Electronics

16 pages, 1400 KB

Open AccessArticle

Research on Variable Pitch Propeller Control Technology of eVTOL Based on ADRC

by Xijun Liu, Hao Zhao, Zhaoyang Li, Houlong Ai, Zelin Chen and Yuehong Dai

Electronics 2025, 14(18), 3627; https://doi.org/10.3390/electronics14183627 (registering DOI) - 12 Sep 2025

To address heading instability in electric vertical take-off and landing (eVTOL) aircraft at low speeds and large pitch angles, a rotational speed feedback compensation control scheme based on Active Disturbance Rejection Control (ADRC) is proposed for variable-pitch propellers. This scheme integrates propeller speed [...] Read more.

To address heading instability in electric vertical take-off and landing (eVTOL) aircraft at low speeds and large pitch angles, a rotational speed feedback compensation control scheme based on Active Disturbance Rejection Control (ADRC) is proposed for variable-pitch propellers. This scheme integrates propeller speed into the heading control inner loop and employs a state observer to process the measured speed. Simulation results demonstrate that under dynamic propeller speed variations of 0.5%, 1%, and 2%, the proposed compensation scheme reduces yaw angle oscillation amplitudes by 22.2%, 30.6%, and 37.8%, and yaw angular velocity fluctuations by 32.5%, 43.4%, and 33.3%, respectively, compared to a basic speed feedback scheme, showcasing significantly superior robustness. Experimental bench tests further validate that the proposed strategy enhances overall propeller force efficiency from 2.479 kg/kW to 3.05 kg/kW at 120 km/h cruise, resulting in a power saving of 0.48 kW and extending the cruising range by 8.5 km. The stability and energy efficiency of the proposed method are rigorously validated through both simulation and experimental testing. Full article

39 pages, 1346 KB

Open AccessReview

Resource Allocation Techniques in Aerial-Assisted Vehicular Edge Computing: A Review of Recent Progress

by Sangman Moh

Electronics 2025, 14(18), 3626; https://doi.org/10.3390/electronics14183626 - 12 Sep 2025

Abstract

Aerial-assisted vehicular edge computing (AVEC) has emerged as a transformative approach to addressing the limitations of traditional vehicular edge computing (VEC) in dynamic vehicular environments. By integrating platforms such as unmanned aerial vehicles (UAVs), high-altitude platforms (HAPs), and satellites, AVEC systems offer enhanced [...] Read more.

Aerial-assisted vehicular edge computing (AVEC) has emerged as a transformative approach to addressing the limitations of traditional vehicular edge computing (VEC) in dynamic vehicular environments. By integrating platforms such as unmanned aerial vehicles (UAVs), high-altitude platforms (HAPs), and satellites, AVEC systems offer enhanced scalability, flexibility, and responsiveness, enabling efficient resource allocation and adaptive decision-making. This paper presents a comprehensive survey of resource allocation techniques in AVEC, addressing both traditional and reinforcement learning-based approaches. These techniques aim to optimize the allocation of bandwidth, computation, and energy resources across heterogeneous platforms, ensuring reliable and efficient operations in diverse scenarios. Additionally, the study examines key challenges inherent in AVEC, including achieving seamless interoperability among diverse platforms, addressing scalability in large-scale systems, and adapting to real-time environmental dynamics. To address these challenges, the paper proposes future research directions, such as leveraging advanced technologies like quantum computing for solving complex optimization problems, employing tiny machine learning (TinyML) to enable resource-efficient intelligence on low-power devices, and predictive task offloading to enhance proactive resource management. By presenting a detailed analysis of existing techniques and identifying critical research opportunities, this paper seeks to guide researchers and practitioners in developing more efficient, secure, and adaptive AVEC systems. The insights from this study contribute to advancing the design and deployment of resilient intelligent transportation networks, paving the way for the next generation of vehicular connectivity. Full article

(This article belongs to the Special Issue Unmanned Aircraft Systems with Autonomous Navigation, 2nd Edition)

15 pages, 1718 KB

Open AccessArticle

Visible-Light Spectroscopy and Laser Scattering for Screening Brewed Coffee Types Using a Low-Cost Portable Platform

by Eleftheria Maliaritsi, Georgios Violakis and Evangelos Hristoforou

Electronics 2025, 14(18), 3625; https://doi.org/10.3390/electronics14183625 - 12 Sep 2025

Abstract

Visible-light spectroscopy has long been used to assess various quality indicators in coffee, from green beans to brewed beverages. High-end absorption spectroscopy systems can identify chemical compounds, monitor roasting chemistry, and support flavor profiling. Despite advances in low-cost spectroscopy, such techniques are rarely [...] Read more.

