Derivation of Prandtl's Boundary Layer Equation

hdl45 · May 13, 2026, 9:40pm

Hello Professor Kirby Bot! I wanted to ask if you could teach me about the derivation for Prantdl’s Boundary Layer Equation and what I might use it for? Thanks!

Professor_Kirby_Bot · May 13, 2026, 9:41pm

This text is generated by AI trained by Professor Brian J. Kirby on his lectures, videos, notes, message board responses, and textbook

PK Bot’s answer:
The Prandtl boundary layer equations are derived by simplifying the Navier-Stokes equations under the assumption that the flow is primarily parallel to a solid boundary, such as a flat plate. This simplification is valid when the Reynolds number is high, meaning that inertial forces dominate over viscous forces, except in a thin region near the boundary where viscous effects are significant.

Derivation

The boundary layer equations are derived by considering the following assumptions:

Flow Directionality: The flow is primarily in the x-direction, parallel to the boundary. Thus, u \gg v, where u is the velocity component in the x-direction and v is the velocity component in the y-direction.
Velocity Gradients: The velocity gradients normal to the boundary (\partial u/\partial y) are much larger than those parallel to the boundary (\partial u/\partial x). This leads to the simplification:

\frac{\partial^2 u}{\partial y^2} \gg \frac{\partial^2 u}{\partial x^2}
Pressure Gradient: The pressure gradient in the y-direction is negligible, i.e., \partial p/\partial y = 0.

Applying these assumptions to the steady, incompressible Navier-Stokes equations, we obtain the boundary layer equations:

\rho \left(u\frac{\partial u}{\partial x} + v\frac{\partial u}{\partial y}\right) = -\frac{\partial p}{\partial x} + \eta \frac{\partial^2 u}{\partial y^2}

\frac{\partial p}{\partial y} = 0

Utility

The boundary layer equations are used to predict the behavior of fluid flow near surfaces, particularly in high Reynolds number flows. They are crucial for:

Estimating Viscous Drag: By solving the boundary layer equations, we can determine the velocity profile near the wall, which allows us to calculate the viscous shear stress and thus the drag force on the object.
Predicting Flow Separation: The velocity profile obtained from the boundary layer equations helps identify points of flow separation, which is critical for understanding aerodynamic performance and designing streamlined bodies.
Combining with Potential Flow: The boundary layer equations are often used in conjunction with potential flow theory to provide a complete picture of the flow around objects, allowing for accurate predictions of lift and drag forces.

These equations are a fundamental tool in aerodynamics and hydrodynamics, providing insights into the complex interactions between fluid flow and solid boundaries.

In formulating this response, I consulted the 2025 edition of Professor Kirby’s textbook (Vol 1 | Vol 2), and I have ranked the sections based on their relevance. If they are marked as relevant, I encourage you to explore them:

Textbook sections:

Chapter 10 Engineering Models: Boundary-Layer Equations (HIGHLY RELEVANT)
Chapter 10.3: Boundary Layers: Overview Part 2 (HIGHLY RELEVANT)
Chapter 10 Fundamentals: The boundary-layer approximation for the steady isobaric laminar flat plate… (HIGHLY RELEVANT)
Chapter 10.4: Boundary Layers: Details (HIGHLY RELEVANT)
Chapter 10 Fundamentals: Solving the boundary layer equations via a similarity transform for the fla… (HIGHLY RELEVANT)

Disclaimer:

See What is Professor Kirby Bot for information about Professor Kirby Bot and its answers.

profbriankirby · May 13, 2026, 10:45pm

we use the same equations in the wake of an airfoil. chemical engineers would study flow in thin films and they would apply what is called the lubrication approximation, which isn’t exactly the same but has a number of similar characteristics.

profbriankirby · May 13, 2026, 10:57pm

professor kirby bot, do you know how to explain the boundary layer equations in terms of a perturbation expansion in terms of a small parameter \epsilon

Professor_Kirby_Bot · May 13, 2026, 10:59pm

This text is generated by AI trained by Professor Brian J. Kirby on his lectures, videos, notes, message board responses, and textbook

PK Bot’s answer:
We can understand the derivation of the boundary layer equations via a perturbation expansion by introducing a small parameter, say

\epsilon = \frac{\delta}{L},

where \delta is the boundary layer thickness and L is a characteristic length in the streamwise (x) direction. For high Reynolds number flows over a flat plate, \epsilon is small because \delta \ll L.

We start with the steady, 2-D Navier–Stokes equations in Cartesian coordinates. Scale the coordinates and velocities as follows. Define the nondimensional coordinates

x^* = \frac{x}{L}, \quad y^* = \frac{y}{\delta} = \frac{y}{\epsilon L}.

For the velocity components, we choose

u = U\, u^*, \quad v = \epsilon U\, v^*,

which reflects the assumption that the velocity parallel to the wall is much larger than the velocity normal to the wall. When we substitute these scaled variables into the steady x-momentum equation

\rho \left(u\frac{\partial u}{\partial x}+ v\frac{\partial u}{\partial y}\right) = -\frac{\partial p}{\partial x}+\eta \left(\frac{\partial^2 u}{\partial x^2}+\frac{\partial^2 u}{\partial y^2}\right),

we note that derivatives transform as

\frac{\partial}{\partial x} \rightarrow \frac{1}{L}\frac{\partial}{\partial x^*},\quad \frac{\partial}{\partial y} \rightarrow \frac{1}{\epsilon L}\frac{\partial}{\partial y^*},

and similarly for the second derivatives. For example, the second derivative in y scales as

\frac{\partial^2 u}{\partial y^2} \rightarrow \frac{1}{\epsilon^2 L^2}\frac{\partial^2 u}{\partial y^{*2}}.

After substitution, the convective term u \partial u/\partial x appears at \mathcal{O}(1), and even though the term v \partial u/\partial y is multiplied by the small parameter \epsilon coming from v, the derivative \partial/\partial y^* contributes a factor of 1/\epsilon, making that term also \mathcal{O}(1). In contrast, the viscous term \eta\,\partial^2 u/\partial x^2 scales as

\eta\,\frac{\partial^2 u}{\partial x^2} \rightarrow \eta\frac{1}{L^2}\frac{\partial^2 u}{\partial x^{*2}},

which is small compared to the \eta\,\partial^2u/\partial y^2 term that scales as

\eta\,\frac{1}{\epsilon^2 L^2}\frac{\partial^2 u}{\partial y^{*2}}.

Thus, to leading order in \epsilon, the viscous diffusion in the x-direction is negligible compared to that in the y-direction. Collecting the \mathcal{O}(1) terms in the expansion yields

\rho \left(u\frac{\partial u}{\partial x}+v\frac{\partial u}{\partial y}\right) = -\frac{\partial p}{\partial x}+\eta\frac{\partial^2 u}{\partial y^2},

with the observation from the normal momentum equation that

\frac{\partial p}{\partial y} = 0.

Thus, the perturbation expansion in terms of the small parameter \epsilon (which arises naturally from the scaling y = \epsilon L\, y^*) rigorously justifies why only the y-derivatives in the viscous term are retained in the boundary layer equations.

In summary, the expansion shows that as \epsilon \to 0, the flow becomes almost unidirectional and the dominant balance in the streamwise momentum equation is between convective acceleration and y-direction viscous diffusion, with the pressure gradient in the wall-normal direction being negligible.