José Messias Magalhães Júnior

Pós-doutorado

Formação complementar

Idiomas

Áreas de atuação

Participação em eventos

Orientou

Produções bibliográficas

• MAGALHÃES JÚNIOR, JOSÉ M. ; HALILA, GUSTAVO L.O. ; VAMVOUDAKIS, KYRIAKOS G. . Data-driven controller and multi-gradient search algorithm for morphing airfoils in high Reynolds number flows. AEROSPACE SCIENCE AND TECHNOLOGY , v. 148, p. 109106, 2024.

• MAGALHÃES JÚNIOR, JOSÉ M. ; HALILA, GUSTAVO L.O. ; KIM, YOOBIN ; KHAMVILAI, THANAKORN ; VAMVOUDAKIS, KYRIAKOS G. . Intelligent data-driven aerodynamic analysis and optimization of morphing configurations. AEROSPACE SCIENCE AND TECHNOLOGY , v. 121, p. 107388, 2022.

• MAGALHÃES Jr, J. M. ; OLIVEIRA, A. V. M. . PODER DE MERCADO DOS AEROPORTOS: UM ESTUDO SOBRE OS INDICADORES DE AVALIAÇÃO. REVISTA DE ENGENHARIA E TECNOLOGIA , v. 5, p. 102-111, 2013.

• MAGALHÃES Jr, J. M. ; OLIVEIRA, A. V. M. . UM ESTUDO DO TRANSPORTE COLETIVO URBANO DE FORTALEZA - PREVISÃO DE DEMANDA PARA 2015. Revista de Engenharia e Tecnologia , v. 5, p. 44, 2013.

• SILVA FIGUEREDO, VINICIUS ; OLICHEVIS HALILA, GUSTAVO LUIZ ; KIYOSHI ARAKI, LUCIANO ; MAGALHAES, JOSE M. . Nonparallel, Nonlocall Flow Stability Analysis Through a Physics-Informed Data-Driven Approach. In: AIAA AVIATION FORUM AND ASCEND 2025, 2025, Las Vegas. AIAA AVIATION FORUM AND ASCEND 2025, 2025.

• MAGALHAES, JOSE M. ; ZHAI, LIJING ; FOTIADIS, FILIPPOS ; KANELLOPOULOS, ARIS ; VAMVOUDAKIS, KYRIAKOS G. ; HUGUES, JEROME . Real-Time and Experimental Reactive and Proactive Defense in a Multi-Agent Scenario. In: AIAA SCITECH 2024 Forum, 2024, Orlando. AIAA SCITECH 2024 Forum. Reston: American Institute of Aeronautics and Astronautics, 2024.

• TUKENMEZ, NEJAT ; FOTIADIS, FILIPPOS ; JÚNIOR, JOSÉ M. MAGALHÃES ; VAMVOUDAKIS, KYRIAKOS G. ; BOGOSYAN, SETA O. . Reward Drops in Learning-based Control with an Experimental Validation on Microdrones. In: 2024 IEEE 63rd Conference on Decision and Control (CDC), 2024, Milan. 2024 IEEE 63rd Conference on Decision and Control (CDC), 2024. p. 3819.

• FIGUEREDO, V. S. ; HALILA, GUSTAVO L.O. ; MAGALHÃES JÚNIOR, JOSÉ M. ; MENDONCA, M. T. . A Physics-Informed Data-Driven Approach for Boundary Layer Flows. In: AIAA AVIATION FORUM AND ASCEND 2024, 2024, Las Vegas. AIAA AVIATION FORUM AND ASCEND 2024, 2024.

• MAGALHAES, JOSE M. ; OLICHEVIS HALILA, GUSTAVO LUIZ ; VAMVOUDAKIS, KYRIAKOS G. . Data-Driven Controller and Multi-Gradient Search Algorithm for Morphing Configurations. In: AIAA SCITECH 2023 Forum, 2023, National Harbor. AIAA SCITECH 2023 Forum, 2024.