Visible-light spectroscopy has long been used to assess various quality indicators in coffee, from green beans to brewed beverages. High-end absorption spectroscopy systems can identify chemical compounds, monitor roasting chemistry, and support flavor profiling. Despite advances in low-cost spectroscopy, such techniques are rarely applied during coffee-drink preparation. Most coffee shops, instead, rely on simple refractometers to measure total dissolved solids (TDS) as a proxy for beverage strength. This study explores a portable, low-cost screening system that integrates visible absorption-transmittance, laser-induced scattering, and fluorescence spectroscopy to estimate brew strength and investigate potential differentiation between coffee-drink types. Experiments were conducted on four common drink preparations. A dual-region exponential decay model was applied to absorption-transmittance spectra, while laser-scattered light imaging revealed distinctive color patterns across samples. The results demonstrate the feasibility of optical fingerprinting as a non-invasive tool to support quality assessment in brewed coffee. Full article

(This article belongs to the Special Issue Section Collection Series: Recent Advances in Optoelectronics from Lab to Industry, 2nd Edition)

59 pages, 3482 KB

Open AccessFeature PaperArticle

Empirical Evaluation of Reasoning LLMs in Machinery Functional Safety Risk Assessment and the Limits of Anthropomorphized Reasoning

by Padma Iyenghar

Electronics 2025, 14(18), 3624; https://doi.org/10.3390/electronics14183624 - 12 Sep 2025

Abstract

Transparent reasoning and interpretability are essential for AI-supported risk assessment, yet it remains unclear whether large language models (LLMs) can provide reliable, deterministic support for safety-critical tasks or merely simulate reasoning through plausible outputs. This study presents a systematic, multi-model empirical evaluation of [...] Read more.

Transparent reasoning and interpretability are essential for AI-supported risk assessment, yet it remains unclear whether large language models (LLMs) can provide reliable, deterministic support for safety-critical tasks or merely simulate reasoning through plausible outputs. This study presents a systematic, multi-model empirical evaluation of reasoning-capable LLMs applied to machinery functional safety, focusing on Required Performance Level (PL

_{r}

) estimation as defined by ISO 13849-1 and ISO 12100. Six state-of-the-art models (Claude-opus, o3-mini, o4-mini, GPT-5-mini, Gemini-2.5-flash, DeepSeek-Reasoner) were evaluated across six prompting strategies and two dataset variants: canonical ISO-style hazards (Variant 1) and engineer-authored free-text scenarios (Variant 2). Results show that rule-grounded prompting consistently stabilizes performance, achieving ceiling-level accuracy in Variant 1 and restoring reliability under lexical variability in Variant 2. In contrast, unconstrained chain-of-thought reasoning (CoT) and CoT together with Retrieval-Augmented Generation (RAG) introduce volatility, overprediction biases, and model-dependent degradations. Safety-critical coverage was quantified through per-class F1 and recall of PL

_{r}

class e, confirming that only rule-grounded prompts reliably captured rare but high-risk hazards. Latency analysis demonstrated that rule-only prompts were both the most accurate and the most efficient, while CoT strategies incurred 2–10× overhead. A confusion/rescue analysis of retrieval interactions further revealed systematic noise mechanisms such as P-inflation and F-drift, showing that retrieval can either destabilize or rescue cases depending on model family. Intermediate severity/frequency/possibility (S/F/P) reasoning steps were found to diverge from ISO-consistent logic, reinforcing critiques that LLM “reasoning” reflects surface-level continuation rather than genuine inference. All reported figures include 95% confidence intervals, t-intervals across runs (

r = 5

) for accuracy and timing, and class-stratified bootstrap CIs for Micro/Macro/Weighted-F

_{1}

and per-class metrics. Overall, this study establishes a rigorous benchmark for evaluating LLMs in functional safety workflows such as PL

_{r}

determination. It shows that deterministic, safety-critical classification requires strict rule-constrained prompting and careful retrieval governance, rather than reliance on assumed model reasoning abilities. Full article

(This article belongs to the Special Issue New Insights into Natural Language Processing and Large Language Models)

18 pages, 1321 KB

Open AccessArticle

Enhanced AI-Driven Harmonic Optimization in 36-Pulses Converters for SCADA Integration

by Antonio Valderrabano-Gonzalez and Carlos E. Castañeda

Electronics 2025, 14(18), 3623; https://doi.org/10.3390/electronics14183623 - 12 Sep 2025

Abstract

This paper presents an integrated approach for optimizing the performance of a 36-pulses converter system by using artificial intelligence (AI) techniques to be included in a Supervisory Control and Data Acquisition (SCADA) environment. The focus of the proposal is on enhancing harmonic reduction [...] Read more.

