Predicting Breakdowns

Continued from page 1

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.