The current challenge is leveraging the terabytes of data generated by deployed,
monitored systems to provide actionable information for commanders, maintainers,
logisticians, and program managers. The benefits of a cloud-based application
performing data transactions, learning and predicting future states from current and
past states in real-time, and communicating anticipated states is an appropriate
solution to reduce latency and improve confidence in decisions. Decisions made from
deep learning and artificial intelligence (AI) application will improve mission
success and operational readiness, improving overall cost/effectiveness of any
program. These improvements will accelerate process improvements at the Depot Level
by filling the information gap between unit-level maintenance and depot-level
maintenance efforts for each inducted vehicle or aircraft.
automation to shorten the time associated with data ingestion and cleansing. Our
team offers a flexible ingestion framework leveraging direct upload, Java Script
Object Notation (JSON) code, or application programming interface (API) endpoints to
analyze, cleanse, and train machine learning (ML) models. The AI consumes multiple
data types, structured or unstructured, from any platform without interrupting
existing applications, adding hardware to platforms, or requiring complex
integration across multiple “silos”.
Systecon’s solution utilizes proprietary,
deep ML algorithms, created with the Defense Advanced Research Projects Agency, and
leverages Topological Data Analysis to automatically present actionable information
via a customized, user-friendly dashboard display. Views are designed to quickly
provide the user with critical decision-making information necessary to maintain
individual platforms and fleets on a day-to-day basis and through major maintenance
events at the Depot level.
The vehicle agnostic algorithms correlate state
variables such as kinematic data, system sensor data, external condition variables,
and digital behavioral data to infer a system’s current state and digital
maintenance information. Systecon’s AI optimizes both sensor-supported equipment and
legacy systems absent supporting sensors or the capability to move data off
platform. Systecon’s solution identifies the prevailing trends, enabling state
prediction at the system/component level. Our platform automates ongoing model
tuning, reducing the cost and risk of running ML models long-term, while
simultaneously improving their accuracy and performance.
The Systecon team
constructs model-based, serialized digital twins across a system’s lifecycle and
across logical/operational groupings of systems. This bi-directional data coupling
enables tactical, operational, and strategic decision support, detachable and
deployable logistics services, and configuration-based automated distribution of
digital technical and product data to enhance supply and logistics operations.