Abstract Operations and support (O&S) expenses of the Department of Defense (DoD) weapon systems account for 65–80% of the total life cycle cost. One of the principal contributors to O&S cost is the airframe maintenance process. The US Air Force airframes are maintained using the Aircraft Structural Integrity Program (ASIP). ASIP's goal is to ensure the desired level of structural safety, durability, and supportability with the least possible economic burden throughout the aircraft design service life. ASIP uses a schedule-based maintenance approach by establishing predefined maintenance intervals for performing manual inspections. This approach requires vehicles to be removed from service at predetermined times regardless of their actual condition. In most cases, inspections performed during this process do not find any damage, and the airframe is returned to service until the next inspection interval. In December 2007, the DoD implemented the “Condition-Based Maintenance Plus” policy. As the name indicates, the DoD plans to move toward a process that services weapon systems based on their actual condition instead of the presumptive schedule-based approach. As a result of this policy, an increased emphasis has been placed on the development of advanced health management technologies, such as structural health monitoring (SHM). An essential element of condition based maintenance is improved decision making. This chapter presents a recently developed method for improved decision making, the cognitive architecture for state exploitation (CASE). CASE is demonstrated in a laboratory simulation of an SHM task. The simulation is followed by a comparison of availability, reliability, and costs that result from CASE and ASIP-guided decisions. Although the CASE guided decisions in the SHM application show great potential benefits, it is a new technology which must be validated before it can be used in practice. The chapter concludes with a discussion regarding methods for the validation of SHM systems when maintenance decisions are aided by a progressive decision framework such as CASE.
[1]
Hoon Sohn,et al.
A review of structural health monitoring literature 1996-2001
,
2002
.
[2]
Keith Worden,et al.
An introduction to structural health monitoring
,
2007,
Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.
[3]
Daniel L. Balageas.
Introduction to Structural Health Monitoring
,
2010
.
[4]
N. Draper,et al.
Applied Regression Analysis
,
1966
.
[5]
M. M. Derriso,et al.
Global workspace theory inspired architecture for autonomous structural health monitoring
,
2012,
2012 IEEE National Aerospace and Electronics Conference (NAECON).
[6]
Mark M. Derriso.
Machine Conscious Architecture for State Exploitation and Decision Making
,
2013
.
[7]
Mark M Derriso,et al.
The probability of detection for structural health monitoring systems: Repeated measures data
,
2015
.
[8]
Charles R. Farrar,et al.
Damage identification and health monitoring of structural and mechanical systems from changes in their vibration characteristics: A literature review
,
1996
.
[9]
Carlos E. S. Cesnik,et al.
Review of guided-wave structural health monitoring
,
2007
.
[10]
Jeong-Beom Ihn,et al.
Pitch-catch Active Sensing Methods in Structural Health Monitoring for Aircraft Structures
,
2008
.