Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 3
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Artificial Intelligence-Driven Aircraft Systems to Emulate Autopilot and GPS Functionality in GPS-Denied Scenarios Through Deep Learning

  • García-Gascón, César|||0009-0007-6772-0474
  • Castelló-Pedrero, Pablo|||0000-0002-6927-6430
  • García Manrique, Juan Antonio|||0000-0001-9507-0746
  • Chinesta-Soria, Francisco
[EN] This paper presents a methodology for training a Deep Learning model aimedat flight management tasks in a fixed-wing unmanned aerial vehicle (UAV), specifically autopilot control and GPS prediction. In this formulation, sensor data and the most recent GPS signal are first processed by an LSTM to produce an initial coordinate prediction. This preliminary estimate is then merged with additional sensor inputs and passed to an MLP, which replaces the conventional autopilot algorithm by generating the control commands for real-time navigation. The approach is particularly valuable in scenarios where the aircraft must follow a predetermined route¿such as surveillance operations¿or maintain a remote ground link under varying GPS availability. The study focuses on Class I UAVs; however, the proposed methodology can be adapted to larger classes (II and III) by adjusting sensor configurations and network parameters. To collect training data, a small fixed-wing aircraft was instrumented to record kinematic and control inputs, which then served as inputs to the neural network. Despite the limited sensor suite and the use of an open-source flight controller (SpeedyBee), the flexibility of the proposed approach allows for easy adaptation to more complex UAVs equipped with additional sensors, potentially improving prediction accuracy. The performance of the neural network, implemented in PyTorch, was evaluated by comparing its predicted data with actual flight logs. In addition, the method has been shown to be robust to both short and prolonged GPS outages, as it relies on waypoint-based navigation along previously explored routes, ensuring reliable performance in known operational contexts., This research received partial funding from the Government of Spain under the project PID2023-151110OB-I00 and Generalitat Valenciana under CIPROM/2022/3 and CIACIF/2021/286. This research project is part of the programme DesCartes and is supported by the National Research Foundation, Prime Minister s Office, Singapore under its Campus for Research Excellence and Technological Enterprise (CREATE) programme. Funding for open access charge: Universitat Politècnica de València.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Manufacturing-driven AI: synthetic image generation for automated fiber orientation analysis in reinforced polymers

  • García-Gascón, César|||0009-0007-6772-0474
  • Javier Bas-Bolufer
  • Castelló-Pedrero, Pablo|||0000-0002-6927-6430
  • García Manrique, Juan Antonio|||0000-0001-9507-0746
[EN] Large Format Additive Manufacturing (LFAM) enables the rapid production of composite components using short fiberreinforced thermoplastics. This process offers high strength-to-weight ratios and efficient material deposition. However, the mechanical performance of printed parts is strongly dependent on fiber orientation. Reliable characterisation of orientation remains challenging due to the limitations of manual microscopy analysis. It is further hindered by the scarcity of large, annotated datasets required for deep learning inference (i.e., the automatic prediction of fiber orientation from image data using trained neural networks). This study addresses this gap by proposing a physics-informed methodology for the synthetic generation of microscopy-like images that replicate the microstructure of LFAM-processed composites. The simulation pipeline, implemented in Python, creates large-scale datasets by generating non-overlapping ellipsoidal fiber distributions with known geometrical and statistical parameters. Each synthetic image is paired with an analytically computed orientation tensor. This enables the supervised training of convolutional neural networks (CNNs) without the need for manual annotation. The system allows full control over fiber orientation, aspect ratio, and area fraction. It is calibrated using real micrographs obtained via X-ray Microscopy (XRM). The resulting synthetic images closely reproduce the statistical features of real microstructures and provide robust ground truth for model training and validation. Overall, this scalable approach enables rapid dataset generation and facilitates the development of accurate AI models for automated orientation analysis. It also supports future applications in digital twin frameworks, in-line quality control, and material characterisation in LFAM., This research received partial funding from the Government of Spain under the project PID2023-151110OB-I00, and from the Generalitat Valenciana through projects CIPROM/2022/3, CIACIF/2021/286, and CIBEFP/2024/045. César García-Gascón is supported by a predoctoral contract funded under CIACIF/2021/286 and has also received a mobility grant for a research stay under reference CIBEFP/2024/045. Javier Bas-Bolufer is funded through the project CIPROM/2022/3. All co-authors are contributors within the framework of the national project PID2023-151110OB-I00.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Interlayer adhesion in Large Format Additive Manufacturing of glass fiber reinforced ABS structures

  • Castelló-Pedrero, Pablo|||0000-0002-6927-6430
  • Javier Bas-Bolufer
  • García-Gascón, César|||0009-0007-6772-0474
  • García Manrique, Juan Antonio|||0000-0001-9507-0746
  • Chinesta, Francisco
[EN] Large Format Additive Manufacturing (LFAM) is a promising technology for the rapid production of molds for high-performance composite parts in aerospace and automotive applications. Using ABS reinforced with short glass fibers (20% by weight) as granules improves production rates and mechanical performance. However, interlayer adhesion remains a major challenge, as the interface between layers is typically the weakest point in printed structures. This study examines the effects of three printing parameters on interlayer adhesion: time per layer ( ), nozzle temperature ( ), and extrusion factor ( ). The ABS/20GF composite is first characterized to determine its thermal and physical properties. An infrared camera monitors temperature evolution during printing, and tensile tests with loads applied perpendicular to the printing direction evaluate mechanical performance. Microstructural analysis reveals fracture mechanisms between layers. Results show that interlayer adhesion improves with shorter and higher and values. Thermal monitoring indicates a strong correlation between enhanced strength and reduced temperature gradients between layers, enabling better polymer chain mobility and bonding. ANOVA analysis identifies and as statistically significant factors influencing interlayer adhesion. These findings provide valuable insights for optimizing LFAM process parameters to enhance the structural integrity of fiber-reinforced thermoplastic components., The authors would like to acknowledge Generalitat Valenciana (GVA), Spain and Spanish Ministry of Science and Innovation, Spain (Grant No.: TED2021-130879B-C21, CIACIF/2021/286, PID2023-1511 10OB-I00 and CIPROM/2022/3) to provide funds for conducting experiments and software licenses. This research is part of the programme DesCartes (INP06437) and is supported by the National Research Foundation, Prime Minister s Office, Singapore under its Campus for Research Excellence and Technological Enterprise (CREATE) programme.