• JUNIOR, JOSE M. MAGALHAES ; KHAMVILAI, THANAKORN ; SUTTER, LOUIS ; FERON, ERIC . Test platform for autopilot system embedded in a model of multi-core architecture using X-Plane flight simulator. In: 2019 IEEE/AIAA 38th Digital Avionics Systems Conference (DASC), 2019, San Diego. 2019 IEEE/AIAA 38th Digital Avionics Systems Conference (DASC), 2019. p. 1.

• KHAMVILAI, THANAKORN ; SUTTER, LOUIS ; JUNIOR, JOSE M. MAGALHAES ; SYED, AQIB A. ; FERON, ERIC . Fault Assessment of Safety-Critical Applications on Reconfigurable Multi-Core Architecture. In: 2019 IEEE/AIAA 38th Digital Avionics Systems Conference (DASC), 2019, San Diego. 2019 IEEE/AIAA 38th Digital Avionics Systems Conference (DASC), 2019. p. 1.

• MAGALHAES, JOSE M. . Data-Driven Controller for Morphing Airfoil. 2022. (Apresentação de Trabalho/Seminário).

• MAGALHÃES Jr, J. M. ; MULLER, C. . A STUDY OF VEHICLE ROUTING PROBLEM, WITH TIME WINDOW, APPLIED TO A FRACTIONAL JET OWNERSHIP COMPANY. 2013. (Apresentação de Trabalho/Congresso).

Projetos de pesquisa

• 2024 - Atual

  A Physics-Informed data-Driven Approaches for Fluid Flow Simulations, Descrição: Physics-informed data-driven modeling of boundary layer flows represents an inexpensive and easy-to-automate technique to simulate wall-bounded flows. The resulting models are easy to operate and couple to other flow solvers. While standard neural networks are largely used as surrogates to computational fluid dynamics (CFD) simulations, the volume of data and required computational time to train such models are large, and the associated errors are not necessarily acceptable for a number of investigations. Physics-informed neural networks (PINNs) use the underlying flow physics, represented by partial differential equations, to accelerate the training process and enhance the modeling accuracy. In this paper, we present numericalresults that indicate the suitability of PINNs to recover flat plate boundary layer flows. The data is generated by running a boundary layer solver. The PINN is then employed to recover relevant boundary layer metrics, such as velocity profiles. Our results indicate that the PINN predictions better capture the boundary layer velocity profiles and thickness evolution when compared to computations made by standard neural networks.. , Situação: Em andamento; Natureza: Pesquisa. , Alunos envolvidos: Mestrado acadêmico: (1) . , Integrantes: José Messias Magalhães Júnior - Integrante / HALILA, GUSTAVO L.O. - Coordenador / Vinicius Silva Figueredo - Integrante.

• 2020 - 2025

  NASA ULI Secure and Safe Assured Autonomy (S2A2), Descrição: The goal of this ULI project is to develop new technologies and innovative operational concepts which will ensure safe, secure and robust integration of autonomous vehicles into Advanced Air Mobility-tailored transportation infrastructure. All this must be done while maintaining inter-operability with current civil air transportation systems and associated safety standards.The project is organized into four Technical Challenges (TCs) areas designed to provide unique UAM solutions and a transition roadmap for industry and government to utilize research product output.. , Situação: Concluído; Natureza: Pesquisa. , Integrantes: José Messias Magalhães Júnior - Integrante / VAMVOUDAKIS, KYRIAKOS G. - Coordenador.

