Fadil Naufal Wahas

---

Assalamu'alaikum Warahmatullahi Wabarakatuh, Salam Sejahtera untuk kita semua.

Perkenalkan, saya Fadil Naufal Wahas, NPM 2306185416, mahasiswa magister Departemen Teknik Mesin Universitas Indonesia.

Thesis

Tesis : Studi komputasi tentang pengaruh sifat fluida terhadap karakteristik counter-current flow limitation (CCFL) di 1/30 pressurized water reactor (PWR) hot leg

Thesis : Computational study of the effects of fluid properties on counter-current flow limitation (CCFL) characteristics in 1/30 pressurized water reactor (PWR) hot leg

Pembimbing : Prof. Dr. Ir. Harinaldi, M.Eng.

Pada kanal uap (hot leg) teras reaktor pada pembangkit listrik tenaga nuklir pressurized water reactor (PWR) terdapat fenomena counter-current flow limitation (CCFL) yang terjadi pada saat kondisi kecelakaan loss-of-coolant accident (LOCA).

Saat LOCA, karena adanya penurunan tekanan, terjadi penguapan air pendingin yang berada di reaktor sehingga uap tersebut mengalir ke steam generator (SG) melalui hot leg. Sebagian uap yang terkumpul di SG tersebut mengalami kondensasi menjadi air. Air tersebut, dipengaruhi gravitasi, mengalir kembali ke reaktor, berlawanan arah dengan uap. Aliran berlawanan arah ini terjadi saat kecepatan aliran uap berada di bawah ambang batas flooding atau counter-current flow limitation (CCFL).

Fenomena CCFL ini menjadi penting untuk diteliti karena berhubungan dengan keselamatan reaktor nuklir. Oleh karena itu, pengaruh sifat fisik fluida terhadap karakteristik CCFL perlu diinvestigasi.

DAI5 Framework

DAI5 Framework is a guideline developed by Dr. Ahmad Indra Siswantara for problem-solving processes. This video essay is my interpretation of the DAI5 Framework.

Computational Fluid Dynamics (CFD)

Convergence and Grid Independence

The two aspects that characterize a successful simulation result are convergence and grid independence. A converged solution have very small residuals – measures of the overall conservation of the flow properties.

The only way to eliminate errors due to coarseness of a grid is to perform a grid dependence study, which is a procedure of successive refinement of an initially coarse grid until certain key results do not change. Then the simulation is grid independent. A systematic search for convergent and grid-independent results forms an essential part of all high-quality CFD studies.

Reference: H. K. Versteeg and W. Malalasekera, An Introduction to Computational Fluid Dynamics: The Finite Volume Method. 2nd Edition. England: Pearson, 2007.

Cavity 2D Laminar Flow with CFDSOF

The image below shows a 0.1 m by 0.1 m cavity section filled with air (udara) where the upper wall is moving in the +x-axis direction at 0.1 m/s where the density (ρ) of air is 1 kg/m^3, the dynamic viscosity (µ) of air is 2 * 10^-5 kg/m-s, and the flow is laminar, i.e. Re = 500.

The grid-structured *CFDSOF* software is used in this simulation case.

First, cavity is discritized by dividing it into cells, in this case, a 10x10 cells.

Then, after specifying the boundary condition of the walls and the iteration of the case, the iteration begins. The results of the velocity vector field and the pressure contour are shown in the images below.

It can be shown that the air is indeed moving inside the cavity and the air that is closest to the upper wall is also moving with the greatest magnitude. From the pressure contour, it can be seen that the upper-most-right corner has the greatest pressure. This is due to the fact that air is colliding at that corner and is diverted to the adjacent bottom. This collision occurs at the 4 corners of the wall, thus creating the swirling effect with the smallest velocity magnitude at the center of the swirl.

OpenFOAM Solvers

Here are solvers that OpenFOAM offers. The table below classifies the solver based on the flow of the fluid and depends on the case-by-case problem.

