Search Results (576)

This paper presents a novel speed controller design for a brushless DC motor (BLDCM) operating under field-oriented control (FOC). The proposed speed controller is developed by integrating the zebra optimization algorithm (ZOA) with sliding mode theory (SMT). In this approach, the parameter ranges of the sliding mode dynamic trajectory control gain, exponential reaching gain, and constant speed reaching gain—three key components of the exponential reaching law-based sliding mode controller (ERLSMC)—are defined as the research space for the ZOA. The feedback speed error and its rate of change are used as features to calculate the fitness value. Subsequently, the fitness value computed by the algorithm is compared with the current best fitness value to determine the optimal position coordinates. These coordinates correspond to the optimal set of gain parameters for the sliding mode speed controller. During the operation of the BLDCM, these optimized parameters are applied to the controller in real time. This enables the system to adjust the three gain parameters dynamically under different operating conditions, thereby reducing the overshoot commonly induced by the ERLSMC. As a result, the speed response of the BLDCM drive system can more accurately and rapidly track the speed command. Therefore, the proposed control strategy is not only characterized by a small number of parameters and ease of tuning, but also does not require large datasets for training, making it highly practical and easy to implement. Finally, the proposed control strategy is simulated using Matlab/Simulink (2024b version) and applied to the BLDCM drive system for experimental testing. Its performance is compared against three types of sliding mode controllers employing different reaching laws: the constant speed reaching law, the exponential reaching law, and the exponential reaching law combined with extension theory (ET). Simulation and experimental results confirm that the proposed novel speed controller outperforms the other three sliding mode controllers based on different reaching laws, both in terms of speed command tracking and load regulation response. Full article

In crab pond environments, obstacles such as long aerobic pipelines, aerators, and ground cages are usually sparsely distributed. Automatic feeding boats can navigate while avoiding obstacles and execute feeding tasks along planned paths, thus improving feeding quality and operational efficiency. In large-scale crab pond farming, a single feeding operation often fails to achieve the complete coverage of the bait casting task due to the limited boat load. Therefore, this study proposes a multi-voyage path planning scheme for feeding boats. Firstly, a complete coverage path planning algorithm is proposed based on an improved genetic algorithm to achieve the complete coverage of the bait casting task. Secondly, to address the issue of an insufficient bait loading capacity in complete coverage operations, which requires the feeding boat to return to the loading wharf several times to replenish bait, a multi-voyage path planning algorithm is proposed. The return point of the feeding operation is predicted by the algorithm. Subsequently, the improved Q-Learning algorithm (I-QLA) is proposed to plan the optimal multi-voyage return paths by increasing the exploration of the diagonal direction, refining the reward mechanism and dynamically adjusting the exploration rate. The simulation results show that compared with the traditional genetic algorithm, the repetition rate, path length, and the number of 90° turns of the complete coverage path planned by the improved genetic algorithm are reduced by 59.62%, 1.27%, and 28%, respectively. Compared with the traditional Q-Learning algorithm, average path length, average number of turns, average training time, and average number of iterations planned by the I-QLA are reduced by 20.84%, 74.19%, 48.27%, and 45.08%, respectively. The crab pond experimental results show that compared with the Q-Learning algorithm, the path length, turning times, and energy consumption of the I-QLA algorithm are reduced by 29.7%, 77.8%, and 39.6%, respectively. This multi-voyage method enables efficient, low-energy, and precise feeding for crab farming. Full article

Objectives: This study investigates the biomechanics of the bench press and overhead press exercises by modeling the trunk and upper limbs as a kinematic chain of rigid links connected by revolute joints and actuated by single- and two-joint muscles, with motion constrained by the barbell. The aims were to (i) assess the different contributions of shoulder and elbow torques during lifting, (ii) identify the parameters influencing joint loads, (iii) explain the origin of the sticking region, and (iv) validate the model against experimental barbell kinematics. Methods: Equations of motion and joint reaction forces were derived analytically in closed form. Dynamic simulations produced vertical barbell velocity profiles under various conditions. A waveform similarity analysis was used to compare simulated profiles with experimental data from maximal bench press trials. Results: The sticking region occurred when shoulder torque dropped below a critical threshold, resulting in a local velocity minimum. Adding elbow torque reduced this dip and shifted the velocity minimum from 38 cm to 23 cm above the chest, although it prolonged the time needed to overcome it. Static analysis revealed that grip width and barbell constraint had a greater effect on shaping the sticking region than muscle architecture parameters. Elbow extensors contributed minimally during early lift phases but became dominant near full extension. Model predictions showed high similarity to experimental data in the pre-sticking (SI = 0.962, p = 0.028) and sticking (SI = 0.949, p = 0.014) phases, with reduced, non-significant similarity post-sticking (SI = 0.881, p > 0.05) due to the assumption of constant torques. Conclusions: The model offers biomechanical insight into how joint torques and barbell constraints shape movement. The findings support training strategies that target shoulder strength early in the lift and elbow strength near lockout to minimize sticking and improve performance. Full article

