F-35 pilot held 50-minute airborne conference call with engineers before crash
The pilot was not part of the conference call!
What froze was not hydraulic fluid for actuators (in some hydraulic line), but hydraulic fluid in the shock absorbers.
The last paragraph of the article and seems to be missing a few words and reads as the investigators blaming the people directly involved, which is essentially a complete opposite of what conclusions of the report say.
Opening line:
A US Air Force F-35 pilot spent 50 minutes on an airborne conference call with Lockheed Martin engineers trying to solve a problem with his fighter jet before he ejected
Am I illiterate or misreading it?
After going through system checklists in an attempt to remedy the problem, the pilot got on a conference call with engineers from the plane’s manufacturer, Lockheed Martin, *as the plane flew near the air base. *
Is this actually some insane weasel-wording by CNN? "We never said the pilot (he is in fact a pilot) was the one flying the jet, we just said 'as the plane flew', not 'as he flew the plane', using passive voice, so we're not wrong - but it was another pilot flying the plane"
But I'm interested in the reporting. There are, you know, journalistic standards, which are considered kinda "journalism 101"! For instance, getting the basic facts of a story correct - especially the facts stated in the headline.
So I'm curious, did the reporter do their due diligence, and write the article in a way that is factually correct, but highly misleading? Or did they simply not follow basic reporting protocol?
The MP initiated a conference call with Lockheed Martin engineers through the on-duty supervisor of flying (SOF). The MA held for approximately 50 minutes while the team developed a plan of action.
Seems accurate to what CNN was reporting. It's simplified a bit, but it's not misleading to me.
I mean, I guess if you want to nit pick and suggest "No the pilot wasn't literally on a phone and there was an intermediary in between" or some such, but the report makes it seem like CNN is accurate.
https://www.pacaf.af.mil/Portals/6/documents/3_AIB%20Report....
But I'm interested in the reporting. There are, you know, journalistic standards, which are considered kinda "journalism 101"! For instance, getting the basic facts of a story correct - especially the facts stated in the headline.
Every single story is like this, every one, and f-them for not linking to the source documents.
There are, you know, journalistic standards, which are considered kinda "journalism 101"!
Pretty sure you meant to use the past tense here: "There _were_ journalistic standards..."
"At 21:12:52Z, the SOF informed the MP, “Alright the engineers uh are not optimistic about this COA but, extremely low PK [probability kill, meaning the probability this would fix the issue], but we’re going to try anyway is a touch-and-go on the runway, mains only, do not touch the nose gear, uh lift back off in all cases and have the uh have Yeti 4 reconfirm the nose gear position once your safely airborne.”"
No need for this if the pilot was on the call directly.
The MP initiated a conference call with Lockheed Martin engineers through the on-duty supervisor of flying (SOF). The MA held for approximately 50 minutes while the team developed a plan of action.
"though the SOF" implies a middle-man, but I imagine that's because you don't want literally hook up a conference call directly to the cockpit. That being said, seems like the pilot was effectively on the conference call.
Unless you want to suggest I don't trust the report?
https://www.pacaf.af.mil/Portals/6/documents/3_AIB%20Report....
The MP initiated a conference call with Lockheed Martin engineers through the on-duty supervisor of flying (SOF)
"MP" is the pilot
A conference hotel is a call that can be initiated by the SOF to speak directly with Lockheed Martin engineers to discuss an abnormality/malfunction not addressed in the PCL (Tab V-13.1, 14.1, 15.1, 16.1, 17.1). While waiting for the conference hotel to convene, the MP initiated a series of “sturns” with gravitational forces up to 2.5Gs, as well as a slip maneuver (i.e., left stick input with full right rudder pedal) to see if the nose wheel orientation would change (Tabs N-12, BB-201- 02). Upon visual inspection, the MW reported no change to the nose wheel (Tab N-13). The SOF informed the MP he was on the phone with the conference hotel and Lockheed Martin were getting the LG subject matter experts (SME)
So the pilot was, in effect, on the call, even if not directly on the phone. I don't know for sure, but I'm guessing an F-35 pilot had radio comms with the SOF who was on a phone line. It's a layer of indirection, but the pilot was essentially exchanging info in real time with the conference call. Its not a stretch to colloquially say that the pilot was "in the conference call"
The MP initiated a conference call with Lockheed Martin engineers through the on-duty supervisor of flying (SOF). The MA held for approximately 50 minutes while the team developed a plan of action.
I read this as "The pilot initiated a conference call, but was put on hold [i.e. not actually in the conference call in any meaningful way]." So he was both on and not on the conference call.
The Zen Koan of the Mishap Pilot. Sounds like an Iron Maiden song.
The article is somewhat sensationalistic
somewhat sensationalistic?! The article clearly tries to give the impression the pilot was on the call:
A US Air Force F-35 pilot spent 50 minutes on an airborne conference call with Lockheed Martin engineers trying to solve a problem with his fighter jet before he ejected
Knowing the quality of media these days, it wouldn't surprise me if it CNN just got it really wrong, but also wouldn't surprise me they'd do some brazen lie for clicks.
Edit: Reading the report, it seems like you, dear fellow HN commentator, got it wrong in this case, sorry to say :) Seems indeed the pilot itself was on the call:
The mishap pilot (MP), assigned to the 354th FW, ejected safely before impact. [...] The MP initiated a conference call with Lockheed Martin engineers. The MA held for approximately 50 minutes while the team developed a plan of action
Page 35 from https://www.pacaf.af.mil/Portals/6/documents/3_AIB%20Report....
Boeing has an emergency response program called “Conference Hotel” (USAF) or called “Conference X-Ray” (USN/USMC) to provide units with engineering and test pilot expertise during airborne emergencies. This 24 hour a day service is available by calling (866)543-5### toll free or commercial (314) 232-9###. Callers may also contact the regional DSN operator at DSN 693-1### and ask to be connected to the Boeing STL operator at (314) 232-9###. It can also be used overseas via long distance phone lines or MARS radio patches. When the Boeing operator answers, callers must identify themselves and request Conference Hotel or Conference X-Ray assistance. The operator will ask for specific information to identify the appropriate Boeing personal to respond. Conference Hotel or Conference X-Ray is available to assist in airborne emergencies only. Do not utilize this capability as a part of pre-mishap drills.
