Artículos (Ingeniería Electrónica)

URI permanente para esta colecciónhttps://hdl.handle.net/11441/11357

Examinar

Mostrando 1 - 20 de 402

A Comparative Study of BERT-Based Models for Teacher Classification in Physical Education
(MDPI, 2025-09-28) Martín-Hoz, Laura; Yanes Luis, Samuel; Huerta Cejudo, Jerónimo; Gutiérrez Reina, Daniel; Franco Álvarez, Evelia; Tecnología Electrónica; Ingeniería Electrónica; Junta de Andalucía; TIC201: ACE-TI
Assessing teaching behavior is essential for improving instructional quality, particularly in Physical Education, where classroom interactions are fast-paced and complex. Traditional evaluation methods such as questionnaires, expert observations, and manual discourse analysis are often limited by subjectivity, high labor costs, and poor scalability. These challenges underscore the need for automated, objective tools to support pedagogical assessment. This study explores and compares the use of Transformer-based language models for the automatic classification of teaching behaviors from real classroom transcriptions. A dataset of over 1300 utterances was compiled and annotated according to the teaching styles proposed in the circumplex approach (Autonomy Support, Structure, Control, and Chaos), along with an additional category for messages in which no style could be identified (Unidentified Style). To address class imbalance and enhance linguistic variability, data augmentation techniques were applied. Eight pretrained BERT-based Transformer architectures were evaluated, including several pretraining strategies and architectural structures. BETO achieved the highest performance, with an accuracy of 0.78, a macro-averaged F1-score of 0.72, and a weighted F1-score of 0.77. It showed strength in identifying challenging utterances labeled as Chaos and Autonomy Support. Furthermore, other BERT-based models purely trained with a Spanish text corpus like DistilBERT also present competitive performance, achieving accuracy metrics over 0.73 and and F1-score of 0.68. These results demonstrate the potential of leveraging Transformer-based models for objective and scalable teacher behavior classification. The findings support the feasibility of leveraging pretrained language models to develop scalable, AI-driven systems for classroom behavior classification and pedagogical feedback.
Kalman Filter-Based Model-Free Predictive Control of Classical DC–DC Power Converters
(IEEE, 2025) Maureira, Angel; Riffo, Sebastián; Ibáñez, Esteban; González-Castaño, Carolina; Rivera, Marco; Guarnizo-Lemus, Cristian; Márquez Alcaide, Abraham; Restrepo, Carlos; Ingeniería Electrónica; Ministerio de Hacienda y Función Pública. España
Conventional model predictive control (MPC) of power converters has been widely found in many power electronics and motor drive applications. The performance of MPC strongly depends on the precision of the converter’s physical parameters, and a mismatch of them produces a control degradation, which leads to MPC suboptimal operation. Ensuring a precise estimation of the converter’s parameters is difficult because they continuously change during the operation process due to their operating point and aging. Recently, model-free predictive control (MF-PC) has been used in motor drives and power electronics converters, especially inverters and rectifiers, to deal with the predictive control method’s dependency model. However, MF-PC proposed for dc–dc converters is an open innovation scientific field. This article proposes an MF-PC designed for second-order dc–dc converters, such as the boost, buck, buck–boost, and noninverting buck–boost converters. The presented approach uses a Kalman filter to estimate the positive and negative inductor current slopes with high accuracy and a low computational cost. The experimental results show that the proposed method is robust against parameter and model changes compared to conventional model-based solutions.
