Here’s another “How HPC saves your worthless hide” type of story - our pals at InsideHPC publicized a collaboration between the Federal Aviation Administration and the Texas Advanced Computing Center (TACC) that should increase air safety for people riding on planes and for the people standing around underneath them. Briefly, …
Actually probably takes longer to run
They didn't make their code any faster at all. All they did was modify it to use more processors.
In fact its likely that the code takes longer to run (if taking all cores into account) due to all the message passing between threads.
Not the issue
It doesn't really matter that the code is probably less efficient. It is realtime sensitive, so what matters is getting it done quickly, not efficiently.
If a rugby team empties a keg
in a small fraction of the time that one player does it, would you not say that the keg was emptied "faster?" The whole point of parallel computing is to solve problems in less time using more processors.
Red Bull will be pleased
May be good news for Blanik L13 freaks, of which there are many.
With unmodified Blaniks grounded this lurk might get the Red Bull Blaniks pulling off more of their stunts and the rest of we low end glider pilots more rides.
Helicopters because I miss the black one that used to kept down the road.
doesn't make sense
From the article: "The invididual simulations aren’t long, but the FCC wanted to create an ensemble analysis that looks at a range of probable values for the critical variables in each situation. This can mean tens of thousands of runs that need to be completed rapidly in response to a detected failure in a flight system."
If it's many runs then they can be farmed & run in parallel, no explicit paralising needed. Trivial, I've done similar myself.
Too easy. I guess something's gone missing in the original article.
too much learning and not enough practical experience
With the best will in the world to our computer friends theres enough practical experience in the aviation industry over the past 100 yrs to be able to evaluate wether a part is going to fail in use or not.
If the pilot flies his aircraft outside the designed flight envelope then he has to accept that something might just break when he doesnt want it to.,
With the airbus 380, they built a rsj test rig to test one to destruction, just to prove that the theorising was in fact about right.
At the end of the day it has to be a practical test of the component that gets its ticket of airworthyness.
metal fatigue is not about over-stressing. It is accumulated stress changes, ie the changes that happen to metal when moved a little, often. The metal crystal structure can change, hence properties.
This is why airframes have a design life, say 2000 hours. The structure may never have been over-stressed or even heavily stressed, but has work hardened to the point the metal is brittle. It may then fail suddenly despite being under design stress.
Here lies the question that simulations and sensibly, ground aging tests check, how long will it really last ?
With minor modifications mechanical components can have their life doubled, cutting hourly cost significantly. Conversly, design faults, like the Comet 1 windows can show up before someone dies.
and its Friday; where is a Paris snippet or the BOFH ?
does the paper air plan have the required simulation ?
Ah, back in the day...
Real Aircraft builders use to build a big rig, mount a full airframe on it and shake it until it fell apart.
Well, that's what Hawkers did after the Comet fiasco in the early 1950's.
I clearly remember a Harrier being give this treatment at Kingston around 1975.
Now, they use massive computer to simulate it.
Do they have a setting for:-
Norwegian SAS Pilot landing in a heavy crosswind on a very short runway at night?
Those guys really used to plonk the plane down on the runway. No softly-softly please be careful of the undercarriage landings for them?
Ok, mines the one with the smell of goat on it from sharing a cabin from on an IL86 flying from Petraplovosk to Moscow!
"Norwegian SAS Pilot landing in a heavy crosswind on a very short runway at night?"
What about the Irish pilot landing on a very short runway, that is also incredibly wide?...
- Vid Hubble 'scope snaps 200,000-ton chunky crumble conundrum
- Updated + vids WHOA: Get a load of Asteroid DX110 JUST MISSING planet EARTH
- 10 years of Facebook Inside Facebook's engineering labs: Hardware heaven, HP hell – PICTURES
- Very fabric of space-time RIPPED apart in latest Hubble pic
- Massive new AIRSHIP to enter commercial service at British dirigible base