Associate professor Pete Manolios and graduate student Vasilis Papavasileiou of the College of Computer and Information Science have designed a constraint-based algorithm capable of assembling the safety-critical systems in the Boeing 787 Dreamliner jet airplane in less than 10 minutes.
The project—backed by a five-year, $1.5 million grant from the National Aeronautics and Space Administration and a three-year, $478,000 contract from The Boeing Company—dovetails with Northeastern’s focus on use-inspired research that solves global challenges in health, security, and sustainability.
The beauty of the algorithm lies in its ability to rapidly solve difficult real-time communication problems arising from the interaction of safety-critical components, such as black boxes, navigation sensors, collision-detection algorithms, and control systems.
“Our system is quicker and more cost-effective, but it also opens up a whole new realm of possibilities in terms of building optimal and efficient systems that properly utilize resources,” Manolios explained. “One major problem with building a system manually is that you cannot deeply analyze it to foresee the long-term consequences of your decisions.”
Manolios showcased the algorithm in Utah at the 23rd International Conference on Computer Aided Verification. Auto industry representatives at the conference expressed interest in using the mathematical tools to solve communication problems within cars, whose navigation and control systems mirror those of airplanes.
The long-term goal of the project, Manolios noted, is to commercialize the algorithm for use in the production of smart grids, secure networks, and other land, sea, and air vehicles.
“This can be used in every industry where you need to assemble something,” said John Chilenski, an associate technical fellow for Boeing Commercial Airplanes. “We’ve also used it for solving wiring allocation problems in the Dreamliner but I could even see it being used in nuclear chemistry to design new materials.”