Requirement Discovery Using Embedded Knowledge Graph with ChatGPT

Nipa Phojanamongkolkij; Braxton VanGundy; Ramana Polavarapu; Ian Levitt; Barclay Brown

NASA NTRS · 20230013353

Requirement Discovery Using Embedded Knowledge Graph with ChatGPT

Nipa Phojanamongkolkij·Braxton VanGundy·Ramana Polavarapu·Ian Levitt·Barclay Brown

Abstract

- NASA’s Air Traffic Management-Exploration (ATM-X) Urban Air Mobility (UAM) Airspace Subproject is conducting research that evolves UAM airspace towards a highly automated and operationally flexible system of the future. - (see https://www.nasa.gov/uam-overview/ for more information) - The complexity of UAM airspace, and its evolution through a series of transformative epochs, requires a planning tool to effectively organize, integrate, and communicate the research that will guide the evolution of UAM operations in the National Airspace System (NAS). - The planning tool, called the UAM airspace research roadmap (or just roadmap), is being developed as a new system engineering methodology leveraging model based system engineering (MBSE) and artificial intelligence capabilities. This presentation gives an overview of the Knowledge Graph and ChatGPT applications within this system engineering methodology and will describe how it is being used to meet the ATM-X UAM Airspace Subproject’s overarching research goals.

Explore related subjects

systems engineering requirement analysis air traffic management urban air mobility digital transformation artificial intelligence knowledge graph

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Nipa Phojanamongkolkij, Braxton VanGundy, Ramana Polavarapu, Ian Levitt, Barclay Brown. Requirement Discovery Using Embedded Knowledge Graph with ChatGPT. https://ntrs.nasa.gov/citations/20230013353

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related reports

NASA NTRS2025

Model-Based Engineering/Digital Engineering (MBE/DE) and Mission Assurance of Complex NASA Systems With Federated Modeling

Explore the source record for details and available documents.

systems engineering↗

NASA NTRS2023

Identifying and Documenting Expert Knowledge, A Practical Study of Design Patterns

Globalization, powered by digitization, is increasing technology growth and knowledge transfer rates to levels not seen in the previous 3500 years, obscuring absolute truth and accelerating rates of innovation and production. Competing,or remaining competitive, in this global marketplace requires a learning organization adopt a method of capture, retention, and reuse for demonstrated tacit knowledge to accelerate the development of increasingly complex systems of high quality at a reasonable cost. The architectural theory of Patterns and Pattern Language is a validated methodology for mining tacit domain knowledge from a proven system. This work applies architectural theory to a multi-year development experiment and captures exposed knowledgeas a design patternin a model based systems engineering tool, demonstrating applicability ofdigital engineering initiativesin thedescription and reuse of expert design knowledge.By creating and archiving model based expressions of expert knowledge,a learning organization canimprovepractical decision making and avoid uninformed concept phase decision making

systems engineering↗

NASA NTRS2015

Model-Based Systems Engineering in Concurrent Engineering Centers

Concurrent Engineering Centers (CECs) are specialized facilities with a goal of generating and maturing engineering designs by enabling rapid design iterations. This is accomplished by co-locating a team of experts (either physically or virtually) in a room with a focused design goal and a limited timeline of a week or less. The systems engineer uses a model of the system to capture the relevant interfaces and manage the overall architecture. A single model that integrates other design information and modeling allows the entire team to visualize the concurrent activity and identify conflicts more efficiently, potentially resulting in a systems model that will continue to be used throughout the project lifecycle. Performing systems engineering using such a system model is the definition of model-based systems engineering (MBSE); therefore, CECs evolving their approach to incorporate advances in MBSE are more successful in reducing time and cost needed to meet study goals. This paper surveys space mission CECs that are in the middle of this evolution, and the authors share their experiences in order to promote discussion within the community.

systems engineering↗