Nov. 4, 1998 Contact: Staci West -- (509) 372-6313, firstname.lastname@example.org
RICHLAND, Wash. - Artificial intelligence could boost the U.S. Army’s battle against budget crunching as well as aid battlefield readiness by diagnosing engine problems in tanks before costly repairs are needed.
Researchers at the Department of Energy’s Pacific Northwest National Laboratory are developing TEDANN, or Turbine Engine Diagnostics Using Artificial Neural Networks, for the Army.
The technology uses diagnostic engineering, artificial neural networks and model-based decision algorithms to predict failures and abnormal operations in the M1 Abrams main battle tank’s turbine engine.
“This technology will extend the life of a tank and enhance readiness while reducing the cost of maintenance,” said Frank Greitzer, program manager for Pacific Northwest.
The Army is planning to field test TEDANN to determine if the technology will be applied across the entire M1 tank fleet.
Currently, sensors aboard a tank indicate only if the engine’s operations are in or out of tolerance - that is, if a problem does or doesn’t exist. But TEDANN monitors engine conditions continually and tracks potential deviations from normal operations. Through TEDANN’s predictive diagnostics, maintenance personnel could be alerted to problems as they develop, which would reduce expensive engine failures.
The Army also schedules periodic engine health checks on M1 tanks that require the engine to be removed from the hull. Using TEDANN, these checks would be performed automatically during normal operations. Mechanics would know if an engine needs maintenance before its scheduled service date or if the engine is in good health and doesn’t need servicing.
TEDANN uses data from 32 existing sensors on the gas turbine engine and 16 new sensors that have been added using a wiring harness. These sensors continually monitor engine performance and relay the information back to a computer processor for analysis.
That analysis is done using artificial neural networks, or ANNs. These networks process information much like a human brain - learning by example. For TEDANN, these neural networks are configured to model the behavior of normal engine performance and to recognize deviations.
A mechanic could access TEDANN’s analysis using a laptop computer. He could monitor the sensor data that has been collected (for example, engine temperatures, fuel levels, pressure, throttle and speed) and view diagnostic reports without having to remove the engine from the hull. Also, the tank’s driver could be alerted to critical engine problems with an onboard display.
Earlier prototypes of TEDANN have been tested since 1997 on Washington National Guard M1 tanks at the U.S. Army’s Yakima (Wash.) Training Center. The latest version of the TEDANN prototype was installed there on a National Guard tank in September 1998. Over the next year, TEDANN will be installed in seven other M1 tanks at selected Army bases and will collect engine data for use in training the ANNs.
“By using TEDANN, the Army could expect to extend the life of the MAbrams tank fleet, lengthen the time between costly overhauls by 25 percent and avoid hundreds of millions of dollars in maintenance costs over 30 years,” Greitzer said.
The U.S. Army Logistics Integration Agency and Department of Defense have funded development of TEDANN with about $2.3 million since 1993. Pacific Northwest is one of DOE’s nine multiprogram national laboratories and conducts research in the fields of environment, energy, health sciences and national security. Battelle, based in Columbus, Ohio, has operated Pacific Northwest for DOE since 1965.
Other social bookmarking and sharing tools:
The above story is reprinted from materials provided by Pacific Northwest National Laboratory.
Note: Materials may be edited for content and length. For further information, please contact the source cited above.
Note: If no author is given, the source is cited instead.