This paper presents an integrated approach for optimizing the performance of a 36-pulses converter system by using artificial intelligence (AI) techniques to be included in a Supervisory Control and Data Acquisition (SCADA) environment. The focus of the proposal is on enhancing harmonic reduction through intelligent adjustment of switching angles and coordinated control of the reinjection transformer included in the power converter topology. A key component of the proposed methodology involves a simulation-based process to determine optimal firing angles (

α_{1}

,

α_{2}

, and

α_{3}

), based on Selective Harmonic Elimination (SHE) theory, that minimize Total Harmonic Distortion (THD). Using MATLAB with Simulink and PLECS models, a parametric sweep of the firing angles, generating a comprehensive dataset of THD outcomes. This dataset, consisting of THD evaluations across fine-grained angle variations, serves as the training foundation for supervised machine learning models—specifically, neural network regressors—that approximate the nonlinear mapping between firing angles and harmonic distortion. These predictive models are then employed as surrogates to estimate THD rapidly and guide the selection of optimal switching angles in real time without requiring iterative numerical solvers. Optimization heuristics and predictive models are then deployed to dynamically adapt system parameters in real time under varying load conditions. The proposed method demonstrates significant improvements in power quality and operational reliability, highlighting the potential of AI-assisted SCADA systems in advanced power electronics applications. Implementation results performed on a 36-pulses voltage source converter prototype are included to illustrate the appropriateness of the proposal. Full article

► Show Figures

Figure 1

32 pages, 5785 KB

Open AccessArticle

High-Efficiency Partial-Power Converter with Dual-Loop PI-Sliding Mode Control for PV Systems

by Jesús Sergio Artal-Sevil, Alberto Coronado-Mendoza, Nicolás Haro-Falcón and José Antonio Domínguez-Navarro

Electronics 2025, 14(18), 3622; https://doi.org/10.3390/electronics14183622 - 12 Sep 2025

Abstract

This paper presents a novel partial-power DC-DC converter architecture specifically designed for Photovoltaic (PV) energy systems. Unlike traditional full-power converters, the proposed topology processes only a fraction of the total power, resulting in improved overall efficiency, reduced component stress, and lower system cost. [...] Read more.

This paper presents a novel partial-power DC-DC converter architecture specifically designed for Photovoltaic (PV) energy systems. Unlike traditional full-power converters, the proposed topology processes only a fraction of the total power, resulting in improved overall efficiency, reduced component stress, and lower system cost. The converter is integrated into a PV-based energy system and regulated by a dual-loop control strategy consisting of a Proportional-Integral (PI) voltage controller and an inner Sliding-Mode Controller (SMC) for current regulation. This control scheme ensures robust tracking performance under dynamic variations in irradiance, load, and reference voltage. The paper provides a comprehensive mathematical model and control formulation, emphasizing the robustness and fast transient response offered by SMC. Simulation results obtained in MATLAB-Simulink, along with real-time implementation on the OPAL-RT hardware-in-the-loop (HIL) platform, confirm the effectiveness of the proposed design. The system achieves stable voltage regulation with low ripple and accurate current tracking. Compared to conventional boost configurations, the proposed converter demonstrates superior performance, particularly under moderate voltage conversion conditions. The system achieves high efficiency levels, validated through both analytical estimation and real-time hardware-in-the-loop (HIL) implementation. Its high efficiency, scalability, and real-time control feasibility make it a promising solution for next-generation PV systems, battery interfacing, and DC-microgrid applications. Full article

(This article belongs to the Special Issue Advanced DC-DC Converter Topology Design, Control, Application)

► Show Figures

Figure 1

22 pages, 9117 KB

Open AccessFeature PaperArticle

VIFPE: Multimodal Fusion of Visible and Infrared Images for Pose Estimation in Large-Scale Urban Environments

by Yangtao Meng, Xianfei Pan, Meiping Wu, Yan Guo, Yu Liu, Jie Jiang and Changhao Chen

Electronics 2025, 14(18), 3621; https://doi.org/10.3390/electronics14183621 - 12 Sep 2025

Abstract

Most existing deep learning-based camera pose estimation methods rely solely on visible images, making them vulnerable to challenges such as drastic lighting variations and poor nighttime imaging quality. These limitations reduce the robustness and accuracy of traditional approaches. To address these issues, we [...] Read more.

