Data Model Fusion: Design, Experiments and Frameworks for Surface Platforms
Abstract
Designing the next generation of autonomous platforms requires resolving several fundamental research challenges if optimal platform s are to emerge. Based on an initial project started in partnership with industry, several areas of need have been identified. The a bility to have highly reliable machinery for long-duration missions and the ability to support system reconfiguration and platform-l evel system assessment with digital twins have both been highlighted as areas where fundamental research is necessary. The ability t o understand tradeoffs between different system designs and understand what drives design interdependency has also been identified a s areas where our fundamental understanding and practical algorithms must be improved. This grant focuses on addressing three challe nges in these areas:1. Improving our ability to design high-reliability machinery systems considering trades between component relia bility and system architecture,2. Growing digital twins from component-based approaches to integrative system models capable of reas oning with multiple input types and choosing between models of differing fidelity and robustness,3. Exploring novel design-stage ont ological representations of these systems to provide increased understanding of the interactions in system design ahead of full prod uct model development.These activities will be supported by developing a tabletop model of a high-reliability machinery system that will generate data to evaluate the approaches and algorithms developed during this project.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Sep 07, 2021
- Source ID
- N000142112795
Entities
People
- Matthew Collette
Organizations
- Board of Regents of the University of Michigan
- Office of Naval Research
- United States Navy