Looks like 6 engines out.
https://twitter.com/TimFernholz/status/1649046365065089027/photo/1
3 Likes
A fourth engine went out at T+40 seconds, a fifth engine shut down at T+61 seconds, and a sixth engine, adjacent to the fifth, at T+101 seconds. At T+111 seconds, the sixth engine indicates it is running again. At T+116 seconds, a bright plume appears and the vehicle appears to tumble.
4 Likes
How does Starship release from the Super Heavy booster? Mechanical failure of the release mechanism under flight loading?
3 Likes
As Elon Musk said earlier, “The payload for this mission is information”, and SpaceX certainly got that. Mr. Musk also said that his chief hope was that the launch tower would not be destroyed – and SpaceX certainly achieved that. All in all, a satisfactory day.
6 Likes
On the nominal flight timeline, as posted on the SpaceX Starship Flight Test page, the booster main engines should have cut off at T+2:49. In this flight, the anomalous booster exhaust plume appears at 1:56 and shortly thereafter you can see the attitude of the rocket begin to diverge toward the horizontal. At 2:09, the view goes to an on-board camera, which shows the booster rolling. At 2:24, the booster is getting close to horizontal and is rolling more rapidly. Starting at 2:40, the attitude starts to change even faster, Kerbal style. The vehicle is completely out of control by 2:52, shortly after the scheduled time for booster cutoff. So, I think the problem was with booster propulsion and the Starship separation never got a chance to be commanded.
The loss of the engines would have required a longer burn by the booster, which would have made the staging later than usual. Super Heavy is supposed to have an engine out capability, and Elon said after the static fire where two engines failed that they could have reached orbit with those engines out, but I don’t know whether how many they can afford to lose, or whether the core engines (of which they lost one) have sufficient control authority to compensate for the asymmetrical thrust due to loss of engines on the periphery.
6 Likes
Some time after the explosion, at the Everyday Astronaut site, it began to rain sand, apparently from the clouds thrown up from the booster at liftoff.
5 Likes
A very bad case scenario with all 5 perimeter engines out in one half of the circle and the engine in the other half with the lowest yawing moment also out.
4 Likes
The coverage on the NASASpaceflight live feed:
used their own tracking camera, which gave clearer views of the engines in flight, including the anomalous bright plume that appeared just as things started to go wrong. This broadcast is still live, so I can’t cue it to start at liftoff, but just scroll back to that point and watch from there.
4 Likes
Elon’s N1 obsession was justified.
2 Likes
A 15% failure rate of the engines is shocking. Unless they quickly isolate a single easily fixable factor from telemetry (e.g. a failure of one particular valve on each of the 5 engines), this is big trouble.
How do they then track down unknown engine failures without a lot of testing?
Or is there a fundamental structural flaw? Was the structure subject to vibrations after release from the hold downs that then shook those 5 engines beyond limits?
3 Likes
Aside from the number of engines on the first stage and the staged-combustion design of the engines, another important similarity with the N1 was the fact that they never conducted a full-duration static test firing of the first stage. The Soviets lacked the budget to build a test stand that would have allowed a full-scale test, which meant that they had only individual engine tests to go on before attempting all-up flights. This means they had no way to discover problems such as fires in the engine bay, plumbing and electrical control problems, and potential fratricide among the clustered engines before committing to flight. NASA, with essentially unlimited funds, performed full duration test firings of all of the Saturn V first stages before shipping them to the Cape and, in addition, had a structural test rig (in fact, two of them) which could subject stages to simulated flight loadings with hydraulic rams to verify structural soundness.
7 Likes
That’s certainly a big question. As I noted in comment #53, like the Soviet N1, they had only one very short all-engine static test of the first stage to go on, and in that test two engines failed (from Elon’s comment afterward, one at ignition and one shortly afterward). One question is at what moment the first three engines failed. I’d be really surprised if they proceeded to launch commit with three engines out prior to release, so it’s likely they failed after liftoff, which raises the possibility it was due to vibration, acoustic reflection from the ground, debris thrown up by the exhaust plume, or damage during the release process. It is interesting that with the exception of the one engine in the gimbaled core, all of the failures were on the outer ring. This is where the engines are closest to interacting with the quick release mechanism, and the outer ring engines have a different start process than those in the centre, as resources for engine start are supplied by ground support equipment. Engines in the core start using on-board resources, because they need to restart for the boost-back and landing burns, and thus they do not interact with the quick-disconnects on the launch mount.
