Search Results (851)

To address the problems of enhanced non-stationarity, significant feature distribution shift, and insufficient cross-condition generalization capability of traditional fault diagnosis methods under variable operating conditions such as varying speed and load, a rolling bearing fault diagnosis method integrating group sparse reconstruction and a multi-strategy improved quantum particle swarm optimization-based relevance vector machine (RVM) is proposed. First, group sparse representation learning is employed to reconstruct the original vibration signals, thereby suppressing background noise and enhancing fault-related impulsive components to improve signal separability and stability. Subsequently, a modal component selection criterion combining kurtosis and correlation coefficients is introduced to optimize and reconstruct the decomposed modal components, enabling the reconstructed signals to retain more fault-sensitive information. On this basis, multiple information entropy features are extracted from the reconstructed signals to construct high-dimensional state feature vectors for comprehensively characterizing the dynamic operating states of rolling bearings. To further enhance the parameter optimization capability, Chebyshev chaotic mapping is incorporated into the quantum particle swarm optimization (QPSO) algorithm to improve the uniformity of population initialization. Meanwhile, a Cauchy mutation strategy is introduced to strengthen the global search capability and avoid premature convergence, thereby forming a multi-strategy improved QPSO algorithm. Finally, the improved optimization algorithm is utilized to adaptively optimize the key hyperparameters of the RVM, resulting in a fault diagnosis model with high accuracy, strong generalization capability, and sparse characteristics. Experimental validation on the HUST and XJTU-SY bearing datasets demonstrates that the proposed MIQPSO-RVM framework achieves diagnostic accuracies of 96.70% and 94.83%, respectively. Compared with several representative intelligent diagnosis methods and deep learning models, the proposed method exhibits superior diagnostic performance, robustness, and generalization capability under complex operating conditions. Full article

While deep learning has significantly improved the accuracy of visual detection systems, the integration of process semantics with visual perception for industrial assembly tasks remains largely unexplored. This study aims to develop a high-accuracy cable connector detection framework that incorporates process knowledge to enhance feature discrimination under varying industrial imaging conditions. To achieve this goal, we build an enhanced Fully Convolutional One-Stage (FCOS) detector with a ConvNeXt V2 backbone and introduce a Process Feature Linear Modulation (PFNM) module. The proposed module adaptively modulates visual features using encoded process semantics, enabling the detector to align visual perception with assembly logic. Experiments conducted on an industrial connector dataset demonstrate that the proposed method achieves an mAP of 84.7%, outperforming representative state-of-the-art detectors including YOLOv11, RT-DETR, and DINO while maintaining an inference speed of 17.6 FPS. Ablation studies further show that each component contributes to progressive performance improvement, and the complete framework achieves a 5.5% AP gain over the ResNet-50 baseline. These results indicate that integrating process knowledge with visual feature learning effectively improves feature discrimination and provides a promising paradigm for process-aware perception in intelligent manufacturing. Full article

Accurately forecasting waypoint-level tropical cyclone (TC) intensity, defined as the local wind speed at specific maritime route waypoints under TC influence, is crucial for navigation safety and voyage planning. Conventional studies mainly focus on the central intensity of TC systems and underutilize the complementary value of multimodal meteorological data with inconsistent sampling intervals. To address these challenges, this study proposes a multimodal-augmented conditional diffusion model (MADiff) for waypoint-level TC intensity prediction. To exploit the potential of multimodal inputs, we first design a temporal-adaptive dynamic convolution module (TDConv) to capture multi-timescale features, mitigating multimodal sampling discrepancies without rigid temporal alignment. Second, we develop a discriminative cross-fusion module (DisCF) to aggregate multi-timescale features across diverse modalities, quantifying multimodal heterogeneity and integrating valuable modality-specific features while suppressing noise interference. Fused features are fed into a diffusion model with physics-informed regularization to generate final intensity forecasts. Extensive experiments on four Western North Pacific datasets show that MADiff achieves average MAE and RMSE values of 2.08 kt and 2.37 kt, respectively, for 12 h intensity forecasting. Compared with the state-of-the-art baseline (TC-Clouds-DP), MADiff yields substantial performance improvements, reducing MAE by 16.3% and RMSE by 10.6% on average. This study provides an effective framework for fine-grained TC intensity forecasting, offering valuable insights for extreme marine weather early warning and intelligent navigation decision-making. Full article