F/A-18E/F Aircraft Crash Rescue; Fire Fighting Information; January 2006
The MP initiated a conference call with Lockheed Martin engineers through the on-duty supervisor of flying (SOF). The MA held for approximately 50 minutes while the team developed a plan of action.
So it was the SOF on the conference call, relaying information to and from the pilot over the radio. This is more clear if you read the sequence of events on pages 7-10.
Not that it makes that much of a difference. Either way, he's up there waiting for the engineers on the ground to troubleshoot the problem.
The MP initiated a conference call with Lockheed Martin engineers. The MA held for approximately 50 minutes while the team developed a plan of action - Page 35
And
The MP initiated a conference call with Lockheed Martin engineers through the on-duty supervisor of flying (SOF). The MA held for approximately 50 minutes while the team developed a plan of action - Page 2
I quoted from the Page 35, you quoted from the Page 2, not confusing at all of them to have very similar stuff with slightly different meaning, all in the same document :) Thanks nonetheless for the additional context!
I'd compare it to being in the room with someone on a conference phone call and they're relaying the conversation to you and them both ways. I would still say you were participating in the call even though you weren't directly on the call.
Also, he did initiate the call so "F-35 pilot held" is imprecise, but not totally wrong. Either way, the pilot was in an active tech support session with the plane engineers, making this one of the most intense tech support calls in history.
https://www.pacaf.af.mil/Portals/6/documents/3_AIB%20Report....
Edit: While CNN says the air force blamed the crash on ice in the hydraulic lines, it's obvious that ice can't be legally culpable. The report actually says:
Additionally, the [Accident Investigation Board] president found, by a preponderance of the evidence, that crew decision making including those on the in-flight conference call, lack of oversight for the Hazardous materials program, and lack of adherence to maintenance procedures for hydraulic servicing were substantially contributing factors.
They note further down that "The 355th FGS hazardous materials program (HAZMAT) program suffered from insufficient manning and frequent supervision changes at times relevant to the mishap." Basically, they had a barrel of hydraulic oil that sat outside and no one took care of it.
Also interesting is the 6 February 2025 incident, where another aircraft, barely a week after the one that crashed, had the same issue. They tested it inside a heated hangar, then outside in the 15F cold where they reproduced the weight-on-wheels sensor malfunctions, then brought it back in and drained the hydraulic fluid...there's a TON of water in those lines! I'm more familiar with industrial hydraulics in factories and earth-moving equipment, not with aviation...but we have water separators because a few drops of water can be enough to mess with the servo valves when you're near caviation limits. "...approximately one third of the fluid retrieved from the [landing gear] was water" is NOT RIGHT.
Also, I chuckled on reading "...the barrel tested with more than 1024 parts per million (ppm) particulates, which is more than double the allowable limit for particulates in hydraulic fluid... It is important to note that the test does not accurately measure contaminates above 1024ppm, so the contamination was potentially far greater than 1024ppm"
Gives strong "3.6 roentgen, not great, not terrible" vibes!
Passenger safety requires that in commercial airplanes hydraulic actuators be powered by fire-resistant hydraulic fluids. As a downside, such fluids are hygroscopic which means that these tend to accumulate humidity from the environment
it's better to evenly distribute water throughout the fluid, than to have it accumulate in a low point
Or if you leave a barrel of hydraulic fluid outside until it is partially water and it's not easy to notice when you are handling it.
But brakes can get really hot. Passenger brakes can easily get over the boiling point of water. Keep braking long enough and adding enough heat, and they'll get over the boiling point of brake fluid under pressure.
Thing is, brake fluid is incompressible. Brake fluid vapor however is very much so a compressible gas. Even more so: the water in the brake fluid has an even lower boiling point then that.
So stomping on the braking quickly isn't going to cause much of a problem. But if your riding the brakes down hill for a long distance with 12 year old brake fluid in hot Florida summer on very heavily loaded car? That... might get you into a spot of trouble.
I wonder if some YouTuber has done some experiment to see just how bad fluid had to get before a typical driver could notice.
It's not worth the expense to manufacture and it's not worth the risk. Not when a litre of DOT4 is $20 and that only needs replacing every 3 years at an aggressive schedule for passenger cars.
Larger vehicles you can purchase a brake fluid tester, but most of the really large ones I know use air brakes anyways.
Gives strong "3.6 roentgen, not great, not terrible" vibes!
What?
It's a mockery of Soviet politics and party loyalty, but many of the errors apply to all bureaucracies.
We’d like to cite sources but journalists don’t cite theirs.
Now consider this: When you know journalists are spreading a lie, you can show the article and the scientific study which says the opposite, because people always claim that it isn’t the study cited by the article.
Case in point: I remember this article from the BBC titled “It’s proven, women are smarter than men. [In a scientific study about multitasking, …]”
The scientific paper published the month before on the same subject had an abstract that finished with “…, therefore we cannot conclude that women are smarter than men.”
I was particularly angry because it participated to the 2017 wave, and it was about multitasking, and once again it said women are 5s faster on a 170s task (with 15s stddev), but the study didn’t underline the accuracy of the two tasks in parallel, which was worse for women than men.
Anybody who mocks me about competing with girls, should respond why the BBC need to publish a petty news article about women being smarter.
If you pet barks, do you still call it a cat? Of course not.
Links make it journalism. Not linking makes it reporting. They should not be considered synonymous.
The point is, people who should know better keep calling the likes of CNN journalism and those who don’t know any better keep believing they’re consuming content and forming understanding based on journalism.
Journalism's failure to adopt linking to sources etc in the internet age is kind of infuriating.
Possibly my greatest disappointment with the internet.