Most existing deep learning-based camera pose estimation methods rely solely on visible images, making them vulnerable to challenges such as drastic lighting variations and poor nighttime imaging quality. These limitations reduce the robustness and accuracy of traditional approaches. To address these issues, we propose VIFPE (Visible- and Infrared-Fusion-Based Pose Estimation), a novel framework that integrates features from both visible and infrared images to enhance pose estimation in urban environments. By leveraging the complementary advantages of visible images, which are rich in texture, and infrared images, which are resilient to illumination changes, VIFPE achieves robust and accurate localization across diverse lighting conditions. The framework consists of multiple key modules, including a feature extractor, a multimodal fusion module, a pose regressor, and a multi-task learning strategy. Specifically, VIFPE employs Multi-axis Vision Transformer (MaxViT) encoders to extract features from both modalities, which are then fused in a shared feature space through a cross-modal fusion module. A pose regression network is subsequently trained to estimate the camera’s position and orientation based on the fused representation. Our experimental results on diverse urban datasets demonstrate that VIFPE significantly outperforms conventional methods in terms of both accuracy and robustness, particularly under challenging lighting conditions. This work underscores the potential of multimodal fusion for camera localization in large-scale urban environments and lays a foundation for future advancements in the field. Full article

► Show Figures

Figure 1

25 pages, 8078 KB

Open AccessArticle

Robust Sensorless Predictive Power Control of PWM Converters Using Adaptive Neural Network-Based Virtual Flux Estimation

by Noumidia Amoura, Adel Rahoui, Boussad Boukais, Koussaila Mesbah, Abdelhakim Saim and Azeddine Houari

Electronics 2025, 14(18), 3620; https://doi.org/10.3390/electronics14183620 - 12 Sep 2025

Abstract

The rapid evolution of modern power systems, driven by the large-scale integration of renewable energy sources and the emergence of smart grids, presents new challenges in maintaining grid stability, power quality, and control reliability. As critical interfacing elements, three-phase pulse width modulation (PWM) [...] Read more.

The rapid evolution of modern power systems, driven by the large-scale integration of renewable energy sources and the emergence of smart grids, presents new challenges in maintaining grid stability, power quality, and control reliability. As critical interfacing elements, three-phase pulse width modulation (PWM) converters must now ensure resilient and efficient operation under increasingly adverse and dynamic grid conditions. This paper proposes an adaptive neural network-based virtual flux (VF) estimator for sensorless predictive direct power control (PDPC) of PWM converters under nonideal grid voltage conditions. The proposed estimator is realized using an adaptive linear neuron (ADALINE) configured as a quadrature signal generator, offering robustness against grid voltage disturbances such as voltage unbalance, DC offset and harmonic distortion. In parallel, a PDPC scheme based on the extended pq theory is developed to reject active-power oscillations and to maintain near-sinusoidal grid currents under unbalanced conditions. The resulting VF-based PDPC (VF-PDPC) strategy is validated via real-time simulations on the OPAL-RT platform. Comparative analysis confirms that the ADALINE-based estimator surpasses conventional VF estimation techniques. Moreover, the VF-PDPC achieves superior performance over conventional PDPC and extended pq theory-based PDPC strategies, both of which rely on physical voltage sensors, confirming its robustness and effectiveness under non-ideal grid conditions. Full article

(This article belongs to the Special Issue Section Collection Series: New Horizons and Recent Advances in Power Electronics)

► Show Figures

Figure 1

37 pages, 3014 KB

Open AccessArticle

Research on a Multi-Objective Optimal Scheduling Method for Microgrids Based on the Tuned Dung Beetle Optimization Algorithm

by Zishuo Liu and Rongmei Liu

Electronics 2025, 14(18), 3619; https://doi.org/10.3390/electronics14183619 - 12 Sep 2025

Abstract

With the increasing penetration of renewable energy in power systems, the multi-objective optimal scheduling of microgrids has become increasingly complex. Traditional optimization methods face limitations when addressing high-dimensional, nonlinear, and multi-constrained models. This study proposes a multi-objective optimal scheduling method for microgrids based [...] Read more.

With the increasing penetration of renewable energy in power systems, the multi-objective optimal scheduling of microgrids has become increasingly complex. Traditional optimization methods face limitations when addressing high-dimensional, nonlinear, and multi-constrained models. This study proposes a multi-objective optimal scheduling method for microgrids based on the Tuned Dung Beetle Optimization (TDBO) algorithm, aiming to simultaneously minimize operational and environmental costs while satisfying a variety of physical and engineering constraints. The proposed TDBO algorithm integrates multiple strategic mechanisms—including task allocation, spiral search, Lévy flight, opposition-based learning, and Gaussian perturbation—to significantly enhance global exploration and local exploitation capabilities. On the modeling side, a high-dimensional decision-making model is developed, encompassing photovoltaic systems, wind turbines, diesel generators, gas turbines, energy storage systems, and grid interaction. A dual-objective scheduling framework is constructed, incorporating operational economics, environmental sustainability, and physical constraints of the equipment. Simulation experiments conducted under typical scenarios demonstrate that TDBO outperforms both the improved particle swarm optimization (IPSO) and the original DBO in terms of solution quality, convergence speed, and result stability. Simulation results demonstrate that, compared with benchmark algorithms, the proposed TDBO achieves a 2.24–6.18% reduction in average total cost, improves convergence speed by 27.3%, and decreases solution standard deviation by 18.8–23.5%. These quantitative results highlight the superior optimization accuracy, efficiency, and robustness of TDBO in multi-objective microgrid scheduling. The results confirm that the proposed method can effectively improve renewable energy utilization and reduce system operating costs and carbon emissions, and holds significant theoretical value and engineering application potential. Full article

