ResCon Technologies employs Machine Learning to create digital twins of complex dynamical systems. Our approach achieves stunning fidelity using minimum power and data, making it compatible with edge computing hardware. This enables model training directly on the edge in real-time without the need for a cloud connection or enormous datasets. Edge-hosted digital twins provide data analysis, adaptive control, and predictive health and status.
Ongoing - ResCon is seeking a Machine Learning Developer to help create models of complex systems. ML-based models will be deployed to embedded computing hardware to provide adaptive control, predict health and status, and furnish actionable insights to users.
Ongoing - ResCon is seeking an individual with a passion for aerospace that has a background in Guidance, Navigation & Control (GNC), ideally with experience in Machine Learning and/or Physics, to help us develop several software products for commercial and Government customers.
November 2023 - ResCon has completed a USAF Phase II STTR project focused on the modeling, optimization, and health prediction of a microturbine-powered hybrid powertrain. Along with partners Infinity Labs and Ohio University, ResCon used the project to develop the RAPPT system, capable of creating and evaluating a full Power, Propulsion, and Thermal system Digital Twin on edge hardware and displaying its ML-derived insights to an operator.
August 2023 - ResCon has completed a USAF Phase I STTR project focused on the real-time interpretation of SansEC sensor signals. SansEC sensors were developed by NASA and are ideal for remote sensing of multiple quantities of interest in structures, fabrics, and dynamic systems like microturbines. ResCon partnered with Sierra Turbines and Ohio University to develop the Reservoir-Augmented Control and Health (ReACH) system, a software suite that rapidly creates SansEC-based models using edge computing hardware.
Copyright © 2024 ResCon Technologies, LLC - All Rights Reserved.