Rocket Engine Design

tahanson43206 · 2025-05-24 08:02:49

This topic is offered in support of NewMars members who might want to collect links, images and text on this important topic.

The topic itself is created to provide a venue for GW Johnson's explanation of the possible/probable cause of 10 Hertz vibrations observed by Dr. Johnson as SpaceX tests the new rocket engines at their nearby test facility.

GW has observed that the windows in his home rattle at about 10 Hertz, below audibility but easily observable as vibration of the house.

(th)

tahanson43206 · 2025-05-24 08:03:50

This post is reserved for an index to posts that may be contributed by NewMars members over time.

Index:

(th)

tahanson43206 · 2025-05-24 09:27:11

This post contains email correspondence with GW Johnson, about the oscillations that may contribute to the POGO effect.

On 5/24/25 09:01, Gary Johnson wrote:
> I rather doubt that the usual quarter-wave organ pipe oscillation is involved. The dimensions are too short and the sound speed is too high. This more likely involves some kind of vortex shedding which happens to be periodic at some frequency. That is called the Strouhal effect.
>
> If there are fuel-rich and oxidizer-rich regions (and there always are), vortices of mostly one species can break off and travel into the other species, ingesting it, and then suddenly exploding. That explosion wave may be impacting the rate at which propellants are coming through the injection orifices, in turn affecting the thrust and pressure of the engine.
>
> The engine cycle being what it is (complex), there are pre-burner volumes ahead of the injectors that can hold and release the flow perturbations, sort of like Helmholtz resonators. If any of this "resonates" at the vortex shedding frequency, there you have the feedback loop!
>
> You change the geometry at or near the injector orifices to interrupt this process by changing or eliminating the vortex shedding frequency. In the Saturn-5 first stage F-1's, they installed fences around groups of injectors, which sort-of mostly worked, once they stumbled on the right fence geometry. I don't think they ever did fix the second stage engines correctly, which is why Apollo-13 lost a second stage engine during its ascent, something forgotten in the wake of the oxygen tank explosion in the service module a few hours later.
>
> It would not surprise me to learn that second-stage thrust oscillations are what damaged the Skylab insulation and solar panel wing, when that item went up. However, I don't know the truth of that.
>
> GW
>
> On Fri, May 23, 2025 at 8:05PM Tom Hanson <tahanson43206@gmail.com> wrote:
>
> Hi Dr. Johnson!
>
> Thanks for considering my question! There ** must ** be physics at work in creating the oscillations you are observing.
>
> An organ pipe can be tuned all the way down to 8 Hertz (according to Google)
>

(th)

tahanson43206 · 2025-05-24 09:39:17

This post contains a collection of snippets Google put together about the "strouhal effect" as cited by GW Johnson in post #3

