Into the Dataverse: Turning Maintenance Actions into Structured Data
An important DoD priority is to use AI to improve maintenance activities. However, AI depends on the quality of data, so the DoD must first be able to capture data on maintenance activities that is complete, structured, and readily accessible.
DoD maintenance faces growing challenges that threaten the strategic advantage the United States Military has long held in both combat and humanitarian missions.
These challenges include:
- More is being demanded of aging equipment
- The complexity of maintenance on new, advanced platforms with more sensors and onboard diagnostic equipment is increasing
- Outdated processes limit effectiveness of maintenance activities
The quality of maintenance activities has a serious impact on operations. Consider the following:
- 80% of industrial maintenance is reactive (i.e. something broke and now needs to be fixed)
- Nearly 50% of unscheduled down time is due to unanticipated equipment failure
- Only 4-7 out of 10 DoD aircraft are operationally ready, causing unacceptable shortfalls between mission requirements and aircraft availability
- The cost of DoD aviation maintenance was $44 billion in FY 2018
- The DoD collects petabytes of data daily that it is unable to effectively exploit to improve maintenance activities
While many modern systems have embedded sensors that capture data on system performance and operating conditions, we also need to be able to collect complete sets of structured data on maintenance activities. Having this data available for analysis using AI tools could lead to improved predictive maintenance capabilities, decreased reactive maintenance, better allocation of maintenance resources, and other effects that could, in turn, lead to improved safety, increased operational availability, and decreased maintenance budgets.
Develop an AI-enabling user interface that can intuitively capture both structured and non-structured maintenance data, and associated maintainer actions, in an efficient and user-friendly manner to produce more accurate maintenance logs.
There are two focus areas imbedded in this challenge:
Data Collection: How do you recognize, classify, and quantify maintainer action? How do you associate those actions with required maintenance data fields?
User Interface: What are the most intuitive and user-friendly interfaces? How can you minimize the burden on the technician?
Solutions can leverage a wide spectrum of Intelligent User Interfaces - from traditional User Interfaces; to more advanced Natural Language Processing; to other more advanced modalities such as Gesture recognition and Augmented Reality.
September 20-22, 2019
Questions About the Event
For more information, email email@example.com