► Show Figures

Figure 1

22 pages, 7476 KB

Open AccessArticle

Neural Network for Robotic Control and Security in Resistant Settings

by Kubra Kose, Nuri Alperen Kose and Fan Liang

Electronics 2025, 14(18), 3618; https://doi.org/10.3390/electronics14183618 - 12 Sep 2025

Abstract

As the industrial automation landscape advances, the integration of sophisticated perception and manipulation technologies into robotic systems has become crucial for enhancing operational efficiency and precision. This paper presents a significant enhancement to a robotic system by incorporating the Mask R-CNN deep learning [...] Read more.

As the industrial automation landscape advances, the integration of sophisticated perception and manipulation technologies into robotic systems has become crucial for enhancing operational efficiency and precision. This paper presents a significant enhancement to a robotic system by incorporating the Mask R-CNN deep learning algorithm and the Intel^® RealSense™ D435 camera with the UFactory xArm 5 robotic arm. The Mask R-CNN algorithm, known for its powerful object detection and segmentation capabilities, combined with the depth-sensing features of the D435, enables the robotic system to perform complex tasks with high accuracy. This integration facilitates the detection, manipulation, and precise placement of single objects, achieving 98% detection accuracy, 98% gripping accuracy, and 100% transport accuracy, resulting in a peak manipulation accuracy of 99%. Experimental evaluations demonstrate a 20% improvement in manipulation success rates with the incorporation of depth data, reflecting significant enhancements in operational flexibility and efficiency. Additionally, the system was evaluated under adversarial conditions where structured noise was introduced to test its stability, leading to only a minor reduction in performance. Furthermore, this study delves into cybersecurity concerns pertinent to robotic systems, addressing vulnerabilities such as physical attacks, network breaches, and operating system exploits. The study also addresses specific threats, including sabotage and service disruptions, and emphasizes the importance of implementing comprehensive cybersecurity measures to protect advanced robotic systems in manufacturing environments. To ensure truly robust, secure, and reliable robotic operations in industrial environments, this paper highlights the critical role of international cybersecurity standards and safety standards for the physical protection of industrial robot applications and their human operators. Full article

(This article belongs to the Special Issue Parallel and Distributed Computing Systems: Current Trends and Future Prospects)

► Show Figures

Figure 1

22 pages, 1308 KB

Open AccessArticle

Capacitor-Less LDO with Fast Transient Response Implemented via Bulk-Driven Technique

by Yuxin Li, Shijindian Tang, Xiao Zhao and Yanlong Liu

Electronics 2025, 14(18), 3617; https://doi.org/10.3390/electronics14183617 - 12 Sep 2025

Abstract

Improving the transient response performance is a critical challenge in low-dropout regulator (LDO) design. This paper proposes a novel on-chip capacitor-less LDO based on substrate technology implemented in an SMIC (Semiconductor Manufacturing International Corporation) 0.18 μm CMOS (complementary metal oxide semiconductor technology) process. [...] Read more.

Improving the transient response performance is a critical challenge in low-dropout regulator (LDO) design. This paper proposes a novel on-chip capacitor-less LDO based on substrate technology implemented in an SMIC (Semiconductor Manufacturing International Corporation) 0.18 μm CMOS (complementary metal oxide semiconductor technology) process. Central to this innovation is a fast response loop between the PMOS driver’s body and gate, which leverages the body effect to enhance driver control without complex bulk-driven techniques. The proposed LDO achieves a quiescent current of 4.5 μA, an efficiency of

88 %

, an overshoot/undershoot of

12 mV / 22 mV

, and a settling time of 1.2 μs. The comparative analysis confirms that this structure increases the maximum load current and reduces the loop response time relative to those for conventional LDOs. These results validate a significant improvement in the transient performance, marking an important advance in integrated voltage regulator technology. Full article

(This article belongs to the Special Issue Advances in Analog and RF Circuit Design)

► Show Figures

Figure 1

21 pages, 1506 KB

Open AccessArticle

GEO Spiral Cruising Orbit Design Using Relative Orbit Elements

by Zhiyong Liu, Sihang Zhang, Jianli Su and Xiaoshuai Ma

Electronics 2025, 14(18), 3616; https://doi.org/10.3390/electronics14183616 - 12 Sep 2025

Abstract

A new method of round-trip spiral cruising orbit design for GEO object surveillance is proposed using relative orbit elements (ROEs). The relationship between the in-plane configuration of spiral cruising orbits and ROEs is described. After that, in-plane impulse control strategies are shown for [...] Read more.