The Strouhal effect refers to the phenomenon where vortex shedding occurs around an object in a fluid, creating a periodic pattern of vortices downstream. This vortex shedding can induce vibrations in the object, leading to phenomena like the whistling of telephone wires or the flapping of a flag. The Strouhal number quantifies the relationship between the frequency of vortex shedding, the characteristic length of the object, and the fluid velocity.
Here's a more detailed explanation:
1. Vortex Shedding:
When a fluid flows past an object, such as a cylinder, the fluid can separate from the object's surface and create swirling regions of fluid called vortices.
These vortices detach from the object periodically, creating a pattern of alternating vortices downstream known as a Kármán vortex street.
2. Strouhal Number (St):
The Strouhal number is a dimensionless parameter that describes the relationship between the frequency of vortex shedding (f), the characteristic length of the object (e.g., cylinder diameter, D), and the fluid velocity (U).
The Strouhal number is calculated as: St = f * D / U
3. Impact on Structures:
If the frequency of vortex shedding matches the natural frequency of a structure, it can lead to significant vibrations.
This can result in phenomena like the whistling of telephone wires or the flapping of a flag in the wind.
Structures exposed to vortex shedding can also experience fatigue damage due to the vibrations.
4. Reynolds Number (Re):
The Reynolds number is another dimensionless parameter that describes the flow regime (laminar, turbulent, or transitional).
The Strouhal number and Reynolds number are related in that the Strouhal number for vortex shedding can vary with the Reynolds number.
5. Applications and Examples:
Structures:
Understanding vortex shedding and the Strouhal number is crucial in designing structures that can withstand wind forces, such as bridges, buildings, and towers.
Aircraft:
Vortex shedding can also impact aircraft designs, particularly in situations involving flaps or control surfaces.
Nature:
The whistling of telephone wires, the flapping of flags, and even the sounds produced by certain musical instruments can be attributed to vortex shedding.
In essence, the Strouhal effect highlights the importance of fluid dynamics in understanding the behavior of structures and objects in fluid flow, and it plays a crucial role in various engineering and natural phenomena.
Vortex shedding - Wikipedia
Governing equation The frequency at which vortex shedding takes place for a cylinder is related to the Strouhal number by the foll...
Wikipedia
Strouhal Number - an overview | ScienceDirect Topics
ScienceDirect.com
Kármán vortex street - Wikipedia
In fluid dynamics, a Kármán vortex street (or a von Kármán vortex street) is a repeating pattern of swirling vortices, caused by a...
Wikipedia
https://en.wikipedia.org › wiki › Strouhal_number
The Strouhal number (St, or sometimes Sr to avoid the conflict with the Stanton number) is a dimensionless number describing oscillating flow mechanisms.
Derivation
Applications
Scaling of the Strouhal number
Scale Analysis
People also ask
What does the Strouhal number tell us?
What is the effect of vortex shedding?
What is the importance of Strouhal number?
What is the Karman vortex effect?
Feedback
Strouhal Number - an overview
ScienceDirect.com
https://www.sciencedirect.com › topics › engineering › st...
The Strouhal number represents the ratio of inertial forces due to the local acceleration of the flow to the inertial forces due to the convective acceleration.
Images
Relationship between Strouhal Number and Reynolds number for ...
Relationship between Strouhal Number and Reynolds number for ...
ResearchGate
Strouhal number - Wikipedia
Strouhal number - Wikipedia
Wikipedia
Strouhal Number - an overview | ScienceDirect Topics
Strouhal Number - an overview | ScienceDirect Topics
ScienceDirect.com
Show more images
Strouhal Number - an overview
ScienceDirect.com
https://www.sciencedirect.com › physics-and-astronomy
The Strouhal Number is a dimensionless parameter that describes the oscillating flow mechanism and represents the ratio of vibration-to-flow velocities.
karman vortex shedding and the strouhal number
Vibrationdata
http://www.vibrationdata.com › tutorials2 › strouhal
PDF
by T Irvine · 2009 · Cited by 1 — This effect is readily apparent as trees are bent backward by the oncoming wind pressure. Wind may also exert a lift force and moment upon a ...
8 pages
Effect of crossflow oscillation Strouhal number on circular ...
AIP.ORG
https://pubs.aip.org › aip › pof › article › Effect-of-cros...
Sep 11, 2023 — At a fixed crossflow oscillation Strouhal number, the wake vortex-shedding Strouhal number increases as the crossflow Reynolds number increases ...
Effect of Strouhal Number on the Flow Field of a Turbulent ...
Aerospace Research Central
https://arc.aiaa.org › doi › pdfplus
The global mean velocity field showed that with increasing primary jet Strouhal number, the centerline velocity decays faster and the potential core length ...
Strouhal number effect on synchronized vibration range of a ...
International Atomic Energy Agency (IAEA)
https://inis.iaea.org › records
by T Kawamura · 2001 · Cited by 14 — Synchronized vibrations were measured for a circular cylinder subjected to a water cross flow in the subcritical Reynolds numbers in order ...
Strouhal–Reynolds number relationship for flow past a circular ...
The University of Western Australia
https://research-repository.uwa.edu.au › files › Ac...
PDF
by H Jiang · 2017 · Cited by 113 — The Strouhal–Reynolds number (St–Re) relationship for flow past a circular cylinder in the low Re range of Re ≤ 1000 is investigated through two-dimensional.
29 pages
Effect of excitation Strouhal number on a backward ...
AIP.ORG
https://pubs.aip.org › aip › pof › article › Effect-of-exci...
Mar 4, 2024 — The flame became more and more turbulent due to the increase in the excitation Strouhal number. This category of flame can be observed within ...

This topic is available for additional contributions NewMars members might care to make to help readers to understand the complex problem that shows up in rocket engine operation upon occasion. Apparently only certain designs encounter this problem.

(th)

SpaceNut · 2025-05-25 05:23:41

There is one more piece to the puzzle and that is the change of temperature over the length of the fule line as it oscilates. This is a simular item for underground conduit that requires a sleeve that moves to compensate for the cycle of winter to summer.

tahanson43206 · 2025-06-01 06:26:31

This topic is intended to provide a resource for anyone thinking about designing a rocket engine for use in a space vessel.

The topic is wider in scope than the related Rocket Nozzle Design topic, because it includes the integration of the engine into the vehicle.

The post quoted below by GW Johnson includes consideration of the use of plumbing in a space vessel that may be subject to resonance with any oscillations that may occur in an engine during operation. The vessel designer would (presumably) think about acoustic resonance along with many other tradeoffs that must be made in planning an entire system.