With the rapid evolution of next-generation mobile communications, semantic communication has emerged as an intelligent communication paradigm capable of surpassing the Shannon limit. A fundamental prerequisite for this paradigm is the synchronization of background knowledge between the transmitter and receiver, making the semantic knowledge base (SKB) a critical cornerstone. However, effectively selecting appropriate content from massive cloud-based knowledge repositories for edge deployment remains a significant challenge. This paper conducts systematic research to address the key issues in the flow deployment of SKBs at the edge, including insufficient adaptation to personalized preferences, inadequate timeliness management, and the complexity of multi-objective optimization. First, a comprehensive system model is constructed, integrating user preferences, knowledge relevance, transceiver matching degree, and the Age of Information (AOI). Second, the Generative Adversarial Network (GAN)-assisted Preference-based Reinforcement Learning (GaPbRL) algorithm is proposed. The experimental results demonstrate that this method outperforms traditional schemes in terms of knowledge-base hit rate, transceiver matching degree, and algorithm convergence speed, while significantly reducing the overhead of manual fine-tuning. This study provides a robust framework for the personalized and efficient cloud–edge collaborative deployment of SKBs. Full article

No-till precision seeding is an important component of conservation tillage, but stable operation remains constrained by compacted undisturbed soil, dense crop residues, and uneven field surfaces. This review examines the evolution of no-till precision seeding equipment from mechanical soil–residue interaction to cyber–physical closed-loop regulation. It first summarizes how soil resistance and residue interference affect furrow opening, seed placement, and seed–soil contact. It then examines the development of residue-management, furrow-opening, covering, and compaction mechanisms, highlighting the transition from passive structural optimization toward active and adaptive operation. Advances in multi-source sensing, electric-drive metering, downforce control, and vibration suppression are further reviewed as enabling technologies for improving seeding stability under variable and high-speed conditions. Despite these advances, persistent trade-offs remain among residue-removal capacity, soil disturbance, energy demand, component durability, system complexity, and operational stability. Emerging approaches based on digital twins, adaptive damping, and cooperative autonomous systems may support further improvements, but their practical implementation still requires robust field performance and effective system integration. Overall, no-till seeding equipment is progressing toward perception-assisted and closed-loop intelligent regulation while continuing to face important mechanical and implementation challenges. Full article

Coal–rock cutting state recognition is essential for adaptive cutting and intelligent speed regulation in shearers. To address the limited representational capability of individual signals, the confusion between adjacent gangue-bearing cutting conditions, and the domain discrepancy between simulation and experimental data, a vibration–current multimodal fusion method based on CORRECT-Net is proposed. First, an EDEM–RecurDyn–MATLAB/Simulink co-simulation system was developed to generate cutting records for four coal–rock states. After screening for physical equivalence and label conflicts, 158 valid records were retained and grouped into 150 physical-condition groups, which were partitioned at the group level into training, validation, and test sets. Subsequently, SincNet was employed to extract frequency-band-constrained features, a Transformer was used to model long-range temporal dependencies, and a residual importance-guided GATv2 module was introduced to perform cross-modal fusion of vibration-impact and current-load features. On 2500 test windows, CORRECT-Net achieved an accuracy of 96.20% ± 0.11%, a macro-F1 score of 95.14% ± 0.21%, and a hazardous-condition miss rate of 0.58% ± 0.13%. Compared with the multimodal 1D-CNN, TCN, and Bi-LSTM models, CORRECT-Net improved the accuracy by 8.80, 4.00, and 2.08 percentage points, respectively. In the progressive ablation study, the accuracy increased from 87.40% ± 0.26% to 96.20% ± 0.11%, while the macro-F1 score increased from 84.57% ± 0.34% to 95.14% ± 0.21%. Under Gaussian noise with a standard deviation of 0.05, the model retained an accuracy of 92.76% ± 0.24%. When the vibration and current modalities were separately unavailable, the corresponding accuracies were 86.56% ± 0.37% and 92.44% ± 0.25%, respectively. A five-fold simulation-to-experiment transfer evaluation was further conducted at the independent-run level using five experimental records per class. Without adaptation using experimental samples, the model achieved an accuracy of 91.33% ± 5.19%. When 20% and 50% of the experimental windows were used for adaptation, the accuracy increased to 96.33% ± 0.75% and 98.67% ± 1.39%, respectively. These results demonstrate that CORRECT-Net effectively integrates mechanical vibration responses and motor-load information and, under the present simulation and experimental conditions, achieves high recognition accuracy, a low hazardous-condition miss rate, and effective adaptability to the experimental domain. Full article

