Big Data Analytics
Big data analytics is the process of examining large and often multiple data sets to reveal trends, patterns, correlations, and other information that can be utilized to assist organizations in making more-informed business decisions. Big Data Analytics can be a very effective tool in support of materiel readiness, mission assurance, and sustainment cost reduction in the Department of Defense. This forum will consist of a series of presentations which will describe analytical capabilities and solution sets that assist DoD maintenance managers and leaders with making decisions on what to maintain, when to maintain, and what maintenance actions have the biggest potential impacts on equipment availability and efficiency.
JTEG Forum: Big Data Analytics
24 September 2019
- OSD – “MADW Update” – Eric Herzberg (LMI) 01 Big Data Analytics_JTEG_Intro (v2)
- NCMS – “Joint AI Center – Predictive Maintenance” – Phil Callihan, NCMS and Michael Gormley, TAMR 03 TAMR
- Army – Bradley / M88 Predictive Maintenance Methodology – How to apply to Army Equipment – Uptake – Jason Valcourt (Debbie to provide POC)
- NAVAIR – “Flight Line Readiness Analytics and How they impact Sustainment Activities” – Calvin Farmer
- NAVSEA – PEO Ship Data – look for indicators – are maintenance cycles lined up optimally, other efforts – Janice Bryant
- USAF – “AFMC Data Analytics” – Dan Adducchio
- DLA – Supply Data – John Luvera & Manny Ferreira
Event: On 24 September 2019, the Joint Technology Exchange Group (JTEG), in coordination with the National Center for Manufacturing Sciences (NCMS), hosted a virtual forum on “Big Data Analytics”.
Purpose: The purpose of this forum was to describe several big data analytical capabilities and solution sets that could assist DoD maintenance managers and leaders with making decisions on what to maintain, when to maintain, and what maintenance actions have the biggest potential impacts on equipment availability and efficiency.
Welcome: Ray Langlais (LMI), in support of OSD(MR), welcomed everyone to the forum, thanked the presenters and all the listeners for their attendance, discussed the importance of big data analytics in DoD sustainment, and then briefly previewed the agenda.
Administrative: This was an open forum. The presentations, along with questions and answers, were conducted through the Defense Collaboration Services (DCS) and Adobe Connect. A separate audio line was used. Approximately 62 participants from across DOD, industry, and academia joined in the forum.
Maintenance & Availability Data Warehouse (MADW) Update: Eric Hertzberg (LMI) described how the MADW process embeds authoritative data from top-down sources in bottom-up transaction records to make every transactional record accountable for all costs and all availability results. He listed the authoritative data sources, described several sample record displays and their data fields, and explained how MADW deploys a machine learning natural language processing algorithm to identify objects and actions associated with each maintenance transaction from freehand text fields. Additionally, he described a new supply diagnostic capability that will link maintenance to Supply (Linking non-availability to parts waiting (NMCS).
NAVAIR Dashboard: Calvin Farmer (NAVAIR) discussed how analysis across the Naval Aviation’s data pillars is conducted using several tools, processes, and teams. He then described the Naval Air Systems’ Aircraft Management Dashboard (AMDB), which is software that integrates near real-time data and reports provided by fleet maintainers and squadrons on the status of their aircraft. He displayed screenshots of the system to review the following: Enterprise Readiness Levels, Unit Level Dashboard, and the Buno (Military Aircraft Serial Number) Report.
AFMC Data Analytics: Dan Adducchio (AFMC) described data analytics approaches in forecasting, supply, maintenance, investment, and visualization. In the use of data analytics for maintenance and supply practices, he identified areas of data use, integration application, and efforts in place; characterized capabilities and gaps of data on hand; detailed SME support and coordinate between AFMC and MAJCOMs, and described the employment of industry tools and engineering practices to improve Weapons Systems status trends awareness of issues. HQ AFMC A4/10-EN is using engineering data analytics techniques to integrate data from several systems to ID trends and improvement areas for overall fleet health in areas of sustainment, maintainability, and reliability
Joint Artificial Intelligence Center (JAIC): Phil Callihan (NCMS) described the JAIC mission to understand the relationships between existing representative databases, which are very large, containing complex and potentially sensitive information, and to prepare the data environment for AI and Data analytic capabilities. He then described an H-60 Proof of Concept project that will create a data model applicable to both the commercial aviation industry and the DoD, validate the ontology application utility, and evaluate the potential value of AI and machine learning using ontology to optimize supply chains and lower overall costs.
Q&A – A Q&A occurred after each briefer finished their presentation. Questions and answers will be posted on the JTEG website with these minutes.
Closing Comments: Ray Langlais thanked the presenters for their contributions and all the work being done to support big data analytics efforts within DoD sustainment. He suggested continuing the information exchange beyond the forum and the importance of collaboration within the DoD maintenance community.
- Work to get the briefing slides cleared for “public release”, and then post them on the JTEG website at http://jteg.ncms.org/ .
Next JTEG Meeting: The next scheduled JTEG virtual forum is 29 October, 1:00 – 3:00 pm EST. The topic is “Cyber Security: Overcoming Challenges to Innovation”.
POC this action is Ray Langlais, email@example.com , (571) 633-8019
MADW: Eric Hertzberg (LMI)
Q1. What is the percentage of Army systems that are serviced by MADW?
A1. All army readiness supported systems are available in MADW. What we don’t have is trans actually executed data for commercially maintained systems, except Navy ships, because the commercial entities are not required to provide the details.
Q2. How does someone in the Military Services gain access to MADW?
A2. Anyone with a CAC card can send Eric Herzberg an email requesting access. The request is then vetted through OSD(Materiel Readiness) for approval.
NAVAIR Dashboard: Calvin Farmer (NAVAIR)
Q1. Is it built on a BI system?
A1. SQL with a Tableau server.
AFMC Data Analytics: Dan Adducchio (AFMC)
Joint Artificial Intelligence Center (JAIC): Phil Callihan (NCMS)
Q1. For Tamr to execute on project requirements, is the data sent outside or do you bring their tool in?
A1. We would prefer to bring the Tamr tool in. We are working through the details.
Q2. Does it rely on ontology or a human element?
A2. Both. The ontology is utilized and then subject matter experts are brought in to “tweak” and perform a sanity check.