GW Johnson wrote:

You completely missed my points.
There is some kind of 10 Hz pressure oscillation in the engine chamber. I can feel those effects from 6 miles away, and they are there whether or not there is any sort of plumbing around the engine.
In the ship, but not the test stand in McGregor, there are particular forms of plumbing that might be susceptible to being driven by that 10 Hz oscillation in engine pressure, via the mechanical shaking of the engine in its mountings in the stage. That is because of the lengths of feed piping in the ship (that are not there at McGregor). You have to pipe propellants from the tanks to the engines. One of the header tanks has been in the nose, almost 50 meters away. The lengths are there to hit one of the first couple of harmonics to that 10 Hz oscillation.
If the plumbing responds to the 10 Hz shake by its contained fluid resonating with it, that could affect the propellant flow, which literally is the energy release rate in the chamber, so there is the possibility that there could be an energy feedback from engine to plumbing and back to engine. The engine shake drives a wave in the plumbing, which affects flow rate, which increases the intensity of the vortex shedding oscillations in the chamber. If the wave in the plumbing gets strong enough, the pressure nodes of it it break a tube or a fitting somewhere. And THAT effect is exactly what they have been describing with their talk about oscillations and fuel leaks.
It does not matter one tinker's damn that there is no ship or ship-like plumbing at the McGregor test stands! The initiating oscillation in the engine is still there! Which is what I have been feeling from all three versions of Raptor. There is nothing outside the engine for it to interact with. Put the engine in the ship, and there is.
Merlin does not seem have this problem with pressure oscillations in its chamber, at least not at a strength that I can observe. But it burns kerosene, not methane! That's inherently a sooty flame, and that soot cloud is a draggy inertia on the gas oscillations, acting to damp them down. So, even if the propellant injection geometry is identical in both engines, and so cause the same exploding-vortex shedding, the two engines are just not very likely to respond in the same way, as one has a damping cloud in it, the other does not. Methane burns virtually soot-free.
GW

(th)

GW Johnson · 2025-06-01 11:44:30

The usual procedure would be to compute an appropriately-defined Reynolds number, and use a correlation to estimate Strouhal number from that Reynolds number, and finally use the Strouhal number to estimate the vortex shedding frequency. For most blockage-type items, this flow pattern is called a Von Karmann vortex street, but there are other vortex-shedding situations. And no, I don't have any handy-dandy Strouhal-Reynolds correlations. Those would all be different for each specific different case. Nothing "general".
-------
Update 6-2-2025: I spent some time looking through my old aerodynamics books, and did find one correlation in my old copy of Hoerner's drag bible. That would be Sighard F. Hoerner, "Fluid Dynamic Drag", self-published by the author in 1965; chapter 3, page 3-6, Figure 7, and equation (13). It's for vortex streets shed by any sort of element for which a blockage-based drag coefficient CD can be defined. S = 0.21/(CD^0.75) is the best curve fit of Strouhal number S vs the CD for a variety of element shapes across a fairly wide range of CD's.

The figure says this is for Reynolds numbers "above 1000" (based on blockage dimension). It would be for well-subsonic flow, too, so Reynolds number would be very unlikely to approach a million. Note that blockage CD is usually determined in part by shape and in part by Reynolds number. Its reference area definition is the frontal blockage area of the element. Which is is line with what I said above.

Estimate frequency f = S*V/D, where V is the flow speed past the element, and D is its typical size dimension. S is the Strouhal number estimated from blockage CD correlation equation. (He did not have rocket engine chamber geometry in mind when he included this correlation!! But, believe it or not, he did have submarine periscopes, as well as civil construction items, to include buildings.)

Then you compare that shedding frequency f to whatever resonant fluid oscillation, or structural vibration, frequencies that there might be,
anywhere associated with your element. (These interactions can be quite unexpected, too!) Where the shedding frequency f is close to any of the oscillation or vibration mode frequencies, you have the risk of resonant feedback producing very high oscillation or vibration amplitudes in those associated items. Usually the fundamental mode and only the first couple of harmonics are of concern. But not always!

BTW, Hoerner was the aerodynamicist for the Messerschmidt Bf-109 fighter airplane project in 1930's Germany. He immigrated to the US after the war.
-------
And by the way, it is vortex shedding in Von Karmann vortex street (with a Strouhal number) that knocked down the Tacoma Narrows suspension bridge deck in 1940, only months after it first opened. The bridge was known to some as "Galloping Gertie", because of the way its bridge deck moved in the strong winds. As it turned out, there was a mechanical oscillation mode of twisting the bridge deck that had a certain natural frequency.

Shedding frequency varies with wind speed, all else equal. The wind was never quite strong enough for the vortex shedding frequency to exactly match the twisting vibration frequency, until the fateful day. Once that match happened, the amplitude of the deck twisting motions reached plus to minus 45 degrees off plumb (that's 90 degrees limit-to-limit!). The steel got "tired" very quickly, and the whole deck collapsed.