OpenFOAM Solvers

No.	Solver	Algorithm	Time	Flow	Compressibility	Phase
1	simpleFoam	SIMPLE	Steady-State	Laminar/Turbulent	Incompressible	Single-phase
2	icoFoam	PISO	Transient	Laminar	Incompressible	Single-phase
3	pisoFoam	PISO	Transient	Turbulent	Incompressible	Single-phase
4	pimpleFoam	PISO+SIMPLE	Transient	Turbulent	Incompressible	Single-phase
5	interFoam	PISO+SIMPLE	Transient	Turbulent	Incompressible	Multi-phase
6	-	-	-	-	-	-

SIMPLE = Semi-Implicit Method for Pressure Linked Equations

PISO = Pressure Implicit with Splitting of Operators

Cavity 2D with OpenFOAM

The problem we are trying to solve is lid-driven cavity. Same as previous case, the geometry is a 2 dimensional 0.1 m by 0.1 m (gamma = Lx/Ly = 1) cavity space with the upper wall moving to the positive x-axis direction at certain velocities. The boundary of right, left, and lower wall is stationary. The fluid is air with kinematic viscosity (nu) of 1 * 10-⁵ m²/s.

The INTENTION of this preliminary study is to understand the effect of Reynolds number (Re) on the air flow inside the lid-driven cavity, particularly the flow profile. At certain velocity, is it laminar, transitional, or turbulent? At what Reynolds number does the change occurs?

<math> Re = \frac{&rho U L}{&mu} = \frac{U L}{\&nu} . . . (1) </math>

where: Re = Reynolds number (-) rho = fluid density (kg/m³) U = inlet velocity = upper wall velocity (m/s) L = characteristic length = wall length = 0.1 m mu = dynamic viscosity (kg/m-s) nu = kinematic viscosity = 1 * 10-⁵ (m²/s)

Reynolds number can be calculated using the Eq. (1). We can vary the Reynolds number by varying the wall velocity. Here, the upper wall velocity is varied from 0.0001 m/s to 0.8 m/s with various increment. The wall velocity variation is presented at the table below.

Table 1. Variation of wall velocity

U (m/s)	Re (-)
0.0001	1
0.01	100
0.02	200
0.03	300
0.04	400
0.05	500
0.1	1000
0.2	2000
0.3	3000
0.8	8000

We used the open-source CFD software OpenFOAM for this study with simpleFoam solver for both laminar and turbulent flow, with the latter using the k-Omega turbulence model. The flow was assumed to be steady-state. A 50 by 50 hexahedral grid mesh was used in the model, where the z-axis was set to 1 cell to represent the 2 dimensional case.

First, we validated our simulation by comparing the case with U = 0.0001 m/s and U = 0.8 m/s, hence the Re are 1 and 8000, respectively, with the case from a study conducted by Hendriketal [1], also with the same Re. The fluid flow with the isolines (streamlines) from both simulation and reference [1] can be seen in the Fig. 1 and Fig. 2 below. It can be seen that the results generated by our simulations is the same as the results obtained from [1].

The flow with Re = 1 is laminar and almost vertically symmetrical and the flow with Re = 8000 is turbulent with 3 secondary eddies in the 3 corners of the cavity.

Next we varied the parameter of U from 0.01 m/s to 0.3 m/s with simpleFoam laminar model as per Table 1, and look at the flow profile of the cavity. The isolines can be seen at Fig. 3 to Fig. 10.

Convergence can be seen from simulation's variables residuals below.

Re = 1

Re = 8000

References:

[1] H. C. Kuhlmann and F. Romanò, "The Lid-Driven Cavity," Computational Methods in Applied Sciences, vol. 50, 2019. https://doi.org/10.1007/978-3-319-91494-7_8

Lid-Driven Cavity with DAI5 Framework

This is a video essay of the application of DAI5 Framework in understanding lid-driven cavity. The lid-driven cavity simulation is done using OpenFOAM.

Disclaimer: the video is in Bahasa Indonesia.

Lid-Driven Cavity Case File: bit.ly/CavityDAI5

Paper Draft

Grid Independency Study on the Turbulence of Lid Driven Cavity using DAI5 Framework

