Degrader analysis for diagnostic and predictive capabilities: A demonstration of progress in DoD CBM+ Initiatives

William Baker, Steven Nixon, Jeffrey Banks, Karl Reichard, Kaitlynn Castelle

Research output: Contribution to journalConference articlepeer-review

1 Scopus citations

Abstract

This paper presents a modified reliability centered maintenance (RCM) methodology developed by The Applied Research Laboratory at The Pennsylvania State University (ARL Penn State) to meet challenges in decreasing life cycle sustainment costs for critical Naval assets. The focus of this paper is on the requirements for the development of the on-board Prognostics and Health Management (PHM) system with a discussion on the implementation progress for two systems: the high pressure air compressor (HPAC), and the advanced carbon dioxide removal unit (ACRU). Recent Department of Defense (DoD) guidance calls for implementing Condition Based Maintenance (CBM) as an alternative to traditional reactive and preventative maintenance strategies that rely on regular and active participation from subject matter experts to evaluate the health condition of critical systems. The RCM based degrader analysis utilizes data from multiple sources to provide a path for selecting systems and components most likely to benefit from the implementation of diagnostic and predictive capabilities for monitoring and managing failure modes by determining various options of possible CBM system designs that provide the highest potential ROI. Sensor data collected by the PHM system can be used with machine learning applications to develop failure mode predictive algorithms with greatest benefit in terms of performance, sustainment costs, and increasing platform operational availability. The approach supports traditional maintenance strategy development by assessing the financial benefit of the PHM technology implementation with promising potential for many industrial and military complex adaptive system applications.

Original languageEnglish (US)
Pages (from-to)257-264
Number of pages8
JournalProcedia Computer Science
Volume168
DOIs
StatePublished - 2020
Event2020 Complex Adaptive Systems Conference, CAS 2019 - Malvern, United States
Duration: Nov 13 2019Nov 15 2019

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Fingerprint

Dive into the research topics of 'Degrader analysis for diagnostic and predictive capabilities: A demonstration of progress in DoD CBM+ Initiatives'. Together they form a unique fingerprint.

Cite this