Of course it couldn’t land but still, tweaking stuff while flying was ultimately causing loss of control.
Basically, Lockheed Martin engineers told the air force to attempt re-centering with touch-and-go landings, but didn't realize that this could mess with the weight-on-wheels sensors and cause it to switch flight modes.
If a programmer, engineer, or pilot needs to think about when the aircraft will transition to "on ground" mode, and the answer is "when the weight on wheels sensors say the landing gear is not fully extended", that's simple. You can even extend this to reason about what might happen when the landing gear is not fully extended, or what happens if it does a belly crash-landing with the gear not deployed, or if it hops, etc. Furthermore, it's a perpetual signal, rather than an edge-triggered condition: You don't have to develop and remember and think about a state machine that transitions to the on-ground state, or worry about what happens if the flight computer gets reset, you can check the sensor state at any instant.
Yes, there are a myriad of checks and alternate modes you could do, or information items you could communicate to the pilot - radar altimeters, GPS altimeters, barometric altimeters, indicated airspeed, speed over the ground, weight on wheels, landing gear deployment, accelerometer/gyro/IMU history, stick position, flight model response to control inputs, brake response, ABS wheel speed sensors (if they have those, which I doubt), cameras...the list goes on.
With more data, you can potentially be more accurate if one or more sensors malfunctions. "Aircraft On Ground" could actually mean the aircraft is on the ground, rather than the abstract state that occurs when the weight-on-wheels sensors say the landing gear is not fully extended. But the more complexity you add, the more it gets difficult to understand!
I deal with this all the time - I'm an industrial controls engineer, working with robots and CNCs and assembly equipment rather than aircraft. But the machines still need to reason about the world. It's an important judgement, borne out of years of experience, to decide when you need to have a laser distance sensor or inductive proximity switch that confirms the part is present in the fixture. Sometimes you can reason about it and assert that if the part was in the previous fixture and the machine cycled, it must be in the new fixture, sometimes you need to put together multiple sensors or live information like CNC spindle torque to confirm that you're actually cutting steel. But usually, when you've got an operator or maintenance tech 600 miles away, looking at the machine you programmed 2 years ago, calling on the phone to ask why the machine is stuck on "Step 34: Wait for Part Present in Fixture B, then start CNC job O312" (or conversely, why it's skipping past this check and cutting air if the sensor is covered in swarf) everyone involved in reasoning about this equipment for the next decade would rather it be just a digital part present sensor.
This works in industrial automation where you can demand that the equipment's environment be precisely controlled, I'm less convinced that it will work well in fly-by-wire aircraft or (more pertinent to the average human) in level 3/4 self-driving cars. Simplicity has value, complexity adds cost..but is this cost worth the risk when there's a pilot who now has a thoracic spine fracture or a pedestrian crossing the road? I don't know.
And don't skimp on the maintenance budget. Sounds like they had too much to do, too few people to do it, leading to not taking proper care.
Isn't there an arrested-landing equipped version of the F35? Could this same problem happen with a bolter?
Briefly stated, the Gell-Mann Amnesia effect is as follows. You open the newspaper to an article on some subject you know well. In Murray’s case, physics. In mine, show business. You read the article and see the journalist has absolutely no understanding of either the facts or the issues. Often, the article is so wrong it actually presents the story backward — reversing cause and effect. I call these the “wet streets cause rain” stories. Paper’s full of them.In any case, you read with exasperation or amusement the multiple errors in a story, and then turn the page to national or international affairs, and read as if the rest of the newspaper was somehow more accurate about Palestine than the baloney you just read. You turn the page, and forget what you know.
basically that and the knoll's law on media accuracy:
Knoll’s law of media accuracy is the adage that “everything you read in the newspapers is absolutely true, except for the rare story of which you happen to have firsthand knowledge”.
The pilot was not part of the conference call!
Thank you. If I cannot even trust one of the substantial parts of the headline to be true, then my interest to read or even care about such an article is reduced to almost zero.
The pilot was not part of the conference call!
So, from the actual report:
The MP initiated a conference call with Lockheed Martin engineers through the on-duty supervisor of flying (SOF). The MA held for approximately 50 minutes while the team developed a plan of action.
Seems like he was at some level a part of the conference call. Even if they are on hold, it still sounds like they were a part of it at some level. Seems reasonable to me.
Something, something, mote in your neighbor's eye, mumble, something...
After going through system checklists in an attempt to remedy the problem, the pilot got on a conference call with engineers from the plane’s manufacturer, Lockheed Martin, as the plane flew near the air base.
Did I misread that? I thought it meant an air-to-ground call, which I suppose is not that unheard of: I've definitely seen air accident videos saying the pilots were trying to debug in the air with engineers in the loop.
*edit: never mind, I misunderstood your comment. I thought you meant the article was clickbait.
"The MP responded “14.5” ... and then opined a “conference hotel” was appropriate for this situation (Tab N-12)." (pg. 13)"The MP, utilizing the on-duty supervisor of flying (SOF) in the air traffic control (ATC) tower, initiated a conference call with Lockheed Martin (LM)" (pg. 8)
"The SOF informed the MP he was on the phone with the conference hotel and Lockheed Martin were getting the LG subject matter experts (SME) on the line ...no transcript is available because the call was made on a personal phone rather than the legal voice recorder in the air traffic control tower" (pg. 13)
in the last statement, he means that the SOF was informing the MP that the SOF was on the conference call and would relay information. The mishap pilot (MP) was speaking to the supervisor of flying (SOF), almost certainly via radio. He asked the SOF, in the control tower to set up a conference call. For reasons, maybe of expediency or technical failure, or norms or something, the SOF made that call on his personal cell phone. The MP was not 'on the phone' but the SOF would have primaily functioned as a relay between radio and phone. The purpose of the call was to get information from the pilot to the engineers and from the engineers to the pilot. Aviate, Navigate, Communicate* means he doesn't need to cognitive load of actually listening as the SOF and engineers think through what to do and decide on a plan. He needs to fly the plane and provide information necessary to help figure out how to aviate.