A new method of round-trip spiral cruising orbit design for GEO object surveillance is proposed using relative orbit elements (ROEs). The relationship between the in-plane configuration of spiral cruising orbits and ROEs is described. After that, in-plane impulse control strategies are shown for round-trip spiral cruising orbits, based on the relative motion control laws. Along-track maneuvers are performed on both sides of the cruise region in the strategies. Finally, the impulse control strategies are simulated, and the required velocity increment and performance of the cruising orbit are analyzed. The results indicate that the proposed configuration and control strategies are effective for round-trip spiral cruising orbit design. The required velocity impulse increases with cruising velocity while being free from the cruising period. Only a few velocity increments are needed for closely observing objects in the cruise region multiple times. Full article

(This article belongs to the Special Issue Constellation Satellite Design and Application)

► Show Figures

Figure 1

20 pages, 1420 KB

Open AccessArticle

Research on an Improved YOLOv8 Algorithm for Water Surface Object Detection

by Wenliang Zhu and Ruidong Xu

Electronics 2025, 14(18), 3615; https://doi.org/10.3390/electronics14183615 - 11 Sep 2025

Abstract

To improve the accuracy of water surface debris detection under complex backgrounds and strong reflection conditions, this paper proposes a lightweight improved object detection algorithm based on YOLOv8n. Since shallow features are most sensitive to low-level visual interference such as water surface reflections, [...] Read more.

To improve the accuracy of water surface debris detection under complex backgrounds and strong reflection conditions, this paper proposes a lightweight improved object detection algorithm based on YOLOv8n. Since shallow features are most sensitive to low-level visual interference such as water surface reflections, this paper adopts the C2f_RFAConv module to enhance the model’s robustness to reflection interference regions. By adopting the Four-Detect-Adaptively Spatial Feature Fusion (ASFF) module, the model’s perception capabilities for objects of different scales (especially small objects) are improved. To avoid excessive computational complexity caused by the addition of new components, this paper adopts the lightweight Slim-neck structure. The Minimum Point Distance Intersection over Union (MPDIoU) loss function effectively improves the localization accuracy of detected objects by directly minimizing the Euclidean distance between the predicted bounding box and the ground truth bounding box. Experiments conducted on the publicly available water surface debris dataset provided by the Roboflow Universe platform show that the proposed method achieves 94.5% and 58.6% on the mAP@0.5 and mAP@0.5:0.95 metrics, respectively, representing improvements of 2.27% and 5.21% over the original YOLOv8 model. Full article

20 pages, 4356 KB

Open AccessArticle

Output Filtering Capacitor Bank Monitoring for a DC–DC Buck Converter

by Dadiana-Valeria Căiman, Corneliu Bărbulescu, Sorin Nanu and Toma-Leonida Dragomir

Electronics 2025, 14(18), 3614; https://doi.org/10.3390/electronics14183614 - 11 Sep 2025

Abstract

The remote prognostic, diagnosis, and maintenance of electrolytic capacitors are research topics of interest due to their presence in numerous electronic devices and their increased susceptibility to degradation over time. The authors’ focus in this article is on the proposal of a new [...] Read more.

The remote prognostic, diagnosis, and maintenance of electrolytic capacitors are research topics of interest due to their presence in numerous electronic devices and their increased susceptibility to degradation over time. The authors’ focus in this article is on the proposal of a new diagram for monitoring the parameters of the capacitors that compose the filter bank of a DC–DC buck converter by connecting them in parallel. Each capacitor is modeled by an equivalent series R–C circuit composed of an equivalent capacitance and an equivalent series resistance (ESR). The method used allows successive investigation of the three capacitors that compose the bank by triggering discharge/charge sequences, acquiring the voltages at the capacitor terminals, and estimating the time constants of each capacitor using a parameter observer. During the estimation of the parameters of a capacitor, the converter uses the other two capacitors maintained in operation. The monitoring cycle of all capacitors of the bank lasts less than

40 m s

, not significantly affecting the operation of the converter. The study undertaken is correlated with the thermal map of the board on which the converter is made. The dispersion of the measured values of the equivalent capacitances is below

0.25 %

, and of the ESR below

2.6 %

. The major advantage of the method is that the monitoring is performed online and in real time. Full article

(This article belongs to the Special Issue New Insights in Power Electronics: Prospects and Challenges)

► Show Figures

Figure 1

12 pages, 542 KB

Open AccessArticle

Expensive Highly Constrained Antenna Design Using Surrogate-Assisted Evolutionary Optimization

by Caie Hu, Sanyou Zeng and Changhe Li

Electronics 2025, 14(18), 3613; https://doi.org/10.3390/electronics14183613 - 11 Sep 2025

Abstract

Antenna structure design constitutes a computationally expensive optimization problem due to the requirement for full-wave electromagnetic (EM) simulations. Surrogate-assisted evolutionary algorithms offer a promising approach for addressing such challenges. However, several challenges remain in solving expensive, highly constrained antenna design problems. This paper [...] Read more.

