Pasar al contenido principal

GENERACION DE TRAYECTORIAS OPTIMAS CON MACHINE LEARNING PARA FABRICACION ADITIVA Y SISTEMAS COMPLEJOS DE TRANSPORTE

PID2023-151110OB-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2023
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSITAT POLITÈCNICA DE VALÈNCIA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 6
Encontrada(s) 1 página(s)

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

Deep Learning-Based Fiber Orientation Analysis for Discontinuous Composites: Application to Material Extrusion Additive Manufacturing

  • García-Gascón, César|||0009-0007-6772-0474
  • Javier Bas-Bolufer
  • Castelló-Pedrero, Pablo|||0000-0002-6927-6430
  • Chinesta, Francisco
[EN] This paper presents a novel deep learning-based (DL) approach to characterize short-fiber orientation in material extrusion large format additive manufacturing (LFAM). The method focuses on Acrylonitrile Butadiene Styrene (ABS) reinforced with short glass fibers 20%, a material widely used due to its enhanced mechanical performance. Traditional fiber orientation analysis, which relies on microscopy and manual image processing, is often costly and time-consuming. To address this, we developed Python algorithms to generate synthetic SEM-like images to train a Convolutional Neural Network (CNN). The proposed CNN accurately predicts the fiber orientation tensors directly from micrographs, with consistent results with conventional methods. The combination of synthetic data generation and deep learning provides a scalable and rapid alternative for fiber orientation analysis. This approach improves the analysis of fiber orientation in discontinuous composite materials and has the potential to be applied to additive manufacturing and other forming processes. This study demonstrates that combining deep learning with synthetic data generation provides an effective, scalable solution for fiber orientation analysis in LFAM, confirming that CNN-based methods can greatly improve material characterization. More accurate performance prediction and quality control could be achieved in fiber-reinforced additive manufacturing., This research received partial funding from the Government of Spain under Project No. PID2023-151110OB-I00 and Generalitat Valenciana under CIPROM/2022/3 and CIACIF/2021/286. This research project is part of the program DesCartes and is supported by the National Research Foundation, Prime Minister's Office, Singapore under its Campus for Research Excellence and Technological Enterprise (CREATE) program.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

An open benchmark dataset for machine learning and intelligent trajectory optimization in fixed-wing unmanned aerial systems

  • 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] This paper presents an open-access telemetry dataset designed to support research and training in intelligent fixed-wing unmanned aerial systems. The dataset contains 240 fully annotated autonomous missions flown outdoors over repeatable, waypoint-based trajectories using two onboard architectures: a compact SpeedyBee F405 flight controller running INAV, and a Holybro Pixhawk 6X paired with a Jetson Orin NX companion computer running PX4. The missions cover key phases, including take-off, cruise, dynamic manoeuvres, and autonomous landing. Each log provides synchronised multi-sensor telemetry (IMU, GNSS, barometric altitude, actuator states, flight modes, and power metrics) at high temporal resolution, enabling realistic modelling of flight dynamics, estimator behaviour, and sensor noise. The dataset supports benchmarking for trajectory tracking under degraded GNSS, anomaly detection, wind-aware navigation, and energy-optimised mission planning. The paper documents hardware integration, communication architecture, mission procedures, and the dataset file structure, and includes representative analyses to illustrate reuse for contested, safety-critical, and complex operational environments in field. No neural network is trained or evaluated; deep learning is cited only as a motivating application domain., 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. 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. 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 . Funding for open access charge: CRUE-Universitat Politècnica de València.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Manufacturing and Structural Testing of Small Wind Turbine Blades Using Thermoplastic Composites

  • Carnicero, Rafael
  • Cano, Luis
  • Cruz, Ignacio
  • García Manrique, Juan Antonio|||0000-0001-9507-0746
[EN] Thermoplastic composites can be a solution for the circular economy of the wind industry. Some studies have focused on addressing the challenges of reusing raw materials and reducing both the economic costs and environmental damage. Thermoset composites have been crucial in increasing the size of wind turbines (WT), achieving longer and structurally more resistant blades, but they are difficult to recycle at the end of life and sometimes end up in landfills. Thermoplastic composites are being tested as an alternative to thermoset composites because of their similar structural properties and substantial advantages, such as ease of recycling. This article presents the results of the structural properties of a 2-m-long thermoplastic WT blade manufactured with a new thermoplastic resin called Akelite to obtain progress in the implementation of thermoplastic composites in this type of product. The new blade has been compared to an epoxy WT blade built with the same procedure. Property, static, and fatigue tests were performed on these blades to characterize them. The results of this comparison were quite similar, with less than 5% displacement in the static tests and a sensitivity change of less than 2% after the fatigue tests. Future studies should be conducted to extend this study to larger-scale blades., This research was funded by the AEI Agency of the Ministry of Science, Innovation and Universities of the Spanish Government, under Grant No. TED2021-130201B-C33, by NextGenerationEU European Funds, and PID2023-151110OB-I00. Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature.
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)

Study and Characterization of Recycled ABS-GF in Large Format Additive Manufacturing to Enhance Mechanical Properties of Printed Structures

  • Javier Bas-Bolufer
  • Castelló-Pedrero, Pablo|||0000-0002-6927-6430
  • García-Gascón, César|||0009-0007-6772-0474
  • García Manrique, Juan Antonio|||0000-0001-9507-0746
[EN] Large format additive manufacturing (LFAM) has proven its ability to produce high-performance components for competitive markets. By depositing material only where it's needed, it drastically reduces waste material and energy use, obtaining a sustainability advantage that is further enhanced on larger scale. However, a deeper understanding of material recycling is critical to achieving the next milestone in sustainability. In this work, a methodology was proposed that uses both molds and final parts, manufactured in acrylonitrile-butadiene-styrene reinforced with short glass fibers (ABS-GF), which had reached the end of their useful life to be used as feedstock. It is observed that recycling reduces fiber length by 47.3%, which directly impacts the mechanical properties in the longitudinal printing direction, resulting in around a 9% decrease in maximum tensile stress. However, this reduction falls to 5.1% in the transverse direction to the printing, and in some cases, the recycled material even surpasses the virgin material due to improved interlayer adhesion. An analysis on the adhesion reveals that the shorter monomer chains obtained during recycling allow better interlacing between layers. These results suggest that the reuse of the molds is viable and by adjusting the printing parameters we can obtain properties suitable for demanding applications., This research received partial funding from the Spain Ministry Science and Innovation under the project PID2023-151110OB-I00 and Generalitat Valenciana under CIPROM/2022/3 and CIACIF/2021/286.