Industry 4.0 has intensified the skills gap in industrial automation education, with graduates requiring extended on boarding periods and supplementary training investments averaging USD 11,500 per engineer. This paper introduces VisFactory, a multimedia learning system that extends the cognitive theory of multimedia learning by incorporating haptic feedback as a third processing channel alongside visual and auditory modalities. The system integrates a digital twin architecture with ultra-low latency synchronization (12.3 ms) across all sensory channels, a dynamic feedback orchestration algorithm that distributes information optimally across modalities, and a tripartite student model that continuously calibrates instruction parameters. We evaluated the system through a controlled experiment with 127 engineering students randomly assigned to experimental and control groups, with assessments conducted immediately and at three-month and six-month intervals. VisFactory significantly enhanced learning outcomes across multiple dimensions: 37% reduction in time to mastery (t(125) = 11.83, p < 0.001, d = 2.11), skill acquisition increased from 28% to 85% (${\eta }_p^2=0.54$), and 28% higher knowledge retention after six months. The multimodal approach demonstrated differential effectiveness across learning tasks, with haptic feedback providing the most significant benefit for procedural skills (52% error reduction) and visual–auditory integration proving most effective for conceptual understanding (49% improvement). The adaptive modality orchestration reduced cognitive load by 43% compared to unimodal interfaces. This research advances multimedia learning theory by validating tri-modal integration effectiveness and establishing quantitative benchmarks for sensory channel synchronization. The findings provide a theoretical framework and implementation guidelines for optimizing multimedia learning environments for complex skill development in technical domains. Full article

Astringency, a complex oral sensation resulting from interactions between mucin and polyphenols, remains difficult to quantify in portable field settings. Therefore, quantifying the aggregation through interactions can enable the classification of the astringency intensity, and assessing the capillary action driven by the surface tension offers an effective approach for this purpose. This study successfully replicates tannic acid (TA)–mucin aggregation on a paper-based microfluidic chip and utilizes machine learning (ML) to analyze the resulting capillary flow dynamics. Aggregates formed by mixing mucin with TA solutions at three concentrations showed that higher TA levels led to greater aggregation, consequently reducing the capillary flow rates. The flow dynamics were consistently recorded using a smartphone mounted within a custom 3D-printed frame equipped with a motorized sample loading system, ensuring standardized experimental conditions. Among eight trained ML models, the support vector machine (SVM) demonstrated the highest classification accuracy at 95.2% in distinguishing the astringency intensity levels. Furthermore, fitting the flow data to a theoretical capillary flow equation allowed for the extraction of a single coefficient as an input feature, which achieved comparable classification performance, validating the simplified feature extraction strategy. This method was also feasible even with only a portion of the initial data. This approach is simple and cost-effective and can potentially be developed into a portable system, making it useful for field analysis of various liquid samples. Full article

Buildings are significant contributors to global energy consumption and greenhouse gas emissions, with air conditioning systems representing a large share of this demand. Multi-building cooperative energy management is a promising solution for improving energy efficiency, but traditional control methods often struggle with dynamic environments and complex interactions. This study proposes an enhanced Soft Actor–Critic (SAC) algorithm, termed ORAR-SAC, to address these challenges in building cluster energy management. The ORAR-SAC integrates an Ordered Reward-based Experience Replay mechanism to prioritize high-value samples, improving data utilization and accelerating policy convergence. Additionally, an adaptive temperature parameter regularization strategy is implemented to balance exploration and exploitation dynamically, enhancing training stability and policy robustness. Using the CityLearn simulation platform, the proposed method is evaluated on a cluster of three commercial buildings in Beijing under time-of-use electricity pricing. Results demonstrate that ORAR-SAC outperforms conventional rule-based and standard SAC strategies, achieving reductions of up to 11% in electricity costs, 7% in peak demand, and 3.5% in carbon emissions while smoothing load profiles and improving grid compatibility. These findings highlight the potential of ORAR-SAC to support intelligent, low-carbon building energy systems and advance sustainable urban energy management. Full article