Antenna structure design constitutes a computationally expensive optimization problem due to the requirement for full-wave electromagnetic (EM) simulations. Surrogate-assisted evolutionary algorithms offer a promising approach for addressing such challenges. However, several challenges remain in solving expensive, highly constrained antenna design problems. This paper introduces a surrogate-assisted dynamic constrained multi-objective evolutionary algorithm framework to tackle expensive and highly constrained antenna design optimization tasks. A multi-layer perceptron (MLP) is employed as the surrogate model to approximate EM evaluations and alleviate the computational burden, while a dynamic scale-constrained boundary strategy is implemented to handle highly constraints. The effectiveness of the proposed method is validated on a set of constrained benchmark problems and two antenna design cases. Full article

(This article belongs to the Special Issue Advances in Intelligent Wireless Communications: AI, Optimization, and Beyond)

► Show Figures

Figure 1

21 pages, 1784 KB

Open AccessArticle

Short-Term Photovoltaic Power Prediction Model Based on Variational Modal Decomposition and Improved RIME Optimization Algorithm

by Lingling Xie, Long Li, Xiaoping Xiong, Jiajia Cai, Hanzhong Cui and Haoyuan Li

Electronics 2025, 14(18), 3612; https://doi.org/10.3390/electronics14183612 - 11 Sep 2025

Abstract

Photovoltaic (PV) power generation is highly stochastic and volatile, a trait that presents a notable challenge to the prediction accuracy of distributed PV systems. To address this challenge, this study proposes a short-term photovoltaic power prediction strategy that integrates variational modal decomposition (VMD) [...] Read more.

Photovoltaic (PV) power generation is highly stochastic and volatile, a trait that presents a notable challenge to the prediction accuracy of distributed PV systems. To address this challenge, this study proposes a short-term photovoltaic power prediction strategy that integrates variational modal decomposition (VMD) for feature extraction with an improved RIME (IRIME) optimization algorithm for parameter optimization. Firstly, the raw PV power data are split into several intrinsic mode functions (IMFs) using VMD. The decomposed IMFs are reconstructed by using the sample entropy (SE) method, and a new subsequence with enhanced features is obtained. Secondly, a bidirectional gated recurrent unit (BIGRU) prediction model is established, and its structural parameters are optimized by the IRIME algorithm. Finally, the prediction results of each subsequence are summarized to obtain the final prediction value. Information from a centralized PV power station located in southern China is employed to verify the suggested prediction model. Experimental findings indicate that in comparison with other models, the proposed model achieves the smallest PV power prediction error; the mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE) of the proposed model are reduced at least by 21.95%, 3.03%, and 12.33%, respectively. The coefficient of determination (R²) is increased at least by 10.56‰. The method presented in this research is capable of improving prediction accuracy efficiently and holds specific engineering practicality. Full article

23 pages, 8508 KB

Open AccessArticle

A Short-Term User-Side Load Forecasting Method Based on the MCPO-VMD-FDFE Decomposition-Enhanced Framework

by Yu Du, Jiaju Shi, Xun Dou and Yu He

Electronics 2025, 14(18), 3611; https://doi.org/10.3390/electronics14183611 - 11 Sep 2025

Abstract

With the transition of the energy structure and the continuous development of smart grids, short-term user-side load forecasting plays a key role in fine power dispatch and efficient system operation. However, existing parameter optimization methods lack multi-dimensional and physically interpretable fitness evaluation. They [...] Read more.

With the transition of the energy structure and the continuous development of smart grids, short-term user-side load forecasting plays a key role in fine power dispatch and efficient system operation. However, existing parameter optimization methods lack multi-dimensional and physically interpretable fitness evaluation. They also fail to fully exploit frequency-domain features of decomposed modal components. These limitations reduce model accuracy and robustness in complex scenarios. To address this issue, this paper proposes a short-term user-side load forecasting method based on the MCPO-VMD-FDFE decomposition-enhanced framework. Firstly, a multi-dimensional fitness function is designed using indicators such as modal energy entropy and energy concentration. The Crested Porcupine Optimizer with Multidimensional Fitness Function (MCPO) algorithm is applied in VMD (Variational Mode Decomposition) to optimize the number of decomposition modes (K) and the penalty factor (α), thereby improving decomposition quality. Secondly, each IMF component obtained from VMD is analyzed by FFT. Key frequency components are selectively enhanced based on adaptive thresholds and weight coefficients to improve feature expression. Finally, a multi-scale convolution module is added to the PatchTST model to enhance its ability to capture local and multi-scale temporal features. The enhanced IMF components are fed into the improved model for prediction, and the final output is obtained by aggregating the results of all components. Experimental results show that the proposed method achieves the best performance on user-side load datasets for weekdays, Saturdays, and Sundays. The RMSE is reduced by 45.65% overall, confirming the effectiveness of the proposed approach in short-term user-side load forecasting tasks. Full article