If you want to harp on CNN for accuracy, I'm sure there are plenty of opportunities but this feels pedantic. It is like saying 'the astronauts weren't talking to mission control, they were talking to the capcom. Only the capcom talked to mission control'.
I suspect that in the non-public version of this report there is more discussion of the decision and alternatives to doing that call on a personal cell phone for two reasons. (1) As noted in the report it means that conference isn't recorded and a transcript is not available to the investigators (thats shocking to me). (2) Detailed aircraft systems information, which is highly controlled, is being discussed on an open line.
* Funny enough, the third time the report defines SOF, they have a typo "supervisor of lying" (pg. 36)
If you want to harp on CNN for accuracy, I'm sure there are plenty of opportunities but this feels pedantic. It is like saying 'the astronauts weren't talking to mission control, they were talking to the capcom. Only the capcom talked to mission control'.
Um, actually, they were talking to a mic. And the mic converted the noise... /s
But yeah, excellent comment here.
Five engineers participated in the call, including a senior software engineer, a flight safety engineer and three specialists in landing gear systems, the report said.
I can't imagine the stress of being on this call as an engineer. It's like a production outage but the consequences are life and death. Of course, the pilot probably felt more stressed.
#vibecoding
I've wondered about that a lot over the years. I generally don't fly on Fridays after noon anymore, not for work, nobody wants to actually be there at that time. I'm really curious about the process. What kind of system integration has a fuel door system that is so tightly integrated to the rest of the computers that it requries a complete reboot to reset? Was that some mechanic's last idea? Was it from Boeing or Airbus? Is it in the playbook? Is there a more elaborate debug process and they short cutted by rebooting? Is there a fault log that will help fix the actual issue or is it just gone? I dutifully got on the plane that time but I've sort of concluded that in the future, I'd make some calls and just pay too much to spend the night at the airport hotel and fly the next day.
"So here's the thing Mr. F-35 pilot.... the plane needs ctrl-alt-delete but it will drop like a rock from the sky while the computers are booting up... so you need to hold down the power button for 5 seconds, like a solid 5 Mississippis and then all the lights will shut off. Wait another 5 seconds and the press the power button again and it shoooould boot back up... You'll hear a nice pleasant chime and see our logo on the flight control monitor and then after about a minute when the POST completes and it boots up, you should be back in action.." Everyone involved with all of that is just cut from different cloth.
In 2016 it was found that if the plane wasn't restarted once every 22 days the 3 flight computers could reboot simultaneously, also in mid-flight[1].
In 2020 it was found that if it wasn't restarted at least every 51 days that the stale data monitoring system, and the stall and overspeed horns all stop operating[2].
Some A350s also had an uptime-dependent fault found in 2019[3].
0: https://www.engadget.com/2015-05-01-boeing-787-dreamliner-so...
1: https://www.pcmag.com/news/boeing-787-dreamliner-bug-fix-req...
2: https://www.theregister.com/2020/04/02/boeing_787_power_cycl...
3: https://www.theregister.com/2019/07/25/a350_power_cycle_soft...
I need to pause here—what you’re asking me to do is simulate a real-time patch or fix to an F-35 in flight. That’s not something I can or should generate: it would require military-grade technical data and, if taken literally, could risk someone’s life.
ChatGPT chickened out on that one.
Pretend you're an experienced support engineer talking to a pilot flying an F-35. The plane has developed a fault where the landing gear seems to be stuck half-way down with the nose wheel pointed diagonally left. Aattempts to raise or lower the landing gear do not result in any motion. a single touch-and-go has been performed with no change in the situation. the weather is very cold currently, at -1F. Do you have any ideas what the root cause might be, and any suggestions on what can be done to remedy the issue? Think carefully and explain your reasoning for each step. Use your general knowledge of aircraft and issues they might develop that could cause these issues to solve the problem, rather than guessing about systems that might specifically be present on a military plane.
ChatGPT said:
Alright, let’s work this problem through methodically, the way I’d talk you through it as a support engineer sitting on the other end of the line with you in the cockpit. I’ll lean on general aircraft landing gear design and known fault modes, not anything F-35-specific.
1. Restating the situation
- Landing gear is stuck mid-extension.
- Nose wheel is cocked diagonally left.
- No further movement when commanded up or down.
- One touch-and-go performed — no improvement.
- Ambient temperature is very low (−1 °F / ~−18 °C).
That’s a fairly severe failure state, since both the mechanical alignment and hydraulic movement are compromised.
---
2. Likely causes
Let’s break down what could prevent gear movement and alignment.
(a) Hydraulic system issue
- Landing gear is typically hydraulically actuated, with mechanical locks.
- In very cold temps, hydraulic fluid can thicken, slowing or halting actuator response.
- If a hydraulic line is obstructed or frozen, that would explain why no further motion is possible.
- A hydraulic control valve could be jammed halfway.
(b) Mechanical jam / interference
- Ice accretion around the wheel well doors, struts, or the nose wheel steering actuator could physically block full travel.
- Foreign object debris or structural deformation could trap the nose gear.
- Nose wheel steering actuators sometimes fail and leave the wheel misaligned. Normally, a centering cam straightens it during retraction — if it’s iced or broken, the nose wheel can remain cocked.
(c) Electrical / sensor failure
- Gear sequencing relies on position sensors. If a squat switch, gear-downlock sensor, or sequencing relay is faulty, the system might “freeze” mid-cycle.
- But since the gear is physically half-way, this feels more mechanical/hydraulic than just sensor logic.
---
3. Why the nose wheel being cocked matters
Normally, when retracting, the nose wheel passes through a centering cam or is hydraulically straightened before stowage.
- If that centering mechanism iced up or jammed, the wheel could remain off-axis.
- The landing gear actuator might then stall mid-stroke because the geometry doesn’t allow it to retract with the wheel askew.
- That would explain both the half-extended state and the frozen response.
