Turbulence modeling is one of the main sources of uncertainty in CFD simulations of technical flows, as turbulence is the most complex phenomenon in classical physics. There are many turbulence models available in Ansys Fluent, but not all of them are suitable for every situation. The choice of the best turbulence model depends on several factors, such as the Reynolds number, the flow regime, the near-wall treatments, and the inlet boundary conditions.
For standard cases where highly accurate resolution of boundary layers is critical, such as applications involving flow separation or finely resolved heat transfer profiles, SST k-w (Stokesian Turbulence with Wall) is a preferred choice. This model can capture both the viscous sublayer and the log-layer regions near the wall, and can handle complex geometries and large-scale structures.
For cases where only a crude estimate of turbulence is required, or where other physical models or assumptions are more important than the turbulence model, k-e (k-epsilon) can be used. This model is simpler and faster to solve than SST k-w, but it has some limitations. For example, it cannot resolve scales larger than 10-6 m or smaller than 10-4 m. It also assumes that the turbulent fluctuations are isotropic and have a constant correlation length.
For cases where very high-resolution simulations are needed for applications involving small-scale features or microstructures, such as aerodynamics or heat transfer in microchannels or microfluidics, k-omega (k-omega) can be used. This model can capture both large-scale and small-scale structures in turbulent flows by using a combination of k-epsilon and k-alpha (k-alpha) models. However, this model requires more computational resources and time than SST k-w or k-e.
There are also other turbulence models that are designed for specific applications or domains. For example, GEKO (Generalized K-Omega) is a flexible and robust model that can handle complex geometries and boundary conditions with high accuracy². It also has an option to use adaptive mesh refinement to improve the quality of the mesh near regions of high turbulence intensity².
To select the best turbulence model for your case, you need to consider your objectives and constraints. You also need to perform some tests and validations to compare different models and check their performance. You can find more information about how to do this in this technical paper: [Best Practice: RANS Turbulence Modeling in Ansys CFD](^1^).
Source:
(1) How to Display Poor Quality Mesh Elements - Ansys Knowledge. https://ansyskm.ansys.com/forums/topic/how-to-display-poor-quality-mesh-elements/.
(2) Best Practice: RANS Turbulence Modeling in Ansys CFD. https://www.ansys.com/resource-center/technical-paper/best-practice-rans-turbulence-modeling-in-ansys-cfd.
(3) Extremely poor mesh quality - Ansys Learning Forum. https://forum.ansys.com/forums/topic/extremely-poor-mesh-quality/.
(4) Lecture 7: Turbulence Modeling Introduction to ANSYS Fluent - Academia.edu. https://www.academia.edu/36090206/Lecture_7_Turbulence_Modeling_Introduction_to_ANSYS_Fluent.
How do I validate a turbulence model in Ansys Fluent?
To validate a turbulence model in Ansys Fluent, you need to compare the results of your simulation with some experimental or analytical data. This can help you assess the accuracy and reliability of your model, and identify any sources of uncertainty or error.
There are different methods and criteria for validating a turbulence model, depending on the type of flow, the turbulence model, and the available data. Some common methods are:
- **Statistical tests**: These are numerical methods that use statistical measures to quantify the agreement between the simulated and experimental data. For example, you can use the coefficient of determination (R-squared), which is the ratio of the variance explained by the model to the total variance in both data sets. A higher R-squared indicates a better fit. You can also use other tests, such as Kolmogorov-Smirnov test, Anderson-Darling test, or Bland-Altman plot¹.
- **Qualitative analysis**: This is a visual inspection of the simulated results to check for any anomalies or discrepancies with the experimental data. For example, you can look at plots of velocity profiles, pressure distributions, turbulence intensity, or heat transfer coefficients². You can also use qualitative tools, such as histograms, box plots, or scatter plots³.
- **Adaptive mesh refinement**: This is a technique that uses machine learning algorithms to optimize the mesh quality near regions of high turbulence intensity. This can improve the accuracy and efficiency of your simulation by reducing computational costs and increasing resolution⁴. You can use adaptive mesh refinement in Ansys Fluent by selecting Fluid Flow > Turbulent Flow > Adaptive Mesh Refinement from Workbench menu⁵.
To perform validation in Ansys Fluent, you need to follow these steps:
- Select a suitable turbulence model for your case from Ansys Fluent's Model Browser.
- Define your boundary conditions and mesh settings.
- Run your simulation and obtain your results.
- Compare your results with some experimental or analytical data using one or more of the methods mentioned above.
- Analyze your results and identify any sources of uncertainty or error.
- Repeat steps 4 to 6 until you are satisfied with your validation.