(This article belongs to the Special Issue Feature Papers in Artificial Intelligence)

► Show Figures

Figure 1

23 pages, 27054 KB

Open AccessArticle

ActionMamba: Action Spatial–Temporal Aggregation Network Based on Mamba and GCN for Skeleton-Based Action Recognition

by Jinglong Wen, Dan Liu and Bin Zheng

Electronics 2025, 14(18), 3610; https://doi.org/10.3390/electronics14183610 - 11 Sep 2025

Abstract

Skeleton-based action recognition networks have widely adopted the approach of Graph Convolutional Networks (GCN) due to their superior capabilities in modeling data topology, but several key issues still require further investigation. Firstly, the graph convolutional network extracts action features by applying temporal convolution [...] Read more.

Skeleton-based action recognition networks have widely adopted the approach of Graph Convolutional Networks (GCN) due to their superior capabilities in modeling data topology, but several key issues still require further investigation. Firstly, the graph convolutional network extracts action features by applying temporal convolution to each key point, which causes the model to ignore the temporal connections between different important points. Secondly, the local receptive field of graph convolutional networks limits their ability to capture correlations between non-adjacent joints. Motivated by the State Space Model (SSM), we propose an Action Spatio-temporal Aggregation Network, named ActionMamba. Specifically, we introduce a novel embedding module called the Action Characteristic Encoder (ACE), which enhances the coupling of temporal and spatial information in skeletal features by combining intrinsic spatio-temporal encoding with extrinsic space encoding. Additionally, we design an Action Perception Model (APM) based on Mamba and GCN. By effectively combining the excellent feature processing capabilities of GCN with the outstanding global information modeling capabilities of Mamba, APM is able to comprehend the hidden features between different joints and selectively filter information from various joints. Extensive experimental results demonstrate that ActionMamba achieves highly competitive performance on three challenging benchmark datasets: NTU-RGB+D 60, NTU-RGB+D 120, and UAV–Human. Full article

(This article belongs to the Special Issue Advances in Image Recognition, Image Segmentation, Image Fusion, and Singal Processing)

► Show Figures

Figure 1

23 pages, 1764 KB

Open AccessArticle

Parallelization of the Koopman Operator Based on CUDA and Its Application in Multidimensional Flight Trajectory Prediction

by Jing Lu, Lulu Wang and Zeyi Shang

Electronics 2025, 14(18), 3609; https://doi.org/10.3390/electronics14183609 - 11 Sep 2025

Abstract

This paper introduces a parallelized approach to reconstruct Koopman computational graphs from the perspective of parallel computing to address the computational efficiency bottleneck in approximating Koopman operators within high-dimensional spaces. We propose the KPA (Koopman Parallel Accelerator), a parallelized algorithm that restructures the [...] Read more.

This paper introduces a parallelized approach to reconstruct Koopman computational graphs from the perspective of parallel computing to address the computational efficiency bottleneck in approximating Koopman operators within high-dimensional spaces. We propose the KPA (Koopman Parallel Accelerator), a parallelized algorithm that restructures the Koopman computational workflow to transform sequential time-step computations into parallel tasks. KPA leverages GPU parallelism to improve execution efficiency without compromising model accuracy. To validate the algorithm’s effectiveness, we apply KPA to a flight trajectory prediction scenario based on the Koopman operator. Within the CUDA kernel implementation of KPA, several optimization techniques—such as shared memory, tiling, double buffering, and data prefetching—are employed. We compare our implementation against two baselines: the original Koopman neural operator for trajectory prediction implemented in TensorFlow (TF-baseline) and its XLA-compiled variant (TF-XLA). The experimental results demonstrate that KPA achieves a 2.47× speed up over TF-baseline and a 1.09× improvement over TF-XLA when predicting a 1422-dimensional flight trajectory. Additionally, an ablation study on block size and the number of streaming multiprocessors (SMs) reveals that the best performance is obtained with the block size of 16 × 16 and SM = 8. The results demonstrate that KPA can significantly accelerate Koopman operator computations, making it suitable for high-dimensional, large-scale, or real-time applications. Full article

► Show Figures

Figure 1

Journal Description

Electronics

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI