Aviation and Aerospace Safety Research

Open-Source Validation and Verification Framework for AI-Controlled Aerial Vehicles

PI M. Ilhan Akbas

The goal of this project is to develop a simulation framework to streamline the testing and validation of AI-controlled aerial vehicles. The Artificial Intelligence (AI) design and verification flow consists of the digital environment creation process, an open-source AI-controlled autopilot, access to multiple open-source simulators, symbolic test generation engine, example test scenarios, and native design-for-experiment layer for each of the major subsystem of an AI-controlled aerial vehicle.

Findings: The proof-of-concept demonstrated the viability of the system, with the low-fidelity simulation successfully flagging key scenarios for further testing, and the high-fidelity simulation providing accurate and realistic results for the flagged scenarios. By streamlining the testing process and focusing computational resources where they are most needed, this framework offers a robust solution for improving UAV safety and reliability in increasingly complex operational environments.

Scholarly Products: External grants being prepared: National Science Foundation (NSF) has a solicitation for open-source ecosystems called ``Pathways to Enable Open-Source Ecosystems (POSE)" that is compatible. Also, NSF’s Cyber Physical Systems (CPS) program. No grant applications submitted so far.

Categories: Faculty-Staff

3D Printing of Continuous Carbon Fiber Composites with Programmable Thermal Behaviors: A Proactive Safety Design for Advanced Thermal Management

PI Yizhou Jiang

CO-I Leitao Chen

CO-I Yanbing Chen

This study aimed to fabricate composite materials, i.e. continuous carbon fibers reinforced thermoset composites (CCFRTC), in a way that makes heat transfer predictable, enabling effective control measures. The ability to control thermal transfer through 3D-printing can lead to significant improvements in preventing thermal-related accidents.

Findings: Final report submitted 9/24. This study demonstrated the adaptability and precision of the team’s 3D printing method but also underscored its potential in advancing the field of thermosetting composite material manufacturing, paving the way for innovative applications, including fire suppression systems.

Scholarly products: Three external proposals were submitted, one $38k award was received from the Florida Space Research Program. Two journal articles were submitted, one has been accepted and one is under second round review. Two conference presentations have been accepted.

Zhuoyuan Yang, Evan Medora, Zefu Ren, Meng Cheng*, Sirish Namilae*, and Yizhou Jiang*. "Coaxial direct ink writing of ZnO functionalized continuous carbon fiber-reinforced thermosetting composites." Composites Science and Technology (Acceptance: 7/30/2024): Impact Factor: 8.3 DOI: https://doi.org/10.1016/j.compscitech.2024.110782
Zhuoyuan Yang, Kehao Tang, Wenjun Song, Zefu Ren, Yuxuan Wu, Daewon Kim, Sirish Namilae, Yifei Yuan*, Meng Cheng*, and Yizhou Jiang*. " Coaxial direct writing of ultrastrong supercapacitors with braided continuous carbon fiber based electrodes" Chemical Engineering Journal. Under journal’s 2nd round review. Impact Factor: 13.3 18
Conference papers
Myles Brussels, Theodore Bernold, Patrick McGuinness, Casey Troxler, Sandra Boetcher, Zhuoyuan Yang, Zefu Ren, Daewon Kim, Yanbing Chen, Yizhou Jiang, Leitao Chen. 3D Printing of Continuous Carbon Fiber Composites with Programmable Thermal Behaviors: A Proactive Safety Design for Advanced Thermal Management. 2025 AIAA SciTech.
Zefu Ren, Zhuoyuan Yang, Rishikesh Srinivasaraghavan Govindarajan, Nicholas Reed, Daewon Kim, Yizhou Jiang. Flame Retardancy of Additively Manufactured Continuous Carbon Fiber Reinforced PEKK Composites with Expandable Graphite Coating. 2025 AIAA SciTech.

Categories: Faculty-Staff

ERAU NASA In-Time Safety Management Data Development and Analysis Year One

PI Kristy Kiernan

CO-I Albert Boquet

CO-I Stephen Rice

CO-I Robert Waltz

CO-I Joel Samu

CO-I Lucas Epperson

CO-I Shashank Kumar

CO-I Lidiaruth Jones

CO-I Sierra Juliano

CO-I Joseph O'Brien

This project explores new data sources and analytical tools for extracting learning opportunities from all aviation operations.