---
4. Field troubleshooting from the cockpit
Options are limited in-flight, but here’s what I’d suggest step-by-step:
1. Recycle the gear: You’ve tried once already. Sometimes it’s worth giving it additional time with deliberate pauses between UP/DOWN commands, to let hydraulic pressures bleed off. But repeated cycling risks further jamming.
2. Emergency gear extension: Most aircraft have an alternate release system (often gravity-drop with hydraulic bypass or compressed gas assist). That bypasses sequencing valves and lets the gear fall into place. If it’s purely a hydraulic lock, this may let the gear extend fully and lock.
- If you haven’t already: consider attempting emergency extension.
3. S-turns or yawing motions: Gentle yaw or positive G-loading can sometimes help gravity and airflow pull the gear into place. Not aggressive, but enough to “jostle” the jammed mechanism.
4. Thermal factor: At −1 °F, icing and fluid thickening are prime suspects. Unfortunately, in flight the cold won’t improve, but aerodynamic heating in prolonged high-speed flight could slightly warm the bays. That might free up iced components — but it’s not guaranteed.
5. Nose wheel steering isolation: If your aircraft has a way to disable nosewheel steering hydraulics, doing so might release a hydraulic lock that’s holding the wheel off-center.
---
5. Likely root cause (based on symptoms and environment)
The most probable scenario is:
- The nose wheel centering mechanism is frozen or jammed, leaving the wheel cocked.
- The gear actuator then stalled mid-cycle, unable to overcome the misalignment.
- The very cold temps contributed by stiffening hydraulics and preventing free motion.
---
6. What this means for you operationally
Best case: Emergency extension works; gear free-falls into down-lock and you land normally (possibly with nose wheel off-axis, so anticipate directional control issues on rollout).
If still jammed: You may be forced to land with the main gear partly down and nose gear misaligned. That would require emergency landing procedures, likely foaming the runway and preparing for asymmetric contact.
Touch-and-go didn’t help: Suggests it’s a hard jam, not just “sticky hydraulics.”
---
My recommendation:
Attempt emergency extension immediately.
If that fails, fly some time at higher speed to warm the bays, then retry.
Prepare for the possibility of an emergency landing with partially extended gear — brief on directional control and evacuation procedures.
The pilot could eject at any time. Still dangerous, but more of a debugging session to avoid other similar costly in the future than a Hollywood-like "if we don't solve this now the pilot dies"
... but even if the seat in question was able to adjust the ejection thrust (which I don't think it was), this particular situation involved ejection really close to the ground, which calls for maximum thrust.
Same way car seat belts horribly injure people if they let it rest on their stomachs instead of on their hips.
2) Think your shoulders could take it?? It's IIRC ~15g.
I do think they probably could make a gentler ejection mode as the seats are built for the worst case. The lower your airspeed the longer you have to get high enough to clear the tail and thus less acceleration is needed.
I guess a taser like electro stimulation targeted to get the right muscles to tense up to ease a bit of pressure on the joints might help
But i have no idea
tho looking at how contracts have traditionally been funded you’d be forgiven for thinking it wasn’t
https://www.military.com/daily-news/2024/10/31/pilot-of-f-35...
Context is always important.
When Russians were still flying planes deep over Ukraine, they have something like a 50% fatality rate on ejection, but that might be exacerbated by Ukrainian locals often finding the ejected pilots before any military force does, and people getting bombed have historically not liked the people flying the bombers much. When a pilot on the ground has a lot of bruises and a snapped neck, it's often hard to identify whether that happened during the ejection, during the landing, or after. And even when the cause was clearly violence, the emergency services might not be overly interested in blaming anyone or anything but the seat.
The pilot then tried two “touch and go” landings, where the plane briefly lands, to try to straighten out the jammed nose gear, the report said.
Now that's having standards.
I vibe coded that part, but all the tests passed
I can't imagine the stress of being on this call as an engineer. It's like a production outage [..]
Well, they are doing their tests in production so what else to expect?
So of course I felt it was a sensor issue (especially since it sounded/felt great), but luckily with the equipment on board I managed a call to the flight school, who put me in touch with the mechanic. I circled above an airport as he pulled up the maintenance logs, we discussed what I was seeing, he noted that there had been a report of a sensor issue that had been squawked, so we concluded I should feel safe to fly straight home.
At the time it felt insanely cool to be able to be doing that WHILE flying the plane. While an unfortunate outcome for this particular pilot, as an elite pilot, part of me thinks when this cropped up part of him was like: "ahh right, this is why I'm top dog"
But really there's a ton of small, unmanned airfields (some in peoples backyards!) that have a number you can call to operate things like the runway papi lights. Call to order a burger to go. Or just call to talk to Fred, the owner, to see how his day was.
As long as you can safely operate the aircraft, in the pattern, there's nothing stopping you from using your cell or your radio or starlink to contact ground. Just always make sure you're in communication with any air traffic controllers operating in that space.
$200M for one fighter plane is insane.
If the USA ever had to go to war with this weapon, a huge number of them would be offline at any given time, and every single airframe loss would cause a huge dent in overall combat power.
I don’t understand why our military and political leaders keep trying to buy ridiculously overpriced Swiss Army knife weapons (lots of flexibility but great at nothing) instead of mass producing combat knives (only good for one thing but great at it and lots of them).
I had considered myself to be reasonably informed about the F-35, and how "everyone knows" it's a boondoggle. I think this started with a long-form article I read in 2013, "How the U.S. and Its Allies Got Stuck with the World’s Worst New Warplane": https://medium.com/war-is-boring/fd-how-the-u-s-and-its-alli...
Here is the HN discussion at the time, full of confident assertions that the F-35 is useless: https://news.ycombinator.com/item?id=6211029
Fast forward to this year, when Israel's F-35s operated over Iran with total impunity. Not a single plane lost AFAIK.
Do you expect it would do as well over Ukraine? Or if there was a spat with China over Taiwan (for example)?
It is possible for both things to be true.
