Communications of the ACM
Virtual Engineer to Predict Machine Failure
"The traditional approach to machine maintenance is being blown out of the water by real time diagnostics," says David Brown, head of the University of Portsmouth's Institute of Industrial Research.
Credit: University of Portsmouth
University of Portsmouth scientists have created a system that uses artificial intelligence techniques to predict when machines need repairing. The virtual engineer system uses sensors to monitor vulnerable parts of a machine, such as the bearings, while predictive software analyzes performance, alerting technicians to problems.
"This new diagnostic system prevents potential mechanical failure by identifying the faulty or worn-out part before it causes a problem," says Portsmouth researcher David Brown. "During the process of monitoring the machine, the software literally learns more about how it works, which parts are becoming worn, and anything else that could potentially cause mechanical failure."
View a video of Dr. Brown discussing the virtual engineer.
Brown says the system will result in significant cost savings for companies because they will no longer need to keep a specialist engineer on call. "It's the first time this kind of technology has been used on this scale in the processing industry," Brown says. "The traditional approach to machine maintenance is being blown out of the water by real-time diagnostics."
From University of Portsmouth
View Full Article
Abstracts Copyright © 2010 Information Inc., Bethesda, Maryland, USA 
No entries found