Most new vehicles are studded with hundreds of sensors that collect raw performance data. While beneficial, such information can only be interpreted by the manufacturer or dealer and is usually only read after the car breaks down. Now researchers at Rochester Institute of Technology (RIT) and Lockheed Martin, a security company in Bethesda, MD, have developed a monitoring system that can better assess the health of a vehicle and can alert drivers to any potential problems.
The system uses a network of embedded smart sensors that are strategically located near automotive components that are prone to problems. The information is sent wirelessly to a central command center, where it is automatically analyzed by software. The monitoring system is similar to OnStar, an in-vehicle security, communications, and diagnostics system built by GM. But Nabil Nasr, assistant provost and director of the Center for Integrated Manufacturing at RIT, says that the system goes “far beyond” anything commercially available by predicting “future health or failures.”
The project is part of a $150 million contract between Lockheed Martin and the U.S. Marine Corp, which is equipping up to 12,000 military vehicles with the new technology. The system can assess the health of military vehicles before they are sent on missions so that commanders can know if a vehicle is up to the task. “It could save money and lives, and extend the lifetime of equipment,” says Nasr.
The technology has also been tested in a public-transit bus at the Rochester Genesee Regional (RGR) Transportation Authority for the past 18 months. Eight months ago, a spinoff company called LIBAN formed to develop the technology for commercial fleet vehicles.
The system uses standard sensors–such as temperature, vibration, and electronic sensors, as well as customized smart sensors–to monitor a vehicle. The sensors are placed near different components on the vehicle, such as the transmission, alternator, and drivetrain. “Most systems on the market today are just reporting fault codes coming out of the engine-control module. We are looking at data from individual components to get better details … and to predict future conditions,” says David Chauncey, CEO of LIBAN.
The data from the sensors is processed by an onboard computer system that analyzes the information. That data is sent at regular intervals to a control center via a cellular network, satellite, or private data network, depending on the customer. “Every vehicle is an intelligent, potential source of information, and we have the technology to make the data useful; we just need to develop communication protocols and standards so we can build the infrastructure to share information, beyond just the manufacturers and dealers,” says Kirk Steudle, director of the Michigan Department of Transportation (MDOT), which just announced a partnership with Michigan International Speedway to create an open testing environment for cross-brand vehicle communication.
The “heart of the system” is the data-monitoring software, says Nasr. The RIT researchers have created sophisticated programs for mining, trending, and analyzing the data from the sensors. “The algorithms are extremely valuable because they help us build a model of predictive and condition-based maintenance, so we can predict failures before they occur, and we can make determinations about service based on the actual conditions of the equipment,” says Randy Weaver, advanced-technology-systems program manager at RGR. The fare box on a bus, for example, is a key piece of hardware that the system monitors. “It’s the number-one reason we change a bus off,” says Weaver. If the box becomes jammed, transit personnel cannot accept fares from magnetic-pass holders (smart cards), so it is imperative that transit authorities know in advance the condition of the box.
“The [technology] is critical because our primary service is to keep buses on the road for the community, so if we can prevent a road breakdown during service hours, then the technology pays for itself,” says Weaver. RGR plans to integrate the technology into its fleets in the next six months.
Steve Underwood, director for the Connected Vehicle Proving Center at the Center for Automotive Research, in Ann Arbor, MI, says that the technology is really important, especially for reducing costs, and that there is a lot that can be done in addition to measuring the performance of a vehicle. Sensors can be used for incident detection, as well as for identifying traffic patterns and pavement conditions.
While the technology is currently being placed in military light-armored vehicles, LIBAN hopes to also use it in commercial vehicles, such as trucks owned by the U.S. Department of Defense, private-fleet operators, freight haulers, and other public-transit systems.
The big new idea for making self-driving cars that can go anywhere
The mainstream approach to driverless cars is slow and difficult. These startups think going all-in on AI will get there faster.
Inside Charm Industrial’s big bet on corn stalks for carbon removal
The startup used plant matter and bio-oil to sequester thousands of tons of carbon. The question now is how reliable, scalable, and economical this approach will prove.
The dark secret behind those cute AI-generated animal images
Google Brain has revealed its own image-making AI, called Imagen. But don't expect to see anything that isn't wholesome.
The hype around DeepMind’s new AI model misses what’s actually cool about it
Some worry that the chatter about these tools is doing the whole field a disservice.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.