This project explores new data sources and analytical tools for extracting learning opportunities from all aviation operations. To continue to learn from a system with very low mishap and incident rates, new data streams must be found that uncover strategies and practices that promote resilience. This project examines both existing mishap data, existing data collected from the NASA Human Contribution to Safety (HC2S) test bed, and data collected independently to identify realistic, actionable methods to support and encourage continuous learning, both at the operator level and the organizational level. The project will be divided into two tasks: Task 1 builds upon the work being done in the HC2S testbed by exploring the existing data and generating new data to address how resilient performance can be manifest at the level of the operator and also in the broader system; Task 2 examines NTSB accident dockets for evidence of resilient performance at the level of the operator and also in the broader system.

Categories: Faculty-Staff

Developing Aviation ASR and NLP Datasets and Tools

PI Jianhua Liu

CO-I Andrew Schneider

The goal is to create an ATC ASR dataset for open access. We have obtained 300 hours of audio data and processed 30 hours using the bootstrap approach: Using Whisper to provide the initial transcripts, Correcting the transcripts by hired transcriber team, reviewing the corrected transcripts.

Categories: Faculty-Staff

Robust Automatic Speech Recognition for Aviation Applications

PI Jianhua Liu

CO-I Andrew Schneider

The goal of this project is to develop speech recognition models that can be used in aviation contexts.

Scholarly products: Participating in NASA In-Time Safety Management grant extension. ASDA’s NSF proposal. Both investigators of this project are involved as senior personnel in the ASDA’s NSF proposal. JSOU proposal not funded. NASA ULI proposal that was not funded.

Categories: Faculty-Staff

Deep-Learning-Based Unobtrusive Estimation of Pilot Adverse Interactions and Loss of Energy State Awareness

PI Hever Moncayo

This project aimed at gaining more insight into the mechanisms of pilot SD and LESA occurrence, capturing their dynamic fingerprint, and developing on-board intelligent schemes capable of predicting and detecting these dangerous phenomena associated to pilot behaviors.

Findings: Final report submitted 9/24. Each of the mathematical models showed good capabilities of estimating each of the pilot parameters and represent a promising tool towards the characterization of pilot behavior using learning components. Continuation can be pursued by generalizing or extending the proposed results to other aircraft-pilot dynamics, possibly eVTOLs for AAM.

Student and Curriculum impact. The simulation and testing tools will be integrated as part of the experiential learning of the course AE623 Guidance, Navigation and Control that will be taught by the PI next Fall 2025. The proposed technique also allowed a master student in Aerospace Engineering to complement and enhance her thesis outcomes.

Scholarly products: NASA ULI submission, NSF Dynamics Control and Systems

Brutch, T. Schill, and H. Moncayo, Machine learning approach to estimation of human-pilot model parameters, in Guidance Navigation and Control Architectures for Autonomous Systems III, AIAA SciTech 2024 Forum, 2024-1200 (AIAA, Orlando, FL, 2024).
S. Brutch and H. Moncayo, Performance analysis of machine learning algorithms to humanpilot-model parameter estimation, in IS-30, Human - Automation Interaction, Accepted for presentation in AIAA SciTech 2025 Forum (AIAA, Orlando, FL, 2025).
S. Brutch, Rocio. Jado-Puente, and H. Moncayo, A physics-informed deep learning model for estimating human pilot behavior and mitigating adverse interactions, in Guidance Navigation and Control Architectures for Autonomous Systems III, AIAA SciTech 2024 Forum, 2024-1200

Categories: Faculty-Staff

Big Data Analytics for Injury Data

PI Dothang Truong

This project leverages big data analytics tools for the exploration and transformation of injury data for a major Part 121 carrier with the goal of predictive modeling. This project offers graduate students an opportunity to work with a substantial airline dataset under the supervision of a faculty member. The outcomes have the potential to lead to more extensive future projects in the realm of big data analytics. (This project is under strict NDA).

Categories: Faculty-Staff

Fabrication of Copper Lithium-ion Battery Case with Integrated Cooling Channels Using Binder Jetting Additive Manufacturing

PI Yue Zhou

CO-I Wenhao Zhang

CO-I Heer Patel

CO-I Henil Patel

CO-I Sirish Namilae

This project leveraged binder jetting processes to directly fabricate metallic battery cases integrated with various cooling channels, paving the way for the additive fabrication of metallic thermal management devices applied in the aerospace field.

Findings: Developed heat transfer model for the geometrical design of cooling channels, created files for experimental design and optimized printing & sintering settings, created scale-down prototypes for battery cases with integrated cooling channels.

Scholarly products: Abstract submitted to SciTech, preparing article for publication. Preparing grant application.

Categories: Faculty-Staff