New Tool Can Detect Problems In Flights
MIT researchers have developed a tool that spots glitches in a plane’s overall health and performance without knowing ahead of time what to look for.
The new technique uses a type of data mining that filters data into subsets, or clusters of flights that share common patterns.
Commercial airlines in the U.S. currently monitor black-box data on a voluntary basis, following guidelines laid out by the Federal Aviation Administration’s Flight Operations Quality Assurance (FOQA) program.
Airlines regularly monitor a “watch list” of 88 flight parameters throughout each flight, including the pitch of a plane at takeoff, the speed at takeoff and landing, and the time at which a pilot retracts a plane’s flaps.
A Boeing 787 is able to record 2,000 flight parameters continuously for up to 50 hours.
The team mapped flight parameters in terms of vectors for each flight, then plotted vectors from multiple flights in a multiple-dimension “hyperspace.”
Vectors with similar measurements clustered together represent “normal” flights, while the vectors outside the data clusters signaled flights with potential problems.
“The beauty of this is, you don´t have to know ahead of time what ℠normal´ is because the method finds what´s normal by looking at the cluster,” John Hansman, professor of aeronautics and astronautics and engineering systems at MIT, said in a press release.
The team compromised 365 flights of Boeing 777s, and each flight included measurements taken at one-second intervals, including aircraft position, speed, acceleration, winds, and environmental pressure and temperature.
The team mapped each flight at both takeoff and landing, finding several flights that stuck out from the normal cluster.
The team found one flight took off with significantly less power than most, indicating either an incorrect thrust setting by the crew or a potential power-system issue.
Another flight survey found that the pilot had difficulty rotating on takeoff.
Ashok Srivastava, project manager for the System-Wide Safety and Assurance Technologies Project at NASA, said the cluster approach may give inspectors early warning of underlying issues.
“To make sure that systems are safe in the future, and the airspace is safe, we have to uncover precursors of aviation safety accidents,” says Srivastava. “In my opinion, these [cluster-based] analyses allow us to do that.”
Hansman said he hopes to test the technique on a richer dataset in the near future.
“We´re in an era where we have very few accidents, which is a good thing,” Hansman said in a statement. “But if there are emerging safety problems, you don´t want to wait for an accident, you want to find it ahead of time.”
On the Net: