Controlling maintenance costs is a critical to commercial industry in order to secure and retain market share/competitive advantage. Reducing maintenance cost is also a critical mission for the Defense Department in today’s budget-constrained environment.
One of the most promising avenues for delivering enhanced maintenance performance is in the area of data analytics, specifically in using data collected by sensors on military assets to predict, and hence avoid, costly failures. Commercial industry has already taken dramatic step forwards in this field, leveraging a combination of embedded sensors, local storage and processing, and remote monitoring and diagnostics, to eliminate unplanned downtime, increase asset availability, and reduce maintenance cost. Given the similarity between the heavy equipment used by the military and some of their counterparts in heavy industry (aircraft engines, diesel engines, gas turbines, pumps, compressors, etc.) there is reason to believe that the military could derive significant value by leveraging COTS predictive analytics technologies.
In 2014, General Dynamics Mission Systems (GDMS) and IBM invested more than $1M internal R&D dollars in the application & demonstration of CBM & Predictive Analytics for NAVSEA LCS shipboard maintenance and operational support. The primary goals were to demonstrate that in both a planning yard and shipboard environment a predictive analytic maintenance solution were achievable. Uninterruptible Power Supplies were selected for the predictive analytic demonstration due to the high failure rate as well as the abundance of maintenance information and historical data. GDMS provided PMS 505 & 505R with a Decision Support Analytics brief that provided an overview of the results of the CBM+ IRAD demonstration and its approach to Predictive Maintenance and Analytics LCS Logistics support.
Based on feedback from PMS 505 leadership GDMS has proposed a pilot program on LCS 4 that builds upon the IRAD demonstration to more comprehensively and accurately demonstrate a CBM and Predictive Analytics/Health Monitoring (PAHM) implementation onboard LCS 4 in an extended, at sea environment with focus on the Sea Giraffe Radar, I/O devices, Servers and the Air Conditioning Plant.
The project team will produce a report of predicted equipment failures during at sea testing, review the predicted accuracy for PAHM system and ROI achieved (notional maintenance cost savings during the test period), and review the impact to Ao based on installation and reporting PAHM systems.
By focusing on the required analytic solutions to tap into the potential value of this CBM data in a timely manner, and enabling proactive CBM actions to be taken prior to failure, this project directly targets the issues that industry is facing in keeping pace with the mountain of collected data, and serves as a template process for addressing the challenges associated with supporting fielded assets.
Objectives achieved through this NCMS/CTMA initiative will allow “Y Company” to show how predictive analytic technologies can be used in conjunction with existing sensors and instrumentation to provide advanced warning of major failures. The result will be a better maintained, more cost effective and better fuel efficiency for mechanized assets; therefore, contributing to a more capable warfighter.