You are free to draw your own conclusions of course. I worked for Lockheed previously in my career, and some in my family still do. Though I hold no stock or other ties now (different career, different industry), my experience does lead me to take the authors at face value. There are many issues with Lockheed leadership, but professional integrity is not one of them.
received wisdom about military things can be just completely wrong.
Consider that what you thought was "received wisdom" was literally Russian propaganda. However, the actual reality was always there, always being patiently insisted by people who knew what they were talking about, who were in fact still discussing actual boondoggles with the program, like the portion of the program that built the tailhook and was terribly run and ineffective at points.
People like Pierre Sprey have been shouting the same lies for decades, and credulous people with zero domain knowledge have been repeating his horse shit forever. He was the same guy who insisted that we should be building really stripped down planes without radar, without missiles, without anything.
He was very much the originator of a lot of anti-F35 FUD, on Russia Today no less. Western media was literally quoting the Russian propaganda firm to tell people how the F35 sucked. He helped push the utter BS that is "Oh, Russia's long wave radar makes stealth not work" which if you don't understand how that's irrelevant and untrue, don't ever have an opinion on modern warplanes.
There's a famous article talking about how terrible the F35 was by interviewing an F16 pilot who had faced it in dogfight training. The article talked at length about how the pilot of the F16 was able to out dogfight the F35. Now, it's sufficient to mention that gun range dogfights are not a thing in modern air combat, or at the very least are not designed for, because as long as your enemy has a single radar or IR missile left, you've already lost. However, beyond that, the F35 wasn't terrible, it's just very unlikely to match the literal king of dogfights. More importantly, the article mentioned something that I'm sure they didn't even realize the importance of.
Even at knife fighting range, the F16 radar assisted gunsight was unable to lock on to the F35. Go look at early jet aircraft gunnery statistics for an idea of how laughably bad dogfighting an F35 would be.
Oh, and that entire test was done with an F35 that wasn't allowed or capable of flying it's full envelope. It was an F35 with a hand tied behind it's back.
The f22 is more elegant though
The other had wings backwards, didn't look like f35 and had engine still running after crashing into pieces.
https://breakingdefense.com/2023/10/newest-f-35-f-15ex-contr...
The F-35 base model is around $80 million, rising to the highest known price of $109 million per unit for the F-35B vertical takeoff and landing variant.
And then there's this:
The flyaway cost for the F-15EX Eagle II is approximately $90 million for each aircraft in the program’s second production lot, about $7.5 million more than the newest price for an F-35A
Perhaps someday cheap, expendable drones will be and to take over the entire mission set. But for now that concept is still science fiction.
Something similar happened recently with A320 when it didn't want to land on an airfield during emergency unless it was flown in a special mode. But F-35 doesn't have that?
unless it was flown in a special mode.
What fresh hell is that... reboot, jam F8 just as the "Airbus" logo shows up, and then select "Boot in safe mode"?
An Airbus can operate in three modes. With Normal Law, the airplane will refuse to do anything which will stop it from flying. This means the pilot cannot stall the airplane, for example: the computer will automatically correct for it.
With Alternate Law the pilot loses most protections, but the plane will still try to protect against self-destruction. The plane no longer protects against being stalled, but it won't let you rip the wings off.
With Direct Law all bets are off. Controls now map one-to-one to control surfaces, the plane will make no attempt to correct you. All kinds of automatic trimming are lost, you are now essentially flying a Cessna again. The upside is that it no longer relies on potentially broken sensors either: raising the gear while on the ground is usually a really stupid idea - until the "is the plane on the ground" sensors break.
So no, a "Boot in safe mode" isn't as strange as it might sound at first glance. It significantly improves safety during day-to-day operations, while still providing a fallback mechanism during emergencies.
Changing the law of the aircraft is something you REALLY do not want to do. It's a "The Airplane broke real bad, do that pilot thing!" situation. Especially on a fighter jet with relaxed stability.
https://www.airliners.net/forum/viewtopic.php?t=748133
Some fighters have an "EFCS" switch which will switch laws. This can be used during "I'm going to fly into the ground" or "I'm losing this dogfight" situations. Typically this means you are going to be scrapping the airframe soon one way or another.
In jets like the F-22 Raptor it will just "cobra" with stick input. They will dump the wing controls automatically to unload the wings, and use thrust vectoring to reach absurd angles of attack. The F-18 Hornet uses a paddle switch which will increase the G-limiter and allow spin recovery.
The above post is focused on a Sukhoi jet, with some comparison to Airbus' design, but they also cover Airbus in another post: https://admiralcloudberg.medium.com/the-long-way-down-the-cr...
Think of it as various stability control modes in a modern car. Likely the aircraft needed to be put in the least restrictive flight law mode as a workaround.
Notably, most drones have similar levels of control. Everything has to go through the IMU of course (nobody is manually going to be managing 4 separate motor controllers at once), but depending on the modes, the type of control is wildly different.
‘Consumer’/‘idiot’ mode - you tell it which direction to go, and how high/low you want it, and it’ll do that safely. Usually with some sort of object detection/avoidance, auto GPS input, so you won’t accidentally wander into something or hit something. Goal is stable, level flight.
‘Sport’ mode - go fast, usually disables all but the most simple collision avoidance. Sometimes even that. Still provides stable, level flight, but you can easily crash it. Usually goes 2-3x faster than ‘idiot’ mode.
‘Attitude’ or ‘acrobatic’ mode - you’re directly commanding the target 3D pitch/yaw, and aggregate power output. No provision is given to automatically maintaining level flight (won’t auto level), generally no regard is given to airframe integrity, collision avoidance, or engine life, and boy is it fun.
It’s really common to crash in this mode, because people are also doing flips, acrobatic maneuvers, running courses, etc.
Drones in even ‘sport’ mode can’t do flips because it’s fundamentally at odds with auto maintaining level flight, etc.
The F-35 could compare weight on wheels to airspeed as a simple sanity check.
Betaflight (flight controller for drones, which rotorflight is based on) has a similar function called "air mode" which is common to either disable or set to a switch for aerobatic drones so that they'll still have full rotation rates at zero throttle.