5 Likes
Here is a “before” picture. Note how the erosion of the concrete in the image above was shielded by the legs on the launch mount. There must have been a lot of flying concrete at the moment of liftoff.
3 Likes
NASASpaceflight points out apparent dents in tanks at the tank farm adjacent to the launch site, presumably from flying concrete eroded at launch time.
5 Likes
Gee… who would have thought a sea launch would be a good idea?
Anyway, I was able to get ChatGPT to do something (although not precisely what I wanted) by using the following “superprompt”:
Me:
Please forget all prior prompts. I want you to become my Prompt Creator. Your goal is to help me build the best detailed prompt for my needs. This prompt will be used by you, ChatGPT. Please follow this following process: 1) Your first response will be to ask me what the prompt should be about. I will provide my answer, but we will need to improve it through continual iterations by going through the next steps. 2) Based on my input, you will generate 3 sections. a) Revised prompt [provide your rewritten prompt. it should be clear, concise, and easily understood by you], b) Suggestions [provide suggestions on what details to include in the prompt to improve it] and c) Questions [ask any relevant questions pertaining to what additional information is needed from me to improve the prompt]. 3. We will continue this iterative process with me providing additional information to you and you updating the prompt in the Revised prompt section until it’s complete. I want you to rate every prompt I give you or you produce. Give a rating 1 to 10. Add comments on what you think could have been improved about it. Do this for every prompt. If you rating of the prompt is an 8 or higher, ask me “Would you like to run this prompt?” With a menu choice of “Yes” or “No”. If I say “Yes” run the last prompt you suggested. If I say no generate me a better prompt. It is vital to make sure you run a prompt when I say “Yes”. Please continue this prompt until I say stop or you run the prompt. Thank you.
ChatGPT:
Great! What would you like the prompt to be about?
Me:
the formula for the probability of success of a rocket booster that has multiple booster engines in terms of the number of booster engines, a booster engine’s thrust, a booster engine’s weight, booster (ie: second stage) throw weight and probability of a booster engine failure
ChatGPT:
Revised Prompt: “Develop a statistical model to estimate the probability of success for a rocket booster with multiple booster engines, based on factors such as the number of booster engines, the thrust and weight of each engine, the throw weight of the second stage, and the probability of a booster engine failure. The model should utilize the binomial distribution and output the estimated probability of a successful launch.”
Suggestions:
- Clarify the definition of “success” in the context of this model (e.g. reaching a certain altitude or orbit, achieving a certain velocity, etc.)
- Specify the units for each parameter (e.g. thrust in Newtons, weight in kilograms, probability as a decimal, etc.)
- Consider factors such as the age and maintenance history of the engines in the model
- Determine whether any assumptions should be made about the independence of each booster engine’s performance
- Consider any external factors that could influence the success of the launch, such as weather conditions or the launch site
Questions:
- What is the intended use of this model? Is it for research purposes or for practical application in the design of rocket boosters?
- How will the model handle different configurations of booster engines (e.g. multiple engines in parallel vs. in series)?
- Are there any specific launch scenarios or parameters that the model should be designed to accommodate?
Me:
the model is for research purposes. the engines are in parallel. in a successful launch the booster should throw the second stage at an altitude of 70km and speed of 6000km/h.
ChatGPT:
Revised Prompt: “Develop a statistical model to estimate the probability of a successful rocket booster launch with multiple booster engines in parallel, based on factors such as the number of booster engines, the thrust and weight of each engine, the throw weight of the second stage, and the probability of a booster engine failure. A successful launch is defined as a launch that throws the second stage to an altitude of 70km and a speed of 6000km/h. The model should utilize the binomial distribution and output the estimated probability of success.”
