Communications of the ACM
Scientist Creates AI Algorithm to Monitor Machinery Health
Researchers say a new algorithm greatly increases accuracy in diagnosing the health of complex mechanical systems.
Credit: Topher Simon Photography
University of Alabama in Huntsville (UAH) researchers have developed an artificial-intelligence algorithm they say greatly increases accuracy in diagnosing the health of complex mechanical systems.
In blind testing using data coming from highly unpredictable and real-life situations, the algorithm consistently achieves more than 90% accuracy.
"What we have done is to take an artificial-intelligence algorithm and 'teach' it the basic principles of physics that govern faults in a vibrating environment," says UAH researcher Rodrigo Teixeira.
The approach has provided the U.S. Army with a new way of producing actionable information from helicopter Health and Usage Monitoring Systems.
"When the particular component we are monitoring sees vibration signatures that no longer reflect the normal performance of a component, an alert is passed to the maintenance team," says Chris Sautter with UAH's Reliability and Failure Analysis Laboratory (RFAL). He notes the RFAL algorithm fits easily into the Condition Based Maintenance paradigm, which has been adopted across the U.S. Department of Defense and the commercial aviation sector.
"Having this capability and the ability to enhance the maintenance policy of large fleet operators has presented UAH and the Reliability Lab with a host of new clients for our research capabilities," Sautter says.
From University of Alabama Huntsville
View Full Article
Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA
No entries found