Fast synthetic aperture radar (SAR) imaging simulation is required by many computer vision applications. Although the Shooting and Bouncing Ray (SBR) method has significantly accelerated electric field calculation, the number of ray tubes is still the bottleneck for SAR image simulation speed. This paper proposes an innovative adaptive SBR method driven by Q-learning for accelerated SAR imaging simulation. The core strategy is to convert the ray tube allocation into a reinforcement learning problem. The ray-shooting plane is dynamically partitioned into localized patches, where a Q-learning agent intelligently scales the ray density in real time. By observing the geometric features of the target surface, the agent learns to employ coarser ray tubes in flat regions to eliminate redundant computation, while deploying denser ray tubes in complex areas. A multi-objective reward function is designed to balance accuracy against computational resource consumption. Numerical experiments demonstrate that the proposed Q-learning-based SBR method drastically reduces computational cost while preserving imaging similarity. Full article

With the rapid development of Industrial Internet-oriented smart energy systems, hydro-turbine generator units are increasingly monitored through networked sensors, industrial communication infrastructures, and edge/cloud-based condition-monitoring platforms. These Internet-connected monitoring environments provide abundant vibration data for intelligent operation and maintenance (O&M) but also introduce a challenging unsupervised cross-scenario diagnosis problem. Specifically, diagnostic models trained on labeled historical data may suffer severe performance degradation when deployed to unlabeled online data collected under different hydraulic conditions, rotational speeds, or operating conditions. Furthermore, existing domain adaptation methods, in their pursuit of distribution alignment, frequently overlook a critical bottleneck that limits generalization performance: inter-class entanglement. Specifically, under intense hydraulic background noise and cross-condition distribution shifts, features belonging to distinct fault types are highly susceptible to aliasing within the feature space. To overcome these issues, this paper proposes a Conditional Wasserstein Adversarial Network with Bi-level Prototype Disentanglement Regularization (CWAN-BPDR). First, a Conditional Wasserstein Adversarial Network (CWAN) is constructed by combining the smooth-gradient property of Wasserstein distance with conditional adversarial alignment, thereby achieving stable and fine-grained category-level domain adaptation. Furthermore, to alleviate the inter-class entanglement problem that may arise during cross-domain alignment, a Bi-level Prototype Disentanglement Regularization (BPDR) term is designed. By jointly implementing source–target prototype alignment and prototype–feature bidirectional alignment, BPDR explicitly suppresses inter-class confusion and enhances intra-class compactness and inter-class separability in the feature space. Experimental results on the JNU and NEFU datasets demonstrate that CWAN-BPDR achieves average diagnostic accuracies of 97.82% and 98.99%, respectively, while significantly mitigating label entanglement in challenging cross-operating-condition tasks. These results indicate that the proposed method can effectively transfer diagnostic knowledge acquired from labeled historical operating conditions to unlabeled online monitoring data. It can therefore serve as an offline-trained diagnostic module for Industrial Internet of Things-based condition-monitoring platforms in hydropower systems. Full article

Unmanned Aerial Vehicles (UAVs) are used in numerous practical applications in industry, science, and ecology; however, the large-scale use of UAVs is hampered by the limited onboard energy capacity. Increasing the energy efficiency of UAVs has thus become one of the most important tasks in UAV research. This review examines approaches to energy optimization of UAVs using algorithms and artificial intelligence (AI). It evaluates and compares algorithms and methods used to optimize energy efficiency of trajectory planning, adaptive speed control, battery management in mission planning, and navigation that accounts for environmental characteristics. It differs from those focusing on hardware solutions by highlighting optimization problems where energy usage is considered the key target for optimization and not a limiting constraint. The analyzed methods have been categorized into five groups, including classical optimization, metaheuristics, machine learning (ML), reinforcement learning (RL), and hybrid approaches. Key approaches such as RL, Model Predictive Control, evolutionary algorithms, and data-driven energy modeling have been outlined and compared with regard to energy-model accuracy, type of validation, scalability, and deployment readiness. Additionally, it emphasizes practical aspects such as the accuracy of energy modeling, real-time capabilities, scalability to multiple UAVs, and robustness to environmental uncertainty. Finally, this review provides directions for future research that will help develop sustainable, intelligent, and energy-efficient UAVs. Full article

The rapid expansion of high-speed railway networks has increased the operational energy demand and indoor overheating risk of large-scale, high-volume railway station buildings. Natural ventilation is a climate-responsive passive strategy that can improve indoor environmental quality and reduce reliance on mechanical cooling. However, its contribution to the operational sustainability of large transportation buildings remains insufficiently quantified, particularly in hot-summer and cold-winter regions. This study investigates a seasonally adaptive window-opening strategy for Chengdu Station, with particular attention to major functional spaces such as waiting halls and commercial areas. A DesignBuilder model was used to simulate six ventilation scenarios, ranging from doors-only operation to fully open doors and windows. The effects of different window-opening ratios on hourly indoor temperature, relative humidity, adaptive thermal comfort, and annual building energy use were systematically evaluated. The simulation approach was further assessed against field measurements obtained from a comparable large railway station. The results reveal a pronounced nonlinear and seasonal response to the window-opening ratio. In winter, maintaining a very low opening ratio or keeping only the entrance doors open limits unnecessary heat loss. During the transitional seasons, opening ratios of 40–60% are sufficient to remove residual indoor heat while maintaining acceptable thermal conditions. In summer, the marginal improvement in ventilation performance becomes limited when the side-window opening ratio exceeds approximately 80%; therefore, an opening ratio of 80% was selected as a practical operating threshold rather than an absolute thermal optimum. Based on these seasonal characteristics, a month-by-month window-opening strategy was developed. Compared with the doors-only baseline, the proposed strategy reduced the annual high-temperature-hour ratio from 33.4% to 16.36%, corresponding to a decrease of 17.04 percentage points and a relative reduction of approximately 51.0%. Total annual building energy use decreased from 32,238.8 MWh to 25,923.8 MWh, representing an energy saving of 19.6%. These findings demonstrate that seasonally adaptive natural ventilation can simultaneously reduce overheating risk and operational energy demand while maintaining acceptable indoor thermal conditions. The proposed strategy provides a quantitative basis for the sustainable, energy-efficient, and intelligently managed operation of large-space railway stations in hot-summer and cold-winter regions. Full article

Railway safety is an important component of public security. Ensuring the safety of high-speed rail systems and passengers is also crucial for railway transportation enterprises. The performance of X-ray security inspection systems is one of the key factors in improving intelligent railway security. Previous studies have shown that, due to the complexity of X-ray images, both traditional vision methods and deep learning approaches struggle to meet the requirements of real-world railway security inspection. With the development of vision-language models, this paper proposes XrayCLIP, a CLIP-based method designed to improve the accuracy and robustness of computerized X-ray security inspection. XrayCLIP adapts CLIP to the semantic and imaging characteristics of prohibited-item inspection through security-oriented prompts, texture-aware visual representations, and global–local supervision. The key component of the model is a set of learnable prompt templates, which guide the model to learn generic features of prohibited objects in complex environments. Multi-level global–local (glocal) features enable the model to focus on both global context and local details, while text space optimization, texture enhancement, text–image fusion, and inference enhancement further improve model performance. XrayCLIP is evaluated on the PIDray and derived HiXray(seg) benchmarks against eight conventional and recent single-view baselines under a common evaluation protocol. A railway-station study is additionally conducted using operational X-ray data, including a same-set missed-detection comparison with a commercial system for knives and power banks. The results show that XrayCLIP achieves the best performance among the evaluated methods on PIDray and HiXray(seg), while reducing the missed-detection rate relative to the commercial system on the two categories examined. Full article

This study examines energy savings and efficient use through the application of smart adaptive lighting within the framework of “smart energy”, “smart city”, and “smart village”. Adaptive street lighting systems have emerged as an effective solution for reducing energy consumption while maintaining traffic safety. However, existing studies typically evaluate energy performance under predefined traffic conditions or focus primarily on AI-based control strategies without systematically investigating the influence of object speed on energy savings. This study proposes a comprehensive methodology that combines CupCarbon traffic simulation, Shape-Preserving Cubic Hermite Interpolation (PCHIP), Monte Carlo simulation, sensitivity analysis, and machine learning to evaluate and predict the energy-saving performance of adaptive street lighting. Unlike previous approaches, the proposed framework establishes a continuous relationship between object speed and energy consumption, enabling the estimation of energy savings across the entire operating speed range while quantifying the effects of object speed, pole spacing, and pre-activation time. The machine learning models are employed to predict energy-saving results generated by the simulation framework. Six regression models were trained and validated using simulated datasets, with Gradient Boosting achieving the highest predictive accuracy. Moreover, the analysis demonstrated that adaptive street lighting scenarios operating at 50% power (50 W) under no-object conditions and 100% power (100 W) during object detection achieved energy savings of 19–37% per luminaire compared with conventional street lighting, depending on object speed. Furthermore, adaptive lighting operating at a constant 50% power (50 W) during object detection yielded substantially higher energy savings of 59–77% per luminaire, highlighting the significant influence of the lighting control strategy on overall energy efficiency. The results demonstrate that lower object speeds yield the greatest savings. The proposed methodology provides a robust and scalable framework for the design, optimization, and intelligent control