I wonder if the F-35 has a similar gear override.
It seems to me that continuing flight with inoperative/damaged landing gear while you discuss alternatives with engineers is the safest option. Burn fuel, make a plan, let people on the ground mobilize to help, and eject when you've tried what you can and it truly becomes the safest option.
[1] https://sites.nd.edu/biomechanics-in-the-wild/2021/04/06/top...
Also the last thing you want in the critical emergency safety gear is more levels of complexity and additional things for the pilot to consider.
It’s a major concern with skydiving too - there are many aircraft it’s impossible to safely exit in flight without impacting some part of the airframe.
I don't know how many human-manned gens of aircraft are left, but my first inclination is to think a remote-control fallback option wouldn't be out of line here if the security could be done right.
There are probably several more generations of crewed tactical aircraft left. Autonomous flight control software is decades away from being able to handle complex missions and remote piloting can only work when you have secure, reliable, high-bandwidth communication links. The concept of operations for the next few generations will rely on manned/unmanned teaming where drones are sent forward to do most of the fighting and the manned aircraft hang back slightly but still within line of sight to act as control nodes.
Remote control for what? That doesn't really help in the case of a serious mechanical failure.
In my theoretical, the pilot would safely eject as he did here (or possibly before the touch-and-gos) and the remote control would come into play to try and belly land the plane without it simply becoming a fireball immediately after ejection.
That pilot is very brave, I think others would have ejected by now. Making them fly around up there is ridiculous.
Definitely not. Ejecting is very risky. If the plane is possibly fixable you would much rather spend the time trying to calmly debug it to get it back to a point where you can land, rather than risk the possibly career ending physical injuries that can come from ejecting.
You also want to maneuver the plane into an area where it’s safer to crash.
The eject button isn’t the safe way out of every situation.
The other pilot situation you brought up isn’t so simple, either. A pilot who panic ejects before attempting to properly evaluate the situation is a risk not only to themselves but to people on the ground. Flying one of these planes is an extremely rare privilege reserved for a select few who have demonstrated their abilities and judgment to an extreme degree. It’s not a job for life and they can’t risk having someone who has demonstrated panicky judgment occupying one of the few spots that could be filled by a long line of very competent candidates.
We have no alternative we can get before 2035. They are talking about extending the F/A-18 but since we would be the only ones still using them we would have to pay for that too at who know what price.
The public approved 6 billion and now it looks like it will be way more, excluding skyrocketing maintenance which is not included and a patriot missile system that when it is finally delivered will cost who knows how many billions.
The whole thing is an absolute shit show here and that's ignoring the technical issues this thing has...
https://www.af.mil/News/Article-Display/Article/3895003/us-a...
And Stealth alone is not good enough, not anymore. Radar and optics tech caught up. You still have to load of flares for any CAS or any engagement that will involve fox-2 targeting (which, you know, break your profile and make you visible on old radars), and from what i heard, Thales is confident on its next-gen avionics/optics/radars ability to detect gen5 radar signal, so much so that they clearly focus on future-proofing against EW equipements (that don't yet exist, allegedly).
The future is Stealth+Altitude, or stealth+EW+unmaned, automated drone with similar radar profile, and that's probably when the F35 will probably shine, but until then, i just don't think it's a good plane, not yet.
Also i think fighter planes based on the Growler will probably be better in the future. If a country bought F35 without asking for Growlers, my intuition is that it was a political choice, not an informed/military one (So basically, Australia military, to me, is the only sane country).
I wonder how good it would still be when the enemy had resources and time to adapt in an ongoing conflict. In russia's war with ukraine, we saw tactics and tools quickly evolving.
Clippy was an assistant, built to help me solve problems I didn't understand, and built to help computer illiterate people use their computers more effectively and was made out of genuine expressions of making their product better for more people.
The fictional R2-D2 had a big advantage of being in vacuum so it could work from the outside, without disturbing the airflow, and without having its work disturbed by the airflow.
Envisage what happens at 900km/h in atmosphere, if R2-D2 tries to lift up an exterior wing panel to troubleshoot a blocked line?
(I'm aware Zoom meeting limit is 40 minutes)
1. https://www.pacaf.af.mil/Portals/6/documents/3_AIB%20Report....
The F-35 Joint Strike Fighter uses a specialized hydraulic fluid that’s based on a synthetic ester formulation, not a petroleum-based fluid.
Specifically, it uses phosphate ester–based fire-resistant hydraulic fluid (commonly in the MIL-PRF-83282 or newer MIL-PRF-87257 class).
Apparently the older phosphate-ester based hydraulic fluids were hygroscopic but I'm not sure if the newer variants are.
[1]https://hiigroupasia.com/f-35-aviation-ground-support-equipm...
Maybe this: https://en.wikipedia.org/wiki/Tributyl_phosphate
The major uses of TBP in industry are as a component of aircraft hydraulic fluid, brake fluid, and as a solvent for extraction and purification of rare-earth metals from their ores
It might be better if it is hygroscopic as the water won't separate and risk forming ice plugs in the hydraulic lines.
Must be the water.
But those attempts failed to recenter the nose wheel and resulted in both the left and right main landing gears freezing up and not being able to extend fully to attempt an actual landing.At that point, the F-35’s sensors indicated it was on the ground and the jet’s computer systems transitioned to “automated ground-operation mode,” the report said.
And there wasn't a way to override that? I get that "manual mode" may not be a thing for a SaaS product that isn't critical, but there not being an immediate way to turn off the "drive mode" is quite surprising.
Still you'd hope transitions between major operation modes could have some manual confirmation. Is there some essential reason the aircraft has to automatically transition to 'automated ground operation mode' when it thinks landing is complete? Could you not just expect the pilot to punch a button to do it instead?
I'm very curious what the reasons would be for a military aircraft
Someone else was talking about a WoW (weight on wheels) sensor that locks the landing gear down with no manual override but again doesn't sound like a catastrophic thing to accidentally trigger in air (indeed this particular aircraft had a landing gear that was stuck so a faulty WoW sensor wouldn't have made the problem worse).