Source:
(1) Best Practice: RANS Turbulence Modeling in Ansys CFD. https://www.ansys.com/resource-center/technical-paper/best-practice-rans-turbulence-modeling-in-ansys-cfd.
(2) Introduction to Turbulence Modeling in Ansys Fluent - Lesson 1. https://courses.ansys.com/index.php/courses/turbulence-modeling-in-ansys-fluent/lessons/introduction-to-turbulence-modeling-in-ansys-fluent-lesson-1/.
(3) Verification & Validation — Lesson 7 - ANSYS Innovation Courses. https://courses.ansys.com/index.php/courses/turbulent-pipe-flow-rans/lessons/verification-validation-lesson-7-4/.
(4) Turbulent Pipe Result Verification and Validation | Ansys Innovation .... https://courses.ansys.com/index.php/courses/turbulent-pipe-flow-les/lessons/validation-verification-lesson-8-2/.
(5) Ansys Fluent Day 2, Turbulence & Meshing | Fastway Engineering. https://fastwayengineering.com/student/ansys-fluent-overview/ansys-fluent-day-2-turbulence-mesh/.
(6) https://turbmodels.larc.nasa.gov/naca0012_val.html%29.
Can you tell me more about adaptive mesh refinement?
Sure, I can tell you more about adaptive mesh refinement. 😊
Adaptive mesh refinement (AMR) is a technique for automatically and dynamically refining (or de-refining) certain regions of the physical domain in a finite difference calculation, in order to lessen the computational effort required to perform a simulation with limited loss of precision³. AMR can improve the accuracy and efficiency of your simulation by reducing computational costs and increasing resolution⁴.
AMR works by using a criterion that can either be user-supplied or based on Richardson extrapolation to tag or identify cells for refinement and coarsening. All tagged cells are then refined, meaning that a finer grid is overlaid on the coarse one. After refinement, individual grid patches on a single fixed level of refinement are passed off to an integrator which advances those cells in time. Finally, a correction procedure is implemented to correct the transfer along coarse-fine grid interfaces, to ensure that the amount of any conserved quantity leaving one cell exactly balances the amount entering the bordering cell¹.
There are different methods and algorithms for implementing AMR, depending on the type of flow, the turbulence model, and the available data. Some common methods are:
- **Local adaptive mesh refinement**: This is an algorithm developed by Marsha Berger, Joseph Oliger, and Phillip Colella that uses high resolution grids only at the physical locations and times where they are required¹.
- **Multiresolution-based adaptive schemes**: These are methods that use different levels of resolution for different regions or scales of interest, such as k-omega (k-omega) models for turbulent flows or multiresolution adaptive space refinement for geophysical fluid dynamics simulations².
- **Posteriori error estimation and mesh adaptivity**: These are methods that use information from previous simulations or experiments to estimate the error or uncertainty in each cell and adjust the mesh accordingly⁵.
- **Adaptive mesh refinement based on optimal sparse representations**: This is a method that uses sparse matrices to represent the solution in each cell and optimizes their sparsity using reinforcement learning techniques⁴.
AMR has been used in various fields and applications, such as computational fluid dynamics (CFD), astrophysics, climate modeling, combustion, biophysics, radiation transport, etc. You can find more information about AMR in these sources:
- [Adaptive Mesh Refinement - Theory and Applications](^2^): A book that contains proceedings from a workshop on AMR methods held in 2003.
- [Reinforcement Learning for Adaptive Mesh Refinement](^5^): A paper that proposes a novel method for AMR using reinforcement learning techniques.
- [An adaptive mesh refinement approach based on optimal sparse representations](^4^): A paper that presents a new method for AMR using sparse matrices.
Source:
(1) Adaptive Mesh Refinement | SpringerLink. https://link.springer.com/chapter/10.1007/978-3-031-09265-7_4.
(2) An adaptive mesh refinement approach based on optimal sparse ... - Springer. https://link.springer.com/article/10.1007/s00162-020-00522-2.
(3) Adaptive mesh refinement - Wikipedia. https://en.wikipedia.org/wiki/Adaptive_mesh_refinement.
(4) Adaptive Mesh Refinement - Theory and Applications - Springer. https://link.springer.com/book/10.1007/b138538.
(5) Reinforcement Learning for Adaptive Mesh Refinement - arXiv.org. https://arxiv.org/pdf/2103.01342v1.
(6) Adaptive Mesh Refinement - Theory and Applications - Springer. https://link.springer.com/book/10.1007/b138538.
(7) Reinforcement Learning for Adaptive Mesh Refinement - arXiv.org. https://arxiv.org/pdf/2103.01342v1.
(8) An adaptive mesh refinement approach based on optimal sparse ... - Springer. https://link.springer.com/article/10.1007/s00162-020-00522-2.
No comments:
Post a Comment