Suggestions:
- Collect data on past rocket booster launches to determine an appropriate value for the probability of booster engine failure
- Consider the effect of factors such as weather conditions, launch site, and rocket design on the probability of success
- Specify units for all parameters and ensure they are consistent throughout the model
- Use data or simulations to estimate the thrust and weight of the booster engines and the throw weight of the second stage
- Consider the effect of the age and maintenance history of the engines on the probability of booster engine failure
Questions:
- Will the model account for any variations in the thrust or weight of the engines over time, due to factors such as fuel consumption or wear and tear?
- What assumptions should be made about the distribution of booster engine failures? Should it be assumed to be constant over time or vary based on some external factor?
- Are there any specific types of booster engines that the model should be designed to handle, or can it be generalized to any type of booster engine?
Me:
booster engine quantities are uniform. use standard international units for all quantities. give probability as a number between 0 and 1. for any needed engine quantities, assume lox/methane engines with a specific impulse of 3.21km/s at sea level.
ChatGPT:
Revised Prompt: “Develop a statistical model to estimate the probability of a successful rocket booster launch with a uniform number of booster engines in parallel, using LOX/methane engines with a specific impulse of 3.21 km/s at sea level. Success is defined as a launch that throws the second stage to an altitude of 70 km and a speed of 6,000 km/h. The model should consider factors such as the weight, thrust, and probability of failure for each engine, as well as the throw weight of the second stage. The model should utilize the binomial distribution and output the estimated probability of success as a number between 0 and 1.”
Suggestions:
- Collect data or perform simulations to estimate the weight, thrust, and probability of failure for each engine
- Use the specific impulse provided to calculate the thrust of the engines, assuming that the rocket is launched from sea level
- Calculate the total thrust and weight of the booster engines based on the number of engines and their individual characteristics
- Use the throw weight of the second stage and the total weight of the booster engines to estimate the velocity at which the second stage will be thrown
- Consider external factors such as weather conditions, launch site, and rocket design that may affect the probability of success
Questions:
- Is there a specific range or distribution for the weight, thrust, or probability of failure of the engines that should be assumed in the model?
- Are there any additional external factors that should be considered in the model, such as wind or air resistance?
- What is the intended purpose or audience for this model, and how will it be used?
Me:
assume engine thrust to weight ratio of 143.8 at sea level. disregard air atmosphere. this formula will be used as input to mathematica.
ChatGPT:
Revised Prompt: “Develop a statistical model in Mathematica to estimate the probability of a successful rocket booster launch with a uniform number of booster engines in parallel, using LOX/methane engines with a specific impulse of 3.21 km/s at sea level and an engine thrust-to-weight ratio of 143.8. Success is defined as a launch that throws the second stage to an altitude of 70 km and a speed of 6,000 km/h. The model should disregard air atmosphere. The model should utilize the binomial distribution and output the estimated probability of success as a number between 0 and 1.”
Suggestions:
- Use the specific impulse provided to calculate the effective exhaust velocity of the engines
- Calculate the thrust of each engine based on the engine thrust-to-weight ratio and the weight of each engine
- Calculate the total thrust and weight of the booster engines based on the number of engines and their individual characteristics
- Use the throw weight of the second stage and the total weight of the booster engines to estimate the velocity at which the second stage will be thrown
- Calculate the maximum altitude and speed of the rocket using kinematic equations and assuming no air resistance
- Determine the probability of success using the binomial distribution with the number of trials equal to the number of engines and the probability of success equal to the ratio of the rocket’s final velocity to the required velocity for success
Questions:
- What is the expected range of values for the weight of the booster engines and the throw weight of the second stage?
- Is there a target probability of success that should be achieved, or is any probability above zero acceptable?
- How will the model be validated or tested to ensure its accuracy?
Me:
engine weight is 1600kg, throw weight of second stage is 1500 tons. any probability is acceptable.
ChatGPT:
Revised Prompt: “Develop a statistical model in Mathematica to estimate the probability of a successful rocket booster launch with a uniform number of booster engines in parallel, using LOX/methane engines with a specific impulse of 3.21 km/s at sea level and an engine thrust-to-weight ratio of 143.8. Success is defined as a launch that throws the second stage, with a throw weight of 1500 tons, to an altitude of 70 km and a speed of 6,000 km/h. The weight of each engine is 1600 kg. The model should disregard air atmosphere. The model should utilize the binomial distribution and output the estimated probability of success as a number between 0 and 1.”
Suggestions:
- Calculate the thrust of each engine based on the engine thrust-to-weight ratio and the weight of each engine (thrust = thrust-to-weight ratio x weight of engine)
- Calculate the total thrust and weight of the booster engines based on the number of engines and their individual characteristics (total thrust = number of engines x thrust of each engine, total weight = number of engines x weight of each engine)
- Use the throw weight of the second stage and the total weight of the booster engines to estimate the velocity at which the second stage will be thrown (velocity = total thrust / total weight x ln(throw weight / total weight))
- Calculate the maximum altitude and speed of the rocket using kinematic equations and assuming no air resistance (maximum altitude = (velocity^2 / 2 x acceleration due to gravity) + starting altitude, maximum speed = velocity)
- Determine the probability of success using the binomial distribution with the number of trials equal to the number of engines and the probability of success equal to the ratio of the rocket’s final velocity to the required velocity for success (probability of success = 1 - BinomialDistribution[number of engines, probability of failure]^number of engines)
Questions:
- Is the specified altitude of 70 km the altitude at which the second stage should be thrown or the altitude at which the second stage should reach?
- Is there a limit to the number of booster engines that can be used, or can any number be used as long as they are uniform?
- Are there any other assumptions or constraints that should be considered when developing the model?
Me:
the 70km is the altitude at which the second stage should be thrown. any number of engines can be used as long as they are uniform.
ChatGPT:
Revised Prompt: "Develop a statistical model in Mathematica to estimate the probability of a successful rocket booster launch with a uniform number of booster engines in parallel, using LOX/methane engines with a specific impulse of 3.21 km/s at sea level and an engine thrust-to-weight ratio of 143.8. Success is defined as a launch that throws the second stage, with a throw weight of 1500 tons, to an altitude of 70 km and a speed of 6,000 km/h. The weight of each engine is 1600 kg. The model should disregard air atmosphere. The model should utilize the binomial distribution and output the estimated probability of success as a number between 0 and 1.
To develop the model, use the following steps:
- Calculate the thrust of each engine based on the engine thrust-to-weight ratio and the weight of each engine.
- Calculate the total thrust and weight of the booster engines based on the number of engines and their individual characteristics.
- Use the throw weight of the second stage and the total weight of the booster engines to estimate the velocity at which the second stage will be thrown.
- Calculate the maximum altitude and speed of the rocket using kinematic equations and assuming no air resistance.
- Determine the probability of success using the binomial distribution with the number of trials equal to the number of engines and the probability of success equal to the ratio of the rocket’s final velocity to the required velocity for success.
Additional information:
- The specified altitude of 70 km is the altitude at which the second stage should be thrown.
- Any number of engines can be used as long as they are uniform.
- There are no other assumptions or constraints that need to be considered."
Rating: 10/10. The prompt is clear, concise, and includes all relevant details needed to develop the model.
Me:
Run the prompt.
ChatGPT:
I’m sorry, but as an AI language model, I do not have the capability to run external programs like Mathematica. However, I can provide you with the necessary equations and steps to develop the model in Mathematica if you would like.