The progression of content during the training and development of young athletes is essential, while considering the developmental stages of the students/athletes. Therefore, it is crucial to monitor training sessions to ensure that content progression is followed and to assess how it is implemented. The aim of this study was to analyze the associations between different male categories of sports development in basketball through pedagogical variables and external loads planned by the coaches. The sample consisted of 148 sessions and 896 tasks, and the SIATE tool was used to observe both the pedagogical variables and the primary external load variables. Significant differences were observed primarily in the U16 category compared to the U12 and U14 categories. In examining the pedagogical variables, three key aspects were highlighted: content type, training methods, and level of opposition. The external load variables were aligned with the pedagogical variables, suggesting a progression of content. This indicates that instruction should follow an order, in which tactical load evolves from the simplest to the most complex, in accordance with the development and training stage of the students/athletes. The analyzed male basketball team demonstrated a content progression focused on the comprehensive development of the student/athlete, encouraging decision-making, and creating a complex, unpredictable, and random environment that closely resembles the dynamics of the real game. Full article

Background/Objectives: Maintaining proper posture and preventing musculoskeletal pain are essential for the healthy development of young football players. Contemporary concepts of postural control emphasize the importance of the lumbopelvic-hip complex and the activation of deep trunk muscles. This study aimed to evaluate the effects of a structured core stabilization training program on postural parameters and pain reduction in young football players. Methods: A total of 182 male football players, aged 9–15 years, were enrolled and allocated to either the intervention or control group. The 12-week intervention consisted of exercises targeting both local and global trunk stabilizers. Assessments included measurements of spinal curvatures, trunk rotation angles, lower limb loading symmetry, and postural stability using the TMX-127 digital inclinometer (Saunders Group Inc., Chaska, MN, USA) and the Baseline scoliometer (Fabrication Enterprises, Inc. New York, USA). Pain intensity was measured using the Visual Analogue Scale (VAS). Repeated-measures statistical analyses were performed with a significance level set at p ≤ 0.05. Results: The intervention group showed significant improvements in trunk rotational parameters, with reductions in ATR values at C7/Th1 (−0.54°) and L5/S1 (−0.49°). SATR values decreased by −0.28° between the second and third assessments. Symmetry of lower limb loading under eyes-open conditions improved significantly (p < 0.00195). No significant changes were observed in dynamic balance, as assessed by the Y-Balance Test (p > 0.05). Pain intensity decreased from 3.33 to 2.55 on the VAS, reflecting a reduction of 0.78 points. Conclusions: Systematic core stabilization training enhances postural quality and reduces the occurrence and severity of musculoskeletal pain in young football players, with lasting effects—except for postural control under conditions of reduced visual input. This type of training represents an effective physioprophylactic strategy, supporting postural control and lowering the risk of injuries. To maintain these benefits, continued training that incorporates balance and proprioceptive exercises is recommended. Full article

Human Activity Recognition (HAR) using wearable sensors plays a critical role in applications such as healthcare, sports monitoring, and rehabilitation. Traditional approaches typically rely on centralized models that aggregate and process data from multiple sensors simultaneously. However, such architecture often suffers from high latency, increased communication overhead, limited scalability, and reduced robustness, particularly in dynamic environments where wearable systems operate under resource constraints. This paper proposes a distributed neural network framework for HAR, where each wearable sensor independently processes its data using a lightweight neural model and transmits high-level features or predictions to a central neural network for final classification. This strategy alleviates the computational load on the central node, reduces data transmission across the network, and enhances user privacy. We evaluated the proposed distributed framework using our publicly available multi-sensor HAR dataset and compared its performance against a centralized neural network trained on the same data. The results demonstrate that the distributed approach achieves comparable or superior classification accuracy while significantly lowering inference latency and energy consumption. These findings underscore the promise of distributed intelligence in wearable systems for real-time and energy-efficient human activity monitoring. Full article

