COLLOQUIUM
Department of Computer Science and Engineering
University of South Carolina

Prognostics and Health Management:
Models, Maintenance, and Maturation

John W. Sheppard

Department of Computer Science
Montana State University

Date: February 10, 2012
Time: 1430-1530 (2:30pm-3:30pm)
Place: Swearingen 1A03 (Faculty Lounge)

Abstract

Recently, the fields of condition based maintenance (CBM) and
prognostics & health management (PHM) have exploded onto the scene as
offering improved methods for providing efficient and effective
"just in time" maintenance of complex systems. The promise of being
able to track and possibly to predict future degraded states of a
systems have led to the institution of large-scale programs such as
CBM+ and prognostics for the F-35 aircraft. Recently, the US Navy,
through its Automatic Test System Framework Working Group has been
supporting the expansion of existing and emerging IEEE standards to
address requirements in PHM. It is in this context that my research is
centered. In this talk, I will provide an overview of ongoing research
being performed in Montana State's Numerical Intelligent Systems
Laboratory to apply a "systems view" to PHM. To manage the
complexity of information sources as well as the diversity of
backgrounds for stakeholders in this area, this research uses a
semantic perspective where we draw on formal semantic models of the
domain to define the tasks of system-level test, diagnosis, and
prognosis for system support and maintenance. I will present the work
on our development of data-driven models and model analysis techniques
for PHM as well as efforts to use semantic models to guide their
maturation.

Dr. John Sheppard was the inaugural RightNow Technologies
Distinguished Professor in Computer Science at Montana State
University and currently holds a position as an Associate
Professor. He is also an Adjunct Associate Professor in the Department
of Computer Science at Johns Hopkins University. He holds a BS in
computer science from Southern Methodist University as well as an MS
and PhD in computer science from Johns Hopkins. In 2007, he was
elected as an IEEE Fellow "for contributions to system-level diagnosis
and prognosis." Prior to joining Hopkins, he was a Fellow at ARINC
Incorporated in Annapolis, MD where he worked for almost 20
years. Dr. Sheppard performs research in Bayesian classification,
dynamic Bayesian networks, evolutionary methods, and reinforcement
learning. He is the director of MSU's Numerical Intelligent Systems
Laboratory with seven PhD students and three MS students. The lab is
engaged in funded research in the areas of machine learning and
ontology-guided data mining in system-level fault diagnosis,
prognosis, and model maturation. In addition, Dr. Sheppard is active
in IEEE Standards activities. Currently, he serves as a member of the
IEEE Computer Society Standards Activities Board and is the Computer
Society liaison to IEEE Standards Coordinating Committee 20 on Test
and Diagnosis for Electronic Systems. He is also the co-chair of the
Diagnostic and Maintenance Control Subcommittee of SCC20 and has
served as an official US delegate to the International
Electrotechnical Commission's Technical Committee 93 on Design
Automation.