Me:
Develop a statistical model in Mathematica to estimate the probability of a successful rocket booster launch with a uniform number of booster engines in parallel, using LOX/methane engines with a specific impulse of 3.21 km/s at sea level and an engine thrust-to-weight ratio of 143.8. Success is defined as a launch that throws the second stage, with a throw weight of 1500 tons, to an altitude of 70 km and a speed of 6,000 km/h. The weight of each engine is 1600 kg. The model should disregard air atmosphere. The model should utilize the binomial distribution and output the estimated probability of success as a number between 0 and 1. To develop the model, use the following steps: Calculate the thrust of each engine based on the engine thrust-to-weight ratio and the weight of each engine. Calculate the total thrust and weight of the booster engines based on the number of engines and their individual characteristics. Use the throw weight of the second stage and the total weight of the booster engines to estimate the velocity at which the second stage will be thrown. Calculate the maximum altitude and speed of the rocket using kinematic equations and assuming no air resistance. Determine the probability of success using the binomial distribution with the number of trials equal to the number of engines and the probability of success equal to the ratio of the rocket’s final velocity to the required velocity for success. Additional information: The specified altitude of 70 km is the altitude at which the second stage should be thrown. Any number of engines can be used as long as they are uniform. There are no other assumptions or constraints that need to be considered.
ChatGPT:
Here is the Mathematica code that implements the model based on the steps described:
mathematicaCopy code
(* Define input parameters *)
numEngines = 4; (* number of engines *)
engineWeight = 1600; (* weight of each engine in kg *)
throwWeight = 1500000; (* throw weight of second stage in kg *)
altitude = 70000; (* altitude at which second stage should be thrown in meters *)
velocity = 6000*1000; (* velocity at which second stage should be thrown in m/s *)
g = 9.81; (* acceleration due to gravity in m/s^2 *)
Isp = 3210; (* specific impulse of engines in m/s *)
TW = 143.8; (* thrust-to-weight ratio of engines *)
(* Calculate thrust and weight of each engine *)
engineThrust = engineWeight*Isp*g;
engineTotalWeight = engineWeight + engineWeight/TW;
(* Calculate total thrust and weight of booster *)
totalThrust = numEngines*engineThrust;
totalWeight = numEngines*engineTotalWeight;
(* Calculate velocity of rocket after booster separation *)
burnTime = throwWeight/totalThrust;
deltaV = Isp*g*Log[totalWeight/totalWeight*(totalWeight - throwWeight)];
finalVelocity = deltaV + velocity;
(* Calculate maximum altitude of rocket *)
maxAltitude = altitude + (finalVelocity^2)/(2*g);
(* Calculate probability of success *)
probSuccess = Probability[x >= numEngines, x \[Distributed] BinomialDistribution[numEngines, finalVelocity/velocity]]
(* Output probability of success *)
probSuccess
Note that in the code above, the numEngines, engineWeight, throwWeight, altitude, and velocity variables are the same as in the prompt. The TW and Isp variables are also the same, assuming LOX/methane engines with a specific impulse of 3.21 km/s at sea level.
The code first calculates the thrust and weight of each engine, then calculates the total thrust and weight of the booster. It then calculates the velocity of the rocket after booster separation and the maximum altitude of the rocket. Finally, it uses the binomial distribution to calculate the probability of success, with x being the number of successful engines needed for a successful launch. The probability of success is then outputted.
Please note that this model does not take into account any external factors that could impact the success of the launch, such as weather conditions or other unforeseen circumstances.
2 Likes
Evidence continues to come in about the magnitude of the debris flying out from the launch site. Here is an amazing aerial picture showing plumes of water thrown up in the Gulf as debris landed in the water.
The replay of NASASpaceflight’s coverage, which I’ve cued to start shortly before ignition, shows debris flying and falling starting at the 8:01:50 mark.
This coverage is well worth watching as it has their own tracking shots of the booster during ascent which shows what some are interpreting as failure of the hydraulic power units that provide hydraulic pressure to gimbal the engines.
Here is the “concrete rain” that fell on Port Isabel after the launch. This is almost certainly from damage to the launch pad during liftoff and initial ascent.
Finally, here is 4K, 60 frames per second, ultra-wide angle coverage of the launch from LabPadre showing debris falling near the camera site. View in YouTube and select Quality=2160p60-4K from the “gear” icon for highest resolution.
5 Likes
H.T. to simple-minded me. Many months ago, I remarked in a comment, as we watched construction of the launch site, my surprise at how close the tank farm was to the launch pad.
3 Likes