Subway train operators face the risk of cumulative cognitive stress due to factors such as visual fatigue from prolonged high-speed tunnel driving, irregular shift patterns, and the monotony of automated operations. This can lead to cognitive decline and human error accidents. Current monitoring of cognitive stress risk predominantly relies on single-modal methods, which are susceptible to environmental interference and offer limited accuracy. This study proposes an intelligent multimodal framework for cognitive stress monitoring by leveraging the symmetry principles in physiological and behavioral manifestations. The symmetry of photoplethysmography (PPG) waveforms and the bilateral symmetry of head movements serve as critical indicators reflecting autonomic nervous system homeostasis and cognitive load. By integrating these symmetry-based features, this study constructs a spatiotemporal dynamic feature set through fusing physiological signals such as PPG and galvanic skin response (GSR) with head and facial behavioral features. Furthermore, leveraging deep learning techniques, a hybrid PSO-CNN-GRU-Attention model is developed. Within this model, the Particle Swarm Optimization (PSO) algorithm dynamically adjusts hyperparameters, and an attention mechanism is introduced to weight multimodal features, enabling precise assessment of cognitive stress states. Experiments were conducted using a full-scale subway driving simulator, collecting data from 50 operators to validate the model’s feasibility. Results demonstrate that the complementary nature of multimodal physiological signals and behavioral features effectively overcomes the limitations of single-modal data, yielding significantly superior model performance. The PSO-CNN-GRU-Attention model achieved a predictive coefficient of determination (R²) of 0.89029 and a mean squared error (MSE) of 0.00461, outperforming the traditional BiLSTM model by approximately 22%. This research provides a high-accuracy, non-invasive solution for detecting cognitive stress in subway operators, offering a scientific basis for occupational health management and the formulation of safe driving intervention strategies. Full article

Blueberries are valued for their flavor and health benefits, but inconsistent ripeness at harvest complicates post-harvest food processing such as sorting and quality control. To address this, we propose a lightweight convolutional neural network (CNN) to detect blueberry ripeness in complex field environments, supporting efficient and automated food processing workflows. To meet the low-power and low-resource demands of embedded systems used in smart processing lines, we introduce a Grouped Large Kernel Reparameterization (GLKRep) module. This design reduces computational cost while enhancing the model’s ability to recognize ripe blueberries under complex lighting and background conditions. We also propose a Unified Adaptive Multi-Scale Fusion (UMSF) detection head that adaptively integrates multi-scale features using a dynamic receptive field. This enables the model to detect blueberries of various sizes accurately, a common challenge in real-world harvests. During training, a Semantics-Aware IoU (SAIoU) loss function is used to improve the alignment between predicted and ground truth regions by emphasizing semantic consistency. The model achieves 98.1% accuracy with only 2.6M parameters, outperforming existing methods. Its high accuracy, compact size, and low computational load make it suitable for real-time deployment in embedded sorting and grading systems, bridging field detection and downstream food-processing tasks. Full article

Anterior cruciate ligament reconstruction (ACLR) results in prolonged muscle weakness, impaired neuromuscular control, and delayed return to sport. Cross-education (CE), unilateral training of the uninjured limb, has been proposed as an adjunct therapy to promote bilateral adaptations. This scoping review evaluated the functional and neuroplastic effects of CE rehabilitation post-ACLR. Following PRISMA-ScR and JBI guidelines, PubMed, Scopus, Web of Science, and PEDro were searched up to February 2025. A bibliometric analysis was also conducted to report keyword co-occurrence and identify trends in this line of research. Of 333 screened references, 14 studies (price index: 43% and low-to-moderate risk of bias) involving 721 participants (aged 17–45 years) met inclusion criteria. CE protocols (6–12 weeks; 2–5 sessions/week) incorporating isometric, concentric, and eccentric exercises demonstrated strength gains (10–31%) and strength preservation, alongside improved limb symmetry (5–14%) and dynamic balance (7–18%). There is growing interest in neuroplasticity and corticospinal excitability, although neuroplastic changes were assessed heterogeneously across studies. Findings support CE as a feasible and low-cost strategy to complement early-stage ACLR rehabilitation, especially when direct loading of the affected limb is limited. Standardized protocols for clinical intervention and neurophysiological assessment are needed. Full article

