Engineering Researchers Seek Ways to Prevent Plane Accidents
The grants have led to the research and creation of a technology that would advise pilots of potential accident situations.
Sherry says accidents from “controlled flight” into terrain or into a stall are not caused by a part malfunction or pilot error, but by an interaction between the components of flight automation that is indiscernible by the pilot.
A typical airliner has more than 100 sensors that send data to approximately 36 computers on the aircraft. Those computers communicate with each other to decide how the plane should respond.
In rare circumstances, small sensor data differences can be misinterpreted, forcing a decision about which sensor is correct. That could lead the aircraft to take an inappropriate action.
“Technology has facilitated the development of increasingly complex automation. There are no natural checks that limit this complexity when complex components interact with other complex components.”
— Lance Sherry
Sherry and his team set out to prevent such accidents by studying pilot behavior in flight. After noticing how senior captains provide experience-based advice to first officers when passing off the controls, they wondered if technology could provide the same type of guidance in potential accident scenarios.
“Our objective is to be a constructive backseat driver,” Sherry says. “A human pilot may only accrue experience from 300 flights a year, but the machine learning algorithm can accrue knowledge from every flight flown by every pilot.”
The technology, called the “Paranoid Associate,” uses machine-learning algorithms to process massive amounts of flight and weather data about anomalies that occur during flights across the country that Sherry and his team collect. These data are then used to create advisories for pilots to prevent them from encountering potential accident scenarios.
The technology is still being developed in what is expected to be a three-year project.
Sherry believes it has the potential to be used on automated ships and cars.