Aircraft


Deep Learning for industrial Prognostics & Health Management (PHM)

#artificialintelligence

Implementation and Results Introduction Conclusion References Deep Auto-Encoders • 4xNvidia K40 GPUs with with 2880 cores and 12 GB device RAM each in Ubuntu OS workstation •Theano based toolchain for Deep Learning • Nvidia K40 with 12 GB device RAM - driving factor for large dataset inhalation, caching and computation - especially the pre-training stage for DBNs Email:{venugov, gierinmj, reddykk}@utrc.utc.com Deep Belief Nets Layer 1 Layer 2 Bottleneck layer Input layer W2 T Layer 1 Layer 2 RBM RBM RBM Recursive pre-training W1 T W3 T • Successful adoption of Deep Learning methodologies to UTC applications in aerospace and building systems as shown in the timeline. Offers customized support agreements to help operators achieve optimal aircraft utilization. Products range from single actuators to complete flight control systems for the fixed wing, rotorcraft and missile segments as well as fly-by-wire cockpit controls, cabin equipment, trimmable horizontal stabilizer actuators and ...


Reliable Perching Makes Fixed-Wing UAVs Much More Useful

IEEE Spectrum Robotics Channel

Dino Mehanovic, John Bass, Thomas Courteau, David Rancourt, and Alexis Lussier Desbiens from the University of Sherbrooke realized that perching with a fixed-wing aircraft doesn't need to involve a stall to achieve that vertical and ultra low-speed approach, as long as you can maintain control over the aircraft. We are thinking about various failure causes (unsuitable states during the approach, smooth surface for the microspines) and failure detection timing (before touchdown, at touchdown and after touchdown). You also have to consider numerous factors that are sometime hard to quantify: efficiency of gears, reuse of some components between flight and climbing, transition time, propeller size, operating away from the design point, battery size, etc. Autonomous Thrust-Assisted Perching of a Fixed-Wing UAV on Vertical Surfaces, by Dino Mehanovic, John Bass, Thomas Courteau, David Rancourt, and Alexis Lussier Desbiens from the University of Sherbrooke in Canada, was presented at the 2017 Living Machines Conference at Stanford, where it won a Best Paper award.


Facebook reveals map showing where EVERY human on the planet lives

#artificialintelligence

'We then combined our results with existing census counts and created a population data set with 5-meter resolution for 20 countries. The revolutionary craft has completed its second test flight as Facebook works on its plan to use to beam the internet to people in remote areas with no mobile network coverage. New'Flip-flop' design makes quantum computers more affordable'Fortunately, we have developed other technologies like Aquila that will connect people as well. New'Flip-flop' design makes quantum computers more affordable Facebook added hundreds of sensors to the aircraft to understand how Aquila's shape responds to flight in real-time for the flight, including hundreds of strain gauges and three-axis inertial measurement units (IMUs.)


Facebook map shows where EVERY human on the planet lives

Daily Mail

Shocking dashcam video of cop saying'we only shoot black people' 'Our data showed the best way to connect cities is an internet in the sky,' Lewis told the conference, according to CNBC. The revolutionary craft has completed its second test flight as Facebook works on its plan to use to beam the internet to people in remote areas with no mobile network coverage. Shocking dashcam video of cop saying'we only shoot black people' 'Fortunately, we have developed other technologies like Aquila that will connect people as well. Shocking dashcam video of cop saying'we only shoot black people' Facebook added hundreds of sensors to the aircraft to understand how Aquila's shape responds to flight in real-time for the flight, including hundreds of strain gauges and three-axis inertial measurement units (IMUs.)