To address the inefficiency of traditional concrete crack detection methods and the heavy reliance of supervised learning on extensive labeled data, in this study, an intelligent assessment method of concrete damage based on pseudo-label semi-supervised learning and fractal geometry theory is proposed to solve two core tasks: one is binary classification of pixel-level cracks, and the other is multi-category assessment of damage state based on crack morphology. Using three-channel RGB images as input, a dual-path collaborative training framework based on U-Net encoder–decoder architecture is constructed, and a binary segmentation mask of the same size is output to achieve the accurate segmentation of cracks at the pixel level. By constructing a dual-path collaborative training framework and employing a dynamic pseudo-label refinement mechanism, the model achieves an F1-score of 0.883 using only 50% labeled data—a mere 1.3% decrease compared to the fully supervised benchmark DeepCrack (F1 = 0.896)—while reducing manual annotation costs by over 60%. Furthermore, a quantitative correlation model between crack fractal characteristics and structural damage severity is established by combining a U-Net segmentation network with the differential box-counting algorithm. The experimental results demonstrate that under a cyclic loading of 147.6–221.4 kN, the fractal dimension monotonically increases from 1.073 (moderate damage) to 1.189 (failure), with 100% accuracy in damage state identification, closely aligning with the degradation trend of macroscopic mechanical properties. In complex crack scenarios, the model attains a recall rate (Re = 0.882), surpassing U-Net by 13.9%, with significantly enhanced edge reconstruction precision. Compared with the mainstream models, this method effectively alleviates the problem of data annotation dependence through a semi-supervised strategy while maintaining high accuracy. It provides an efficient structural health monitoring solution for engineering practice, which is of great value to promote the application of intelligent detection technology in infrastructure operation and maintenance. Full article

The extended operation of high-speed railways has led to an increased incidence of tunnel lining defects, with falling debris posing a significant safety threat. Within tunnels, single-train passage and trains-crossing events constitute the most frequent operational scenarios, both generating extreme aerodynamic environments that alter debris trajectories from free fall. To systematically investigate the aerodynamic differences and underlying mechanisms governing falling debris behavior under these two distinct conditions, a three-dimensional computational fluid dynamics (CFD) model (debris–air–tunnel–train) was developed using an improved delayed detached eddy simulation (IDDES) turbulence model. Comparative analyses focused on the translational and rotational motions as well as the aerodynamic load coefficients of the debris in both single-train and trains-crossing scenarios. The mechanisms driving the changes in debris aerodynamic behavior are elucidated. Findings reveal that under single-train operation, falling debris travels a greater distance compared with trains-crossing conditions. Specifically, at train speeds ranging from 250–350 km/h, the average flight distances of falling debris in the X and Z directions under single-train conditions surpass those under trains crossing conditions by 10.3 and 5.5 times, respectively. At a train speed of 300 km/h, the impulse of C_Fx and C_Fz under single-train conditions is 8.6 and 4.5 times greater than under trains-crossing conditions, consequently leading to the observed reduction in flight distance. Under the conditions of trains crossing, the falling debris is situated between the two trains, and although the wind speed is low, the flow field exhibits instability. This is the primary factor contributing to the reduced flight distance of the falling debris. However, it also leads to more pronounced trajectory deviations and increased speed fluctuations under intersection conditions. The relative velocity (CRV) on the falling debris surface is diminished, resulting in smaller-scale vortex structures that are more numerous. Consequently, the aerodynamic load coefficient is reduced, while the fluctuation range experiences an increase. Full article

Rubber–textile conveyor belts are an important element of large-scale transport systems, which in many cases are subjected to excessive dynamic loads. Assessing the impact resistance of them is essential for ensuring their reliability and longevity. The article focuses on the use of machine learning methods as one of the approaches to the analysis and prediction of the impact resistance of rubber–textile conveyor belts. Based on the data obtained from the design properties of conveyor belts and experimental testing conditions, four models were created (regression model, decision tree regression model, random forest model, ANN model), which are used to analyze and predict the impact force of the force acting on the conveyor belt during material impact. Each model was trained on training data and validated on test data. The performance of each model was evaluated using standard metrics and model indicators. The results of the model analysis show that the most powerful model, ANN, explains up to 99.6% of the data variability. The second-best model is the random forest model and then the regression model. The least suitable choice for predicting the impact force is the regression tree. Full article