ORCID Number

0009-0009-7686-5338

Date of Award

Spring 2026

Access Type

Thesis - Open Access

Degree Name

Master of Systems Engineering

Department

Electrical, Computer, Software, and Systems Engineering

Committee Chair

M. Ilhan Akbas

Committee Chair Email

akbasm@erau.edu

Committee Advisor

M. Ilhan Akbas

Committee Advisor Email

akbasm@erau.edu

First Committee Member

Radu F. Babiceanu

First Committee Member Email

radu.babiceanu@wmich.edu

Second Committee Member

Berker Pekoz

Second Committee Member Email

pekozb@erau.edu

College Dean

James W. Gregory

Abstract

Currently, there is no governing standard that addresses the safe integration of AI into computer-based control systems (CBCS) in human spaceflight. The computer-based control expectations of those safety-critical systems on the International Space Station (ISS) are captured in SSP 50038, Computer-Based Control System Safety Requirements, with one caveat: the standard was not designed with AI applications in mind. SSP 50038 does not cover the probabilistic behavior, opacity, and training-data dependency of modern AI/ML systems. The objectives of this work is to develop an AI taxonomy relevant to safety characteristics (determinism, transparency, data dependency, failure predictability), systematically map AI characteristics against SSP 50038, propose a requirements framework that defines a safe operating envelope for AI within CBCS, demonstrate the requirement application within Environmental Control and Life Support System (ECLSS) cases, and validate the framework through gap analysis against SSP 50038 and cross-domain approaches (EASA AI Roadmap, ISO 21448/SOTIF, and UL 4600). This thesis presents one of the first systems-engineering approaches to address AI in safety-critical systems for human spaceflight. The requirements framework illustrates conditional suitability and restrictions for each AI category. Lastly, the framework proves to extend and fill gaps in the space domain while being consistent with cross-domain standards.

Download

Share

COinS