Browsing by Author "Gebraeel, Nagi"
Now showing 1 - 2 of 2
- Results Per Page
- Sort Options
Item A Development Framework for a Comprehensive Capstone which Demonstrates Human Interaction with Autonomous Habitat Technology(2024 International Conference on Environmnetal Systems, 2024-07-21) Sherman, Sage O.; Pischulti, Patrick K.; Mohanty, Ayush; Hwang, Min; Ivey, Daniela B.; Robinson, Stephen K.; Berges, Mario; Gebraeel, Nagi; Klaus, David; Anderson, Allison P.Future deep-space missions will require crews to operate more autonomously due to the increased distance from Earth, which results in communications delay and resupply scarcity. Specific flight phases (crewed or uncrewed) and time critical situations, where Earth-based support is impossible, highlight the critical need for the crew and habitat to operate independently from Earth. The Habitats Optimized for Missions of Exploration (HOME) Space Technology Research Institute (STRI) addresses some of the challenges by developing and advancing mission enabling habitat technologies. The HOME STRI encompasses researchers from seven universities that are spread across five research-thrusts, providing novel contributions in the area of vehicle functional design, self-awareness, human-autonomy-teaming, vehicle self-sufficiency, and digital twin technology. This paper presents the development framework of a capstone demonstration which aims to integrate several technologies needed for autonomous fault management mission operations. We present a system architecture that contains various HOME-developed technologies which include; machine learning and artificial intelligence, adaptive modes of autonomy, a decentralized system architecture, a digital twin integration concept, and subsystem fault interaction. The demonstrated mission scenario begins with an uncrewed deep space habitat, operating nominally, with a computational system with incorporated machine learning and artificial intelligence in-training to learn system inter-dependencies while uploading its current knowledge to a digital twin. As a new crew approaches, anomalous behavior in the EPS and the ECLSS subsystems is detected by the deep space habitat. The crew is alerted and provided with root cause analysis. Using this knowledge, the crew correspondingly safe the system remotely prior to docking. Upon arrival to the habitat, the root cause is manually fixed by crew, and the habitat returns to nominal operations. This capstone integrates twelve research projects, highlighting the complex and interconnected nature of detecting faults and how crews interact with habitats that have autonomous elements.Item A Diagnostics Model for Detecting Leak Severity in a Regenerable CO2 Removal System(51st International Conference on Environmental Systems, 7/10/2022) Eshima, Samuel; Nabity, James; Mohany, Ayush; Rozas, Heraldo; Gebraeel, NagiHuman spaceflight beyond Earth orbit will experience high latency in communication and data transmission requiring autonomous deep space habitats that can keep the crew alive when present and keep the habitat "alive" when not. To achieve this goal, the autonomous agent must be both self-aware and self-sufficient. A self-aware system able to perform advanced diagnostics and prognostics of possible failures will be crucial towards enabling autonomy. Keeping the crew alive will demand a robust Environmental Control and Life Support System (ECLSS), the health of which can be sensed in real-time (self-aware) and appropriate corrective action taken when something's wrong (self-sufficient). To investigate the feasibility for autonomous control of ECLSS, a case study utilized a machine learning-based diagnostics model for a leaky regenerable CO2 removal system. A zeolite 13X sorbent bed processed simulated cabin atmosphere flows laden with elevated levels of CO2. Experiments were conducted at nominal operating conditions as well as with faults to generate a diverse set of data for training the model. For this paper, a leak was introduced into the CO2 removal bed. We present the experimental data, describe model development for diagnostics, and then discuss its validation and performance. This paper will further pose a design framework for self-aware ECLSS that utilizes machine learning-based algorithms.