Google Drive

Mid Test with ChatGPT

Mid Test with ChatGPT
	User
ChatGPT
	I am going to take an exam on the subject of basic Computational Fluid Dynamics (CFD). I need you to create a basic test consisted of 5 short-answer questions all at once and grade what I do.
Here’s a basic test on Computational Fluid Dynamics (CFD) consisting of 5 short-answer questions: CFD Basic Test Question 1: Define the term "viscosity" and explain its significance in fluid flow. Question 2: What is the difference between laminar and turbulent flow? Provide examples of each. Question 3: Explain the concept of grid independence in CFD and why it is important for accurate simulation results. Question 4: Describe the role of the Navier-Stokes equations in CFD. What do they represent? Question 5: What are boundary conditions in CFD, and why are they crucial for setting up a simulation? Once you answer these questions, I can grade your responses!
	1. Define the term "viscosity" and explain its significance in fluid flow. Viscosity is a measure of a fluid’s internal friction or resistance to deformation or flow when a force is applied to it. It is a fluid-specific property where fluids with higher viscosity, like syrup, deform less easily compared to fluids with lower viscosity, like water. There are two types of viscosity, the dynamic viscosity (mu) and the kinematic viscosity (nu), with units kg/m.s and m^2/s, respectively. In fluid flow applications, viscosity plays a vital role in determining whether the flow is laminar or turbulent. Viscosity is a critical property that affects fluid dynamics, influencing how fluids flow and behave under various conditions. 2. What is the difference between laminar and turbulent flow? Provide examples of each. Laminar flow is characterized by smooth, orderly motion of fluid layers, with each layer sliding past the adjacent ones with minimal to no mixing. This type of flow typically occurs at low Reynolds numbers (Re < 2000). An example of laminar flow is the flow of blood inside our capillaries or the flow of air inside a wind tunnel before contact. Turbulent flow, on the other hand, is characterized by irregular fluid motion with significant mixing and fluctuations in velocity. This type of flow typically occurs at high Reynolds numbers (Re > 4000). An example of turbulent flow is the air in and out of our respiratory system or the airflow around an airplane wing. 3. Explain the concept of grid independence in CFD and why it is important for accurate simulation results. Grid independence refers to the condition where the results of a simulation do not significantly change with further refinement of the computational grid (mesh). This can be done with a grid dependence study, which is a procedure of successive refinement of an initially coarse grid until certain key results do not change. Achieving grid independence is crucial because it ensures that the numerical solution is not influenced by the discretization of the domain, leading to more reliable and accurate results. A systematic search for grid-independent result forms an essential part of all high-quality CFD studies. 4. Describe the role of the Navier-Stokes equations in CFD. What do they represent? The Navier-Stokes equations are a set of nonlinear partial differential equations that describe the motion of fluid. They represent the conservation of momentum in fluid flow and are fundamental to the field of computational fluid dynamics. The equations account for viscosity, pressure, and external forces acting on the fluid. In CFD, solving the Navier-Stokes equations enables the prediction of velocity fields, pressure distributions, and other flow characteristics, making them essential for simulating and analyzing fluid behavior in various engineering applications. 5. What are boundary conditions in CFD, and why are they crucial for setting up a simulation? Boundary conditions in CFD define the behavior of the fluid at the boundaries of the computational domain. They specify values for variables such as velocity, pressure, and other relevant quantities at the edges of the simulation space. They ensure that the simulation reflects the physical reality of the problem being modeled, allowing for accurate predictions and are essential for producing valid and reliable CFD results.
Grading: Definition of Viscosity: (9/10) Your explanation is clear and well-structured. You correctly define viscosity and its types (dynamic and kinematic) along with their units. You also mention its importance in fluid dynamics and how it affects flow behavior. One minor note: You could expand on how viscosity affects energy dissipation in the flow. Nonetheless, your answer is quite strong. Difference between Laminar and Turbulent Flow: (10/10) Excellent explanation of both laminar and turbulent flows with clear examples and correct references to Reynolds numbers. The distinction between orderly and chaotic motion is well articulated, and the examples are accurate. Grid Independence Concept: (10/10) Great explanation! You correctly identify grid independence and explain the grid dependence study and its importance in ensuring simulation accuracy. This is a key concept in CFD, and your description captures it thoroughly. Role of Navier-Stokes Equations: (10/10) Your answer effectively highlights the significance of the Navier-Stokes equations in CFD. You mention their role in momentum conservation, accounting for viscosity, pressure, and forces, and how they are used to predict key flow characteristics. This is a complete and concise answer. Boundary Conditions in CFD: (9/10) Good explanation of boundary conditions and their role in simulations. You correctly mention their importance in defining variables at the boundaries and ensuring physical realism in the model. A small suggestion: you could briefly touch upon specific types of boundary conditions (e.g., Dirichlet, Neumann) for more depth, but your answer is still very solid. Overall Score: 96/100 Excellent work! Your understanding of CFD fundamentals is strong, and you provided clear, well-articulated answers throughout the test. Just minor improvements in elaboration could make it even better.
	USER
AI
	USER
AI
	USER
AI
	USER
AI

Self-assessment Mid-Test

Rencana untuk Kelas Aplikasi CFD pasca-UTS