Reliable Perching Makes Fixed-Wing UAVs Much More Useful

IEEE Spectrum Robotics Channel

Dino Mehanovic, John Bass, Thomas Courteau, David Rancourt, and Alexis Lussier Desbiens from the University of Sherbrooke realized that perching with a fixed-wing aircraft doesn't need to involve a stall to achieve that vertical and ultra low-speed approach, as long as you can maintain control over the aircraft. We are thinking about various failure causes (unsuitable states during the approach, smooth surface for the microspines) and failure detection timing (before touchdown, at touchdown and after touchdown). You also have to consider numerous factors that are sometime hard to quantify: efficiency of gears, reuse of some components between flight and climbing, transition time, propeller size, operating away from the design point, battery size, etc. Autonomous Thrust-Assisted Perching of a Fixed-Wing UAV on Vertical Surfaces, by Dino Mehanovic, John Bass, Thomas Courteau, David Rancourt, and Alexis Lussier Desbiens from the University of Sherbrooke in Canada, was presented at the 2017 Living Machines Conference at Stanford, where it won a Best Paper award.


Machine Learning Model Tracks U.S. Spy Planes

#artificialintelligence

Marshals Service along with military aircraft and surveillance flights operated by military contractors. It turned out the sorties over the Bay Area and southern California supported of U.S. Special Operations Command training missions. The machine-learning exercise also turned up a surprising number of local and state police aerial surveillance operations in Arizona, Florida, southern California and Ohio, the web site reported. It also spotted testing of special operations aircraft based in Ohio but detected flying over other parts of the U.S.


This plane pattern is so meta it hurts

Mashable

If you have to test fly an aircraft for 18 hours, with no passengers and no destination, you might as well get a little creative. While testing their newest 787 Dreamliner engines, pilots for aircraft manufacturer Boeing did just that. Boeing's jet flew a total of 9,905 miles across 22 states, on a flight path that drew a near perfect outline of, what else: a Boeing 787. From wingtip to wingtip, the outline spanned 1,500 miles from Michigan's Upper Peninsula all the way to the southernmost tip of Texas, making the image roughly 40,000 times larger than the jet which drew it.


Florida startup boldly sets sights on moon

The Japan Times

WASHINGTON – The Florida startup Moon Express is setting its sights high: ambitiously shooting to become the first private company to launch a small, unmanned craft to the moon before the year's out. A big success could pave the way for scheduled flights to deliver scientific and exploration equipment, to exploit lunar soil resources and commercial potential. Moon Express's relatively small lunar vessel, dubbed MX1-E, measures just 3 feet (0.91 meters) wide by 4.5 feet high. In addition to the first flight with MX1-E, a second is programmed to the lunar south pole, rich in water ice, to establish a robotic research station there.


The Blackbird set for a hypersonic overhaul

Daily Mail

Lockheed Martin has revealed its secretive Skunk Works unit is beginning to build the first flight demonstrator of a radical hypersonic update of the long-retired Mach 3 SR-71 Blackbird spy plane. Lockheed Martin posted an artist's impression of the craft to its website, with the caption'The Skunk Works hypersonic design – an aircraft developed to execute Intelligence, Surveillance and Reconnaissance and strike missions at speeds up to Mach 6.' The plane will also have a'warm structure' that will heat up during flight Lockheed Martin posted an artist's impression of the craft to its website, with the caption'The Skunk Works hypersonic design – an aircraft developed to execute Intelligence, Surveillance and Reconnaissance and strike missions at speeds up to Mach 6.' NASA is backing plans to return to supersonic flight, with its Quiet Supersonic Transport (QueSST) low-boom flight demonstrator aims to produce a much lower'boom' than other supersonic aircraft, and NASA is hoping to see the first flight tests take place in 2021 The XS-1 program envisions a fully reusable unmanned vehicle, roughly the size of a business jet, which would take off vertically like a rocket and fly to hypersonic speeds.


facebook-internet-drone-test-flight

TIME

Facebook plans to develop a fleet of drone s powered by sunlight that will fly for months at a time, communicating with each other through lasers and extending internet connectivity to the ground below. The company called the first test, in June 2016, a success after it flew above the Arizona desert for 1 hour and 36 minutes, three times longer than planned. The second test occurred on May 22, Martin Luis Gomez, Facebook's director of aeronautical platforms, said in a blog post. The aircraft flew for an hour and 46 minutes before landing near Yuma, Arizona, with only "a few minor, easily-repairable dings," he said.