They learned two things from this: (1) no more two-lane suspension bridges with a narrow, easily-twisted deck, which changes greatly the natural vibration frequencies, and (2) put some holes through the side girders to let the wind through the deck structure, which reduces, or even completely interrupts, the formation of the vortex street, which is the excitation for all this risk.

In airplanes, they call it "flutter", but it's pretty much the same kind of dynamics.

GW

Last edited by GW Johnson (2025-06-02 08:22:31)

SpaceNut · 2025-06-02 17:03:59

One can think of the engine bell as having functions simular to a trombone in that the vibration starts at the mouth piece and due to changing of slide position you hear the note out of the bell. Change the slide and the sound of the note will shift.

https://www.youtube.com/watch?v=Atqn9WoYRHA

To change a note on a guitar string you apply pressure to the string at a fret and the string when struck produces a note, move the finger to another fret and with the same strike of the string the note shifts.
we would have

the next fret is a half step up, and the same for each step the tone will rise

Harmonics of a string is the center of the length of whch you will hear the first when placing a finger lightly to the string while striking it.
https://www.youtube.com/watch?v=mZ6HKrFFM_4&t=405s

So to change the harmoncis can be done with a piece of sleeve at the intervals to move the sound of the low note that the rocket engine plays.

tahanson43206 · 2025-06-02 18:28:53

For SpaceNut re #8

Your observations about sound produced by various instruments seems to me a good way to encourage our readers to think about how rocket engines work, and how something in a design might lead to a rhythmic pattern. My understanding is that a rocket engine designer would prefer NOT to see any such regular frequency pattern. I asked Google's Gemini to ** think ** about the situation, and it shared with me that the Raptor has a design that I'd not heard about before. I'm hoping that at least one other NewMars reader might be interested. Here is a part of my exchange with Gemini:

You mentioned the Raptor may use "staged combustion cycle". I'm not familiar with that concept and wonder if it could account for the strong 10 Hertz signal? We are pursuing this because the Starships have had breakups in recent tests, although the most recent flight did not fail due to engine failure.
Yes, the staged combustion cycle of the Raptor engine could indeed be a contributing factor to the strong 10 Hz signal, potentially through its influence on combustion stability. Let's explore this:
The Staged Combustion Cycle and Raptor:
The Raptor engine utilizes a full-flow staged combustion (FFSC) cycle. In simplified terms, this means:
Preburners: Instead of burning a small amount of propellant to drive the turbines (like in a gas-generator cycle), the Raptor has two preburners. One is fuel-rich (mostly methane with some oxygen), and the other is oxidizer-rich (mostly oxygen with some methane).
Turbines: These preburners drive separate turbines connected to the fuel and oxidizer pumps.
Main Combustion Chamber: The exhaust from both preburners, now hot and pressurized, is then injected into the main combustion chamber where it undergoes complete combustion.
Why this might relate to the 10 Hz vibration:
Increased Complexity and Potential for Instabilities: Staged combustion, especially full-flow, is a very complex process. The intricate dance of propellant flow, pre-combustion, and main combustion can create conditions where instabilities are more likely to arise compared to simpler cycles.
Combustion Instability: Rocket engines are known to be susceptible to combustion instabilities, which are high-frequency (and sometimes low-frequency) oscillations in pressure and combustion within the chamber. These can be very destructive. While engineers design engines to avoid these, they can sometimes manifest, especially in new and high-performance designs.
Low-Frequency Oscillations ("Chugging"): While high-frequency instabilities are more commonly feared for causing immediate damage, lower-frequency oscillations (like the observed 10 Hz, sometimes called "chugging" at slightly higher frequencies) can also occur due to interactions between the propellant feed system and the combustion process. The complex flow dynamics in a staged combustion engine might make it more prone to certain types of these interactions.
Vortex Shedding Revisited: Even within the context of staged combustion, the engineer's hypothesis about vortex shedding due to mixing issues could still be relevant. The way the preburner exhaust mixes in the main chamber could create conditions for vortex formation, leading to pressure oscillations at a specific frequency.

(th)

New Mars Forums

Announcement

#1 2025-05-24 08:02:49

Rocket Engine Design

#2 2025-05-24 08:03:50

Re: Rocket Engine Design

#3 2025-05-24 09:27:11

Re: Rocket Engine Design

#4 2025-05-24 09:39:17

Re: Rocket Engine Design

#5 2025-05-25 05:23:41

Re: Rocket Engine Design

#6 2025-06-01 06:26:31

Re: Rocket Engine Design

#7 2025-06-01 11:44:30

Re: Rocket Engine Design

#8 2025-06-02 17:03:59

Re: Rocket Engine Design

#9 2025-06-02 18:28:53

Re: Rocket Engine Design

Board footer