Center for Predictive Maintenance Activities
The Center for Predictive Maintenance combines comprehensive engineering fundamentals and research with a multi-faceted process to support the continued success of various industrial maintenance programs. The Center has developed a three step methodology for creating an effective maintenance program for any industry looking to better their current matinenance routine. The first step is to assess current practices and to create a strategy that yields maximum reliability for minimum cost. The next step can be as thorough as resources will allow implementing the items in the "Wheel of Predictive Maintenance". All of these items work independently of one another but when combined together will result in the best possible maintenance strategy. The last step is to determine optimal maintenance intervals and train employees on the new procedures to maximize the return on investment.
Training and Education
The ultimate success of any maintenance program will depend on the training and education of all users involved and stakeholders – from maintainers to leadership. Improper and unnecessary maintenance actions can result in a waste of resources, time, and money. Training and education play a vital role in maintenance implementation and can be used to prevent improper maintenance actions. The Center for Predictive Maintenance has developed a demonstration framework and tool that can be used to educate and train users from maintainers to leadership on the maintenance process from fault to maintenance action. This demonstration tool will walk an audience through the maintenance process starting with the data collection of sensor and historical data. The data is then integrated and used to create predictive models. Finally, the data and results are displayed in unique dashboards that provide personnel with the information needed to make educated decisions on the condition and maintenance of their system.
The Center is also involved in providing short training courses on the different areas of maintenance. Previously, the Center hosted a two-week hands-on Health and Usage Monitoring System (HUMS) workshop. The attendees got to experience first-hand with the Apache's HUMS system doing everything from completing changeouts, to conducting test runs and data analysis.
Since 2007, the Center for Predictive Maintenance test facilities have accumulated invaluable testing experience via thousands of hours of component testing. The test stands were designed to facilitate a scientific understanding of aircraft component conditions as they relate to TAMMS-A inspections, vibration signals, health monitoring systems output, and other data. An important part of many maintenance programs is the component testing of faulted articles (components with damage) as it allows verification of existing condition indicators (CIs) with known faults and maintenance actions. Testing can also lead to improving existing CIs by determining optimal thresholds to maximize true positives and minimize false positives for identification of failure modes.
Testing data also plays an important role in helping with analysis for daignositic and prognostic algorithms. It is used to help support and validate information extracted from logistical and sensor data.
The Maintenance Steering Group 3 (MSG-3) is an internationally recognized maintenance program used to determine initial scheduled maintenance requirements. The main objective of MSG-3 is to provide an optimized Scheduled Maintenance Program (SMP). This SMP is built on a strong engineering basis with clear focus on predictive analytics and maintenance cornerstones. The Center is involved in MSG-3 research and Working Group discussions.