eDNA and Citizen Science Reveal Hidden Fish Biodiversity in Climate-Stressed Urban Ports of the Mediterranean Sea
(Wiley, 2025) Madon, Bénédicte; Haderlé, Rachel; Arotcharen, Emma; David, Romain; Fontaine, Quentin; Marengo, Michel; Thomas, Hélène; Torralba Silgado, Antonio Jesús; Valentini, Alice; Jung, Jean-Luc; Teoría de la Señal y Comunicaciones; Ingeniería Electrónica; European Union (UE). H2020
This paper provides a pioneering study case on monitoring fish biodiversity in ports through the eDNA and citizen science approach. eDNA samples were collected in the spring and in fall 2022 in the ports of Calvi, L'Île-Rousse, STARESO, Saint-Florent. Samples collected led to the identification of 73 taxa. These ports appeared to harbor at least 20% of the known teleost biodiversity in Corsica and 11% of the Mediterranean teleost biodiversity. The ports of Calvi and L'Île-Rousse displayed the highest taxonomic, phylogenetic, and functional diversities and appeared the most similar. However, taxonomic turnover highlighted that none of the 4 ports was a subset of any of the others. In August 2022, an extreme climate event (ECE) struck Corsica, offering a unique opportunity to collect data under abnormal conditions. Although it is not possible to distinguish the seasonal effect from the ECE effect in the fall, we detected in all ports but Saint-Florent an increase in taxonomic richness, phylogenetic, and functional diversity: we did not only detect new species but also showed that these species led to an increase in the local representativeness of phylogenetic diversity, most likely correlated with new functional traits. The port of Saint-Florent displayed the highest relative phylogenetic diversity, that is, a smaller but evolutionarily more distinct group of species. Our study demonstrated the robustness and relevance of eDNA citizen science coupled with relevant indicators for port biodiversity monitoring and emphasized the need for more research and targeted conservation efforts to better understand and mitigate the ecological impacts of ports while exploring their potential as habitats.
Optical Fiber Performance for High Solar Flux Measurements in Concentrating Solar Power Applications
(Multidisciplinary Digital Publishing Institute (MDPI), 2025) Jerez González, Manuel; Carballar Rincón, Alejandro; González-Aguilar, José; Ingeniería Electrónica; Ministerio de Ciencia e Innovación (MICIN). España
Extreme operating conditions in solar receivers of concentrated solar thermal power plants, such as high temperatures, intense irradiance, and thermal cycling, pose significant challenges for conventional sensors. Optical fibers offer a promising alternative for flux measurement in such environments, but their long-term performance and degradation mechanisms require detailed investigation and characterization. This work presents a proof of concept for high solar flux measurement by using optical fibers as photon-capturing elements and showcases the behavior and damage that these optical fibers undergo when exposed to relevant conditions, including temperatures over 600 ◦C and flux levels exceeding 400 kW/m2. Three fiber configurations, including polyimide and gold-coated fibers, were tested at a high-flux solar simulator and analyzed via scanning electron microscopy to assess structural integrity and material degradation. Results reveal significant coating deterioration, fiber retraction, and thermal-induced stress effects, which impact measurement reliability. These findings provide essential insights for improving the durability and accuracy of optical fiber-based sensing technologies in concentrating solar energy.
0.7 V Supply SC Circuits with Relaxed Slew Rate Requirements Using GB-Enhanced Multiple-Output Class AB/AB Op-Amps
(Multidisciplinary Digital Publishing Institute (MDPI), 2025) Rico-Aniles, Hector Daniel; Paul, Anindita; Ramírez-Angulo, Jaime; López-Martín, Antonio J.; González Carvajal, Ramón; Ingeniería Electrónica
A family of improved low-voltage switched-capacitor circuits is introduced. It is based on the utilization of multiple-output class AB/AB op-amp architectures that provide true sample and hold outputs that are not subject to a reset phase as with conventional switched-capacitor circuits. This feature essentially relaxes the op-amp slew rate requirements, allowing a higher speed and simple low-voltage operation. A power-efficient GB boosting technique based on resistive local common mode feedback is used to significantly improve the GB and internal/external slew rate of the op-amps with only a 36.5% additional power dissipation.
Comparative Study of Sphere Decoding Algorithm and FCS-MPC for PMSMs in Aircraft Application
(Multidisciplinary Digital Publishing Institute (MDPI), 2025) Akinwumi, Joseph O.; Gao, Yuan; Yuan, Xin; Vázquez Pérez, Sergio; Ruiz, Harold S.; Ingeniería Electrónica; Ministerio de Ciencia e Innovación (MICIN). España; University of Leicester
In this study, we propose a long prediction horizon finite control set model predictive control (FCS-MPC) framework for PMSMs. Initial simulations using a one-norm cost function resulted in instability in switching frequency control, particularly due to the inherent limitations imposed by the sampling interval when no control effort was applied. To mitigate this, we reformulated the MPC framework using a two-norm cost function within a sphere decoding algorithm (SDA), which, at high sampling intervals (>40 μs), resulted in an undershoot in the direct-quadrature axis. Extensive simulations were conducted over a range of sampling intervals (1–80μs), revealing that while a 10μs interval achieved the lowest THD, it also led to an increased switching frequency. To address this trade-off, a weighting factor tuning approach was employed, effectively reducing switching frequency while maintaining acceptable THD levels. Further investigations analyzed the effects of three-step and five-step prediction horizons, as well as parameter mismatches in the long prediction formulation, providing critical insights into controller robustness. These findings underscore the importance of norm selection, sampling interval optimization, and weighting factor adjustments in balancing THD reduction and switching frequency. The proposed approach enhances system efficiency, reliability, and overall performance, offering significant implications for high-performance aerospace PMSM applications.
