeling, we incorporate the stream function and velocity potential as additional input features in the tensor invariant input layer. In this study, we focus on turbulent flows over the backward-facing step as the application case, and flow field cases with different Reynolds number (Re_h=424, 441, 458) are generated using the ANSYS FLUENT solver. We employ the flow information from Re_h=424 and 458 to train the TBNN model for predicting the case at Re_h=441. In the priori test, the predicted Reynolds stresses effectively eliminate the problem of overfitting by averaging the predicted results. While the predicted Reynolds stresses cannot exactly match the results of LES simulations, they capture the overall trends reasonably well. In the posteriori test, the average flow field obtained from the Reynolds stress predicted by the neural network through RANS solver is very close to the results of LES simulation. The flow features, such as recirculation region or free stream region, are accurately captured. By incorporating streamline function and velocity potential as additional inputs, this study successfully improves the accuracy of TBNN in turbulence modeling. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-10-03T17:36:05Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2023-10-03T17:36:05Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 致謝 i
中文摘要 iii Abstract iv 目錄 vi 圖目錄 viii 表目錄 xi 符號表 xii Chapter1 緒論 1 1.1 研究背景 1 1.2 文獻回顧 8 1.2.1 後向階流場的結構與特性 8 1.2.2 深度神經網路 9 1.2.3 張量基底神經網路(tensor basis neural network) 10 1.3 研究動機 13 1.4 全文概述 14 Chapter2 方法 15 2.1模型設置 15 2.1.1 計算域與網格與邊界條件設置 16 2.2 先驗測試(priori test) 19 2.2.1 優化(optimization) 20 2.2.2 平均(ensemble) 22 2.3 後驗測試(posteriori test) 25 Chapter3 結果與討論 29 3.1 流場結果與驗證 29 3.2 先驗結果(results of priori) 33 3.3 後驗結果(results of posteriori) 40 Chapter4 結論 50 Chapter5 未來工作與展望 52 參考文獻 53 附錄A 56 A.1大尺度渦流模擬模型(Large Eddy Simulation, LES) 56 A.2 Smagorinsky Model (SM) 58 A.3 Dynamic Smagorinsky-Lilly Model (DSM) 59 A.4 SIMPLE法 61 A.5 QUICK法 64 附錄B 65 B.1 非人工佈點 65 | - |
| dc.language.iso | zh_TW | - |
| dc.subject | 後向階流場 | zh_TW |
| dc.subject | 張量基底神經網路 | zh_TW |
| dc.subject | 機器學習 | zh_TW |
| dc.subject | 紊流模型 | zh_TW |
| dc.subject | turbulence modeling | en |
| dc.subject | machine learning | en |
| dc.subject | backward-facing step flow | en |
| dc.subject | tensor basis neural network | en |
| dc.title | 張量基底類神經網路應用於通過後向階流場之紊流模型 | zh_TW |
| dc.title | Application of tensor basis neural network to model turbulent flows over the backward-facing step | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 111-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 曾建洲;牛仰堯;林洸銓 | zh_TW |
| dc.contributor.oralexamcommittee | Chien-Chou Tseng;Yang-Yao Niu;Kuang-Chuan Lin | en |
| dc.subject.keyword | 紊流模型,機器學習,張量基底神經網路,後向階流場, | zh_TW |
| dc.subject.keyword | turbulence modeling,machine learning,tensor basis neural network,backward-facing step flow, | en |
| dc.relation.page | 67 | - |
| dc.identifier.doi | 10.6342/NTU202302768 | - |
| dc.rights.note | 同意授權(限校園內公開) | - |
| dc.date.accepted | 2023-08-11 | - |
| dc.contributor.author-college | 工學院 | - |
| dc.contributor.author-dept | 應用力學研究所 | - |
| dc.date.embargo-lift | 2028-08-02 | - |
| 顯示於系所單位： | 應用力學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-111-2.pdf 未授權公開取用 | 3.11 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。