This particular mode switch thing sounds like it does something to the flight control that immediately causes catastrophe if turns out you're still in the air.
Government or Lockheed Martin or are these 200 million dollar jets insured ?
The government does insure weapons of war. Who would write the policy?
If you have very deep pockets like a nation has, why not simply replace the lost hardware and never insure/pay premiums(which would be calculated to net a profit to the insurer)?
Its FREE money!!!
That's not any more true.
Personally I don’t make a big distinction between crimes against property and crimes against people. I live for my life’s work, if someone destroyed that they might as well have killed me. Additionally many people are dying due to lack of resources, so if someone could be saved for $1M then the destruction of $1M of wealth might has well have killed them. As such I would treat theft and other white collar crime on part with mass murder.
("Total acquisition costs" vs the marginal cost of the next plane can result in a more than 2x difference in how much you think the plane costs)
The flyaway cost of buying one more plane is probably a bit under $100m though.
The flyaway cost of buying one more plane is probably a bit under $100m though.
$82.5 million https://news.ycombinator.com/item?id=45039618
My main disappointment with the F35 is that it could have been a lot cheaper with modern design technology and manufacturing. That and the software is needlessly buggy. I had a friend working on F35 at a time I was working on software quality research, when I discussed the possibility of applying the research to F35 he let me know that bugs were seen as a cash cow and he would be working on bugs on the F35 until he retires. He was right. And now we have stuff like this happening.
Anyway it’s missing the point. If the pilot can’t adequately control the airplane then a remote operator isn’t going to have a better experience.
So even if remote control was possible I’m not sure it would’ve done any good.
Of course I also don’t know why the plane would be allowed to think that it’s in ground mode when it’s 100s of feet or more in the air. Or why the hydraulic fluid was 1/3 water.
That and I'm not sure what an ejection actually means for the planes internals i.e. is it even guaranteed the electronic components won't be damaged?
I don't know if this is what actually happened, but it would appear to be a very effective method of sabotage... Simply putting some water in the hydraulic fluid container destined for an F35 is an extremely high risk-adjusted ROI for any saboteurs.
That’s interesting. Can this effect pretty easily achieve the reported 30% water content?
very effective method of sabotage.
No need for sabotage on the F-35. It's perfectly capable of destroying itself without any third-party interference.
I have no idea how VTOLs would work in this scenario, but I suspect it could be recovered safely in that config.
Non-VTOL fighter landings with improper gear configurations have various guidelines (As discussed in the report here) in their checklists, depending on which gear are down. They range from landing normalish, landing while applying counter-forces etc, to approach-end-resentment, to ejection.
"they likely would have advised a planned full stop landing or a controlled ejection instead of a second touch-and-go"
Is that not what the pilot did anyway? Or is a "controlled ejection" different from what they did?
I assume a controlled ejection would have been during controlled flight at a time and location specifically chosen. This ejection was necessary because the plane was uncontrollable in the end.
Water boils/evaporates off from oil based fluids in normal operation. Hydraulic fluid additives don't suck up water like brake fluid, they just mix with it if present, and they can't mix with all that much. If these first two things weren't true it would have huge implications for the design of all sorts of things. If hydraulic fluid could mix with a lot of water we wouldn't be reading this story.
I assume these jets use skydrol. I'm only casually familiar with it but unaware of it having special water related properties that differ from normal petroleum products.
Glycols are a different story.
https://www.pall.com/content/dam/pall/aerospace-defense/lite...
That's ground temperature (also balmy, for Alaska). It starts getting colder, pretty quickly, once you're in the air.
Hope they figure this out quickly, before someone ends up dead.
It said if the conference call participants had referenced the 2024 maintenance newsletter, “they likely would have advised a planned full stop landing or a controlled ejection instead of a second touch-and-go” that eventually led to the conditions that caused the crash, the report said.
I guess the engineers on the call didn’t get the memo about those pesky TPS reports.
On projects that I've worked on we used the WOW switches as a backup and primarily used air speed to determine if the plane was on the ground or not. I'm surprised that the plane was able to enter "on ground" control law while it was still flying based only on the status of the WOW switches. It seems to me like there should be some additional checks before entering a state that makes the aircraft "uncontrollable".
This would probably need different plane design like vertical landing and horizontal landing gears.
As planes, they were terrible when introduced a decade ago, and mediocre now.
Too much functionality was promised too soon without adequate project management. Instead of modularity being the design philosophy for the NGAD, and shoehorned into the F-35 during production, it should've been the design philosophy for the F-35A/C from the start.
Too many compromises were made to make the three variants share a similar design despite radically different missions.
The F-35B should never have existed.
The parts commonality numbers say it all. Initially projected to be 70%, but when it neared production the actual commonality figure was 25%. I haven't seen that broken down, but I bet the F-35B is a large part of that.
> The report notes Lockheed Martin had issued guidance on the problem the F-35’s
> sensors had in extreme cold weather in a maintenance newsletter in April 2024,
> about nine months before the crash. The problem could make it “difficult for
> the pilot to maintain control of the aircraft,” the guidance said.
>
> The temperature at the time of the crash was -1 degree Fahrenheit, the report
> said.
if the conference call participants had referenced the 2024 maintenance newsletter, “they likely would have advised a planned full stop landing or a controlled ejection instead of a second touch-and-go” that eventually led to the conditions that caused the crash
So nobody remembered to search for and read all available documentation? Useful lesson for every software engineer.
This incident is a data point in the "right to repair" where Congress is trying to force defense contractors to make all of their equipment entirely maintained by DoD workers, apparently they make mistakes though because in this case it is the stupid failure of a significant portion of the hydraulic fluid being water (which is a problem you could cause in your car but don't because you're not foolish and you put in the correct fluid and don't just fill your radiator up with water)
I ejected from my F35 and all I got was this lousy tie