The Role of Modulation Techniques on Power Device Thermal Performance in Two-Level VSI Converters
(Multidisciplinary Digital Publishing Institute (MDPI), 2025) Márquez Alcaide, Abraham; León Galván, José Ignacio; Rojas, Christian A.; Berger, Jhonattan G.; Stowhas-Villa, Alejandro; Wilson-Veas, Alan H.; Buticchi, Giampaolo; Kouro Renaer, Samir; Ingeniería Electrónica; Ministerio de Ciencia e Innovación (MICIN). España; Junta de Andalucía; Centro de Investigación en Energía Solar (SERC). Chile
The failure of power semiconductors due to variations in junction temperature represents an important factor in determining the reliability of a power converter. This work presents a comparative assessment of the thermal performance of IGBT power semiconductors within a two-level voltage source converter, specifically the average junction temperature and the variation of this value over a given period. The evaluation was carried out using different continuous and discontinuous carrier-based pulse width modulation (CB-PWM) techniques. The use of discontinuous PWM allows for a decrease in switching losses and therefore in average junction temperatures, but the variation in junction temperature is largely and non-linearly dependent on several factors, including the power factor of the three-phase load. Among the discontinuous PWM techniques, this analysis focuses on those that allow for a symmetric thermal load. The aforementioned comparisons have been tested in a laboratory setup, whee we directly measured the junction temperature through a high-end infrared thermal camera.
Optical Detection Techniques for Biomedical Sensing: A Review of Printed Circuit Board (PCB)-Based Lab-on-Chip Systems
(Multidisciplinary Digital Publishing Institute (MDPI), 2025) Perdigones Sánchez, Francisco; Giménez Gómez, Pablo; Muñoz Berbel, Xavier; Aracil Fernández, Carmen; Ingeniería Electrónica
Lab on Printed Circuit Boards (Lab-on-PCB) technology has emerged as a promising platform, offering miniaturization, integration, and cost-effective fabrication for a wide range of sensing applications. This review explores the most common optical detection techniques implemented on printed circuit boards (PCBs), including absorbance, fluorescence, and chemiluminescence, discussing their working principles, advantages, and limitations in the context of PCB-based sensing. Additionally, evanescent wave generation is considered as an alternative optical approach with benefits for specific applications. Elements such as excitation sources, photodetectors, and the distinguishing characteristics of each method are analyzed to provide a comprehensive, but concise, overview of the field. Emphasis is placed on how the PCB platform influences the performance, sensitivity, and feasibility of these detection methods, highlighting relevant design considerations. This work aims to provide a solid foundation for researchers interested in optical sensing within this technology, serving as a reference for future developments and applications in PCB-based optical detection.
Predictive Current Control of a Five-Phase Drive Using a Lead-Pursuit Strategy and Virtual Voltage Vectors
(Multidisciplinary Digital Publishing Institute (MDPI), 2025) Barrero, Federico; Bermúdez Guzmán, Mario; Arahal, Manuel R.; González Prieto, Ignacio; Ingeniería Electrónica; Ingeniería Eléctrica; Ingeniería de Sistemas y Automática; Ministerio de Ciencia, Innovación y Universidades (MICIU). España; European Union (UE)
Modern electric machines are attracting the greatest interest from the research community due to their current increasing number of applications, including electric vehicles and wind power generators. Their use requires the development of complex regulators, where predictive controllers appear as interesting and viable alternatives in recent research works. Although these controllers have an easy formulation and high flexibility to incorporate different control objectives in multidimensional systems, they have limitations that require attention and limit their application: a high computational cost and current harmonic content. This work presents a novel controller that focuses on these limitations, where the additional degree of freedom introduced in the predictive controller through the lead-pursuit guidance law concept is combined with the use of virtual voltage vectors to reduce the harmonic content in a controlled drive. The effectiveness of the proposed controller is explored using a five-phase drive and several figures of merit, such as the root mean square error in current tracking, the total harmonic distortion in the stator currents, and the number of switching commutations per cycle. Different predictive controllers are compared with the proposal in terms of speed regulation, stator current control, and steady-state performance, where the results obtained are analyzed to show the interest, improvements, and limitations of the proposal.
On the Usage of Deep Learning Techniques for Unmanned Aerial Vehicle-Based Citrus Crop Health Assessment
(MDPI, 2025-06-30) Gálvez, Ana I.; Afonso, Frederico; Martínez Heredia, Juana María; Ingeniería Electrónica
This work proposes an end-to-end solution for leaf segmentation, disease detection, and damage quantification, specifically focusing on citrus crops. The primary motivation behind this research is to enable the early detection of phytosanitary problems, which directly impact the productivity and profitability of Spanish and Portuguese agricultural developments, while ensuring environmentally safe management practices. It integrates an onboard computing module for Unmanned Aerial Vehicles (UAVs) using a Raspberry Pi 4 with Global Positioning System (GPS) and camera modules, allowing the real-time geolocation of images in citrus croplands. To address the lack of public data, a comprehensive database was created and manually labelled at the pixel level to provide accurate training data for a deep learning approach. To reduce annotation effort, we developed a custom automation algorithm for pixel-wise labelling in complex natural backgrounds. A SegNet architecture with a Visual Geometry Group 16 (VGG16) backbone was trained for the semantic, pixel-wise segmentation of citrus foliage. The model was successfully integrated as a modular component within a broader system architecture and was tested with UAV-acquired images, demonstrating accurate disease detection and quantification, even under varied conditions. The developed system provides a robust tool for the efficient monitoring of citrus crops in precision agriculture.
Integrated Bragg Grating Spectra
(Multidisciplinary Digital Publishing Institute (MDPI), 2025) Praena, José Ángel; Carballar Rincón, Alejandro; Ingeniería Electrónica
In this paper, we present a general methodology suitable for analyzing any IBG (Integrated Bragg Grating) as a linear time-invariant (LTI) system using the effective refractive index (ERI) and transfer matrix method (TMM). This approach is based on the translation of the IBG’s physical structure into a matrix of effective refractive indexes, neff, which is wavelength-dependent and describes the behavior of light in the IBG while avoiding the use of approximations like Coupled Mode Theory does. This procedure allows to obtain very accurate reflection and transmission spectra, regardless of the perturbation complexity of the grating. Using this methodology, different apodization and chirp methods are revised and compared. Its generality is considered by analyzing two distinct technological platforms, silicon-on-insulator (SOI) and aluminum oxide (Al2O3).
Automatic and Versatile Test Bench for Data Collection on Battery Cells
(Multidisciplinary Digital Publishing Institute (MDPI), 2025) Marsal Pederzani, Esteban; Martínez Cantero, Nicolás; Pérez Vega-Leal, Alfredo; Barrero, Federico; Hamdan, Mohamad; Garrido Satué, Manuel; Ingeniería de Sistemas y Automática; Ingeniería Electrónica; Ministerio de Ciencia e Innovación (MICIN). España; European Union (UE)
Rechargeable batteries are a key component of sustainable future systems, as their performance directly affects energy efficiency, maintenance costs, and system reliability. Assessing performance requires evaluating parameters such as the state of health (SoH) of the battery, which necessitates developing a system capable of efficiently gathering large amounts of data. This article presents a safe, simple, versatile, and automated system designed to test and characterize various types of battery cells. The system is conceived as a practical tool capable of automatically collecting the required data for analysis, thus enabling the determination of the performance parameters of a battery cell. The proposed system incorporates an innovative approach based on the concatenation of charge/discharge data, allowing for a more reliable evaluation of battery performance. Experimental tests show the interest and performance behavior of the proposed system.
A Review of Techniques to Enhance an Amplifier’s Performance Using Resistive Local Common Mode Feedback
(Multidisciplinary Digital Publishing Institute (MDPI), 2023) Ramírez Angulo, Jaime; López Martín, Antonio J.; González Carvajal, Ramón; Torralba Silgado, Antonio Jesús; Huerta Chua, Jesús; Ingeniería Electrónica; Agencia Estatal de Investigación. España; Junta de Andalucía
A review of some of the most common applications of the resistive local common mode feedback technique to enhance amplifier’s performance is presented. It is shown that this simple technique offers essential improvement in open loop gain, gain-bandwidth product, slew rate, common mode rejection ratio, power supply rejection ratio, etc. This is achieved without increasing power dissipation or supply voltage requirements and with small additional silicon area and circuit complexity. It is also shown that it is especially appropriate to improve amplifiers’ performance in current fine-line submicrometer CMOS technology. Some of the applications discussed are GB enhanced, class AB and super class AB operational amplifiers, gain boosted op-amps, bulk-driven circuits, sample and hold circuits and power management circuits, among others.
Structural assessment of the medieval city wall of Seville (Spain) using low-cost accelerometers
(Elsevier, 2025-06) Serrano Chacón, Álvaro Rubén; Mascort-Albea, Emilio J.; Romero Hernández, Rocío; Canivell, Jacinto; Muñoz Chavero, Fernando; Hidalgo Fort, Eduardo; Jaramillo Morilla, Antonio; Ingeniería del Diseño; Estructuras de Edificación e Ingeniería del Terreno; Construcciones Arquitectónicas II (ETSIE); Ingeniería Electrónica; Ministerio de Educación, Cultura y Deporte (MECD). España; TEP018: Ingeniería del Terreno; TEP211: Conservación Preventiva del Patrimonio Construido; TIC192: Ingeniería Electrónica
The remains of fortifications are commonly found embedded in the contemporary urban fabric of historic cities. Due to their typological nature, these heritage assets are usually elements of great size and impact on the urban landscape. Their location within cities exposes them to very specific risks, such as pollution, vibration, biodegradation, and anthropic factors, which must be taken into account for the proper conservation and maintenance of such remains. The case of the medieval wall of Seville (Spain), built on rammed earth, shows specific factors of vulnerability, degradation, and erosion which prompt the need for non-destructive techniques (NDT). In the present research, vibration-based inspection is used and, specifically, when subjected to ambient vibrations. The collection of accelerations, which covered a period of nine months, was conducted in different parts of the structure under study by using mainly high-resolution accelerographs. These data allowed to perform an exhaustive dynamic characterisation of this defensive structure. Among other findings, it was determined that the filling of cracks and voids in the walls increased the fundamental frequency by about 2 %. In addition, no serious damage to the structure was found. Knowledge of the historic buildings' condition is essential in order to determine the most appropriate intervention. To this end, a protocol for the global structural diagnosis of these buildings has been proposed. It is based on the recording of accelerations with low-cost accelerographs. Besides being an inexpensive protocol, it allows a quick decision making, since the dynamic characterization of the structure is performed by means of the fast Fourier transform. Basically, the designed protocol is based on the variation of the fundamental frequency of the structure between two time instants. These values are used for the calculation of a damage index. By means of an exhaustive review of conventional masonry buildings tested in the laboratory, the damage index has been correlated with the state of the structure prior to collapse. Specifically, this threshold, which ranges from DS4 to DS5 according to the criteria of the European Macroseismic Scale 1998 (EMS-98), provides a valuable reference point for the structural assessment of historical box-shaped constructions with conventional masonry load-bearing walls. This simplified procedure for structural diagnosis was applied in its initial phase at the White Tower. It was found that this protocol is able to identify the fundamental frequency of the structure with an error of <0.65 % in comparison to the results obtained through operational modal analysis methods.
Decoupling Patrolling Tasks for Water Quality Monitoring: A Multi-Agent Deep Reinforcement Learning Approach
(IEEE, 2024) Seck Diop, Dame; Yanes Luis, Samuel; Perales Esteve, Manuel Ángel; Toral, S. L.; Gutiérrez Reina, Daniel; Ingeniería Electrónica; Ministerio de Ciencia e Innovación (MICIN). España; European Union (UE)
This study proposes the use of an Autonomous Surface Vehicle (ASV) fleet with water quality sensors for efficient patrolling to monitor water resource pollution. This is formulated as a Patrolling Problem, which consists of planning and executing efficient routes to continuously monitor a given area. When patrolling Lake Ypacaraí with ASVs, the scenario transforms into a Partially Observable Markov Game (POMG) due to unknown pollution levels. Given the computational complexity, a Multi-Agent Deep Reinforcement Learning (MADRL) approach is adopted, with a common policy for homogeneous agents. A consensus algorithm assists in collision avoidance and coordination. The work introduces exploration and reinforcement phases to the patrolling problem. The Exploration Phase aims at homogeneous map coverage, while the Intensification Phase prioritizes high polluted areas. The innovative introduction of a transition variable, ν, efficiently controls the transition from exploration to intensification. Results demonstrate the superiority of the method, which outperforms a Single-Phase (trained on a single task) Deep Q-Network (DQN) by an average of 17% on the intensification task. The proposed multitask learning approach with parameter sharing, coupled with DQN training, outperforms Task-Specific DQN (two DQNs trained on separate tasks) by 6% in exploration and 13% in intensification. It also outperforms the heuristic-based Lawn Mower Path Planner (LMPP) and Random Wanderer Path Planner (RWPP) algorithms, by 35% and 20% on average respectively. Additionally, it outperforms a Particle Swarm Optimization-based Path Planner (PSOPP) by an average of 26%. The algorithm demonstrates adaptability in unforeseen scenarios, giving users flexibility in configuration.
Variational model-based Deep Reinforcement Learning for Non-Homogeneous Patrolling aquatic environments with multiple unmanned surface vehicles
(Elsevier, 2025-04-25) Yanes Luis, Samuel; Basilico, Nicola; Antonazzi, Michele; Gutiérrez Reina, Daniel; Toral, S. L.; Ingeniería Electrónica; TIC201: ACE-TI
This paper addresses the challenge of Non-Homogeneous Patrolling for Autonomous Surface Vehicles in non-homogeneous importance water environments with a dissimilar biological monitorization criterion. Traditional monitoring methods fail, especially in expansive areas such as Lake Ypacaraíin Paraguay. The proposed solution employs a cooperative Deep Reinforcement Learning framework, specifically a multi-agent version of the Double Deep Q-Learning algorithm based on safe-consensus decision making. This framework optimizes adaptive policies for such vehicles by simultaneously modeling the environment and patrolling high-importance zones. The incorporation of a Variational Auto-Encoder based on the U-Network architecture directly addresses the non-observability of the environment by predicting biological importance from partial observations. The methodology is validated in a realistic algae bloom contamination scenario, demonstrating superior performance and computational efficiency compared to traditional approaches like Gaussian Processes and K-Nearest-Neighbors. The Deep Reinforcement Learning framework, coupled with the Variational Auto-Encoder model, showcases flexibility and efficiency in addressing multi-agent cooperation and long-term objective optimization for water quality monitoring. The results reveal significant improvements, with the proposed model exceeding well-founded approaches with a 30% faster minimization of the patrolling score compared to these methods.
Cascade Control of Grid-Connected NPC Converters Via Sliding Mode Technique
(Institute of Electrical and Electronics Engineers, 2023-02) Shen, Xiaoning; Liu, Jianxing; Lin, Hao; Yin, Yunfei; Márquez Alcaide, Abraham; León Galván, José Ignacio; Ingeniería Electrónica; TIC109: Tecnología
This paper proposes a two-stage control strategy including an adaptive sliding mode control (ASMC) and a nonlinear high-gain observer (HGO) for the three-level neutral-point-clamped (NPC) converter in dc microgrids. In the outer loop, an ASMC is utilized to regulate the dc-link voltage. By introducing an adapted gain, the tradeoff between the chattering and dynamic performance of the classic sliding mode control is overcome, thus the transient response of the NPC converter can be further enhanced without increasing the chattering. In addition, a nonlinear HGO is cooperated with the ASMC method to reject exogenous disturbance for the NPC converter, which not only assures a high disturbance rejection capacity but also accommodates the inevitable measurement noise in the actual applications. For the inner loop, in consideration of the parameter uncertainty, a high-gain observer-based second-order sliding mode (SOSM) control is adopted to assure the steady state performance and the robustness of the NPC converter. Finally, a set of comparative experimental results confirm the effectiveness and superiority of the proposed control scheme implemented in the NPC converter. Additionally, the robustness under parameter variation of the proposed method is also validated.