• 2020 - Atual

  Simulação e otimização aerodinâmica de forma com apoio de machine learning, Descrição: Descrição: A combinação de machine learning, controle preditivo baseado em dados (em inglês data-enabled predictive control) e dinâmica dos fluidos computacional (CFD - Computational Fluid Dynamics) possibilita processos eficientes de análise e otimização de configurações aeronáuticas. Dentre as aplicações possíveis, considera-se a proposição de configurações morphing. Em linhas gerais, este projeto de pesquisa procura utilizar dados gerados em simulações de CFD de alta fidelidade para alimentar uma série de modelos de ordem reduzida e surrogate models. Estes modelos, capazes de fornecer resultados relevantes de forma eficiente, são empregados para realizar análise e otimização aerodinâmica. Surrogate models baseados em redes neurais estão sendo utilizados, e técnicas matemáticas de redução de ordem também são objeto de interesse dentro do escopo deste projeto. Processos livres de gradientes e baseados em gradientes são utilizados para realizar otimização aerodinâmica neste projeto. O controle preditivo baseado em dados é um algoritmo não-paramétrico orientado a dados que combina identificação (aprendizagem) e controle de sistemas dinâmicos. Este algoritmo não requer conhecimento explícito do sistema dinâmico, em vez disso, usa uma matriz de trajetórias contendo dados de entrada/saída coletados previamente para descrever o comportamento do sistema em análise. Este algoritmo, equivalente ao controle preditivo baseado em modelo (em inglês, model predictive control), usa dados históricos para prever o comportamento do sistema a uma dada trajetória de referência. Neste projeto, desenvolvemos um surrogate model baseado em redes neurais (do inglês, deep neural networks) para gerar, em tempo real, a matriz de trajetória para condição de voo e combinamos técnicas de regularização para permitir a aplicação deste algoritmo ao sistemanão-linear. , Situação: Em andamento; Natureza: Pesquisa. , Integrantes: José Messias Magalhães Júnior - Integrante / HALILA, GUSTAVO L.O. - Integrante / VAMVOUDAKIS, KYRIAKOS G. - Coordenador.

• 2019 - 2025

  SAS: INT: COLLAB: Aerodynamic Intelligent Morphing System (A-IMS) for Autonomous Smart Utility Truck Safety and Productivity in Severe Environments, Descrição: Unlike conventional approaches, the A-IMS will integrate model-free shape-morphing learning mechanisms with model-based interactive design to manage air-fluid flows, based on the road conditions, meteorology, speed limit, wind speed, and direction. This potentially transformative framework for A-IMS will: (1) bring new perspectives of learning to enhance the adaptability and intelligence in natural-engineering systems that leverage physical and information processes; (2) establish an integrated design framework for hazardous environments to achieve resilience, and productivity through integrated adaptation of morphological properties while also mitigating the effects of potentially adversarial learning agents that can exist in the cloud; (3) investigate the interactive physical components of the A-IMS, that will simultaneously operate in two different mediums of multi-phase fluids, and solids (i.e., the air/fluid and road).. , Situação: Concluído; Natureza: Pesquisa. , Alunos envolvidos: Mestrado acadêmico: (2) Doutorado: (2) . , Integrantes: José Messias Magalhães Júnior - Integrante / VAMVOUDAKIS, KYRIAKOS G. - Coordenador.

Projetos de desenvolvimento

• 2022 - Atual

  CPS: Small: An Integrated Reactive and Proactive Adversarial Learning for Cyber-Physical-Human Systems, Descrição: The gradual deployment of self-driving cars will inevitably lead to the emergence of a new important class of cyber-physical-human systems where autonomous vehicles interact with human-driven vehicles via on-board sensors or vehicle-to-vehicle communications. Reinforcement learning along with control theory can help meet the safety requirements for real-time decision making and Level 5 autonomy in self-driving vehicles. However, it is widely known that conventional reinforcement learning policies are vulnerable to adversarial or non-adversarial perturbations to their observations, similar to adversarial examples for classifiers and/or reward (packet) drops of the learning. Such issues are exacerbated by concerns of addressing resiliency as the use of open communication and control platforms for autonomy becomes essential, and as the industry continues to invest in such systems. Decision making mechanisms, designed to incorporate agility with the help of reinforcement learning, allow self-adaptation, self-healing, and self-optimization. This research will contribute and unify the body of knowledge of several diverse fields including reinforcement learning, security, automatic control, and transportation for resilient autonomy with humans-in-the-loop.. , Situação: Em andamento; Natureza: Desenvolvimento. , Alunos envolvidos: Doutorado: (2) . , Integrantes: José Messias Magalhães Júnior - Integrante / VAMVOUDAKIS, KYRIAKOS G. - Coordenador.

Prêmios