|
Research lab develops system that predicts
problems
Blackanthem.com, KIRTLAND AIR FORCE BASE, N.M., September 01, 2005
Intelligent computer software capable of predicting when systems are about
to break down or need special attention is expected to improve operations
and generate large cost savings.
The technology has already been used to improve the reliability of
high-power advanced chemical lasers, and nearby computer chip
manufacturers are expected to save millions of dollars a year by
installing the technology on just one portion of a production line.
"There are significant advantages to performing maintenance on high-value
equipment when needed instead of on a periodic basis," noted Victor Stone,
a computer engineer at the laboratory's Directed Energy Directorate. "The
equipment can be safely operated longer, which improves productivity and
saves money."
The technology, called Prognosis, uses advanced software to predict
conditions, circumstances and faults. It is being developed by Mr. Stone
and Dr. Mo Jamshidi, a professor at the nearby University of New Mexico
and director of the university's Autonomous Control Engineering Center.
Dr. Jamshidi is temporarily employed by the directorate under a special
arrangement.
While Prognosis can include diagnostic techniques and statistical
analysis, it also involves computer software tools that provide a level of
sophistication characterized as "intelligent." Included are a variety of
neural network systems, fuzzy logic, pattern recognition, data mining,
classical expert systems and hierarchical and hybrid systems. No one tool
works in every situation but the Air Force's Prognosis system can select
the most appropriate tool for a particular situation or use multiple
prediction tools that transcend traditional collecting and detecting
systems.
Thus far Mr. Stone and Dr. Jamshidi have been developing a test bed
system, working to improve the operation of chemical lasers at the
directorate. Through Dr. Jamshidi's university affiliation the two are
able to enlist several students to assist them in their work. In return,
the students are gaining experience with a state-of-the-art technology.
Mr. Stone and Dr. Jamshidi are also working with technicians at Intel Corp
in nearby Rio Rancho on a Cooperative Research and Development Agreement
that is expected to benefit the Air Force and Intel.
If a Prognosis process is installed on just one portion of Intel's
production line, Mr. Stone and Dr. Jamshidi believe the saving will be $7
million a year. Intel employees are currently providing Mr. Stone and Dr.
Jamshidi with some of the information they need to develop and implement a
system tailored to Intel's needs.
The Directed Energy Directorate benefits by validating Prognosis
techniques in the process of solving real problems.
"Prognosis goes beyond using instrumentation to collect information and
systematically keep track of a process" said Mr. Stone. "It also goes
beyond collecting and using information to identify the cause of a
phenomenon or detect failures and abnormal behavior. Those processes look
at things the way they are, not the way they will be, which is where
Prognosis steps in."
By knowing what will happen, operators can plan an orderly shutdown or can
continue operating in a safe, but degraded, mode.
In the near future, Mr. Stone's work in Prognosis will contribute
intelligent software to existing processes as the next generation in
efficiently operating and maintaining complicated, high-value systems.
By J. Rich Garcia
Air Force Research Laboratory Directed Energy Directorate Public Affairs
|