Towards a Retrieval-Augmented Generation Framework for Originality Evaluation in Projects-Based Learning Classrooms
(MDPI, 2025-06) Yanes Luis, Samuel; Gutiérrez Reina, Daniel; Toral, S. L.; Ingeniería Electrónica; Junta de Andalucía; TIC201: ACE-TI
Project-Based Learning is central to modern engineering education, but assessing the originality of student work poses significant challenges, particularly when previous project repositories are accessible. This paper addresses the issue by proposing a framework based on Retrieval-Augmented Generation and Large Language Models to evaluate the originality of project proposals in the context of a master’s course in Electronic Engineering. The system processes and summarizes prior work—including reports, code, and presentations—creating a semantically indexed knowledge base. Upon receiving a new proposal, the RAG system compares it to this base, identifies the most similar previous works, and generates an originality assessment. Results show the effectiveness of the approach, with a strong correlation (coefficient of 0.87) between the originality scores assigned by the system and those given by expert instructors in a blind evaluation. The proposed RAG system demonstrates its ability to systematically detect similarities and potential lack of originality that might be overlooked by human evaluators due to the volume of prior work. This framework provides an objective and efficient tool to support originality assessment, benefiting both instructors and students by promoting genuine innovation in PBL settings.
Computational Analysis of the Long Horizon FCS-MPC Problem for Power Converters
(Institute of Electrical and Electronics Engineers, 2024-06) Zafra, Eduardo; Vázquez Pérez, Sergio; Geyer, Tobías; Aguilera, Ricardo P.; Freire Macías, Emilio; García Franquelo, Leopoldo; Ingeniería Electrónica; Matemática Aplicada II (ETSI); Ministerio de Ciencia e Innovación (MICIN). España; TIC109: Tecnología
Long prediction horizon finite control set model predictive control (LPH-FCS-MPC) for power converters can be reformulated as a box-constrained integer-least squares (ILS) problem to find the optimal control action without requiring an exhaustive search. Instead, the solution can be found by means of a sphere decoding method that still presents several intricacies regarding its complexity and its variable computational cost. This article provides a study of the computational behavior of this approach. Special emphasis is placed on how the generator matrix is calculated, either as a lower or an upper triangular structure. This choice decides whether the switching sequences are explored forward- or backward-in-time during the optimization process. In this work, it is explained how this selection holds a great impact on the computational burden of the algorithm. Similarly, it is also analyzed how the tuning of the FCS-MPC and system parameters also drastically impacts the computational cost.
Common DC-link Capacitor Lifetime Extension in Modular dc/dc Converters for Electric Vehicle Fast Chargers via Variable-Angle Interleaved Operation
(Institute of Electrical and Electronics Engineers, 2022-12) Márquez Alcaide, Abraham; Guenter, Sandro; León Galván, José Ignacio; Buticchi, Giampaolo; Kouro, Samir; García Franquelo, Leopoldo; Ingeniería Electrónica; Ministerio de Ciencia e Innovación (MICIN). España; Junta de Andalucía; TIC109: Tecnología
The global shift toward the electrified transportation as a means of achieving decarbonized economy has led to an increase in the demand of electric vehicles. In order to enhance the transition, there is a need to develop fast and ultrafast charging substations. Hence, power converters play an inherently vital role in the mass adoption of electric vehicles. However, the reliability and active maintenance scheduling of these converters are becoming prominent issues for manufacturers and operators. As a result, optimization of the operation of an interleaved dc/dc converter present in the charging poles plays a significant role. This article proposes an alternative modulation technique for interleaved dc/dc power converters of fast chargers aiming to improve the harmonic performance of the common dc-link capacitor current. This technique leads to an extension of lifetime of the capacitor, which is one of the most critical component of the power system. Experimental results are shown in order to validate the effectiveness of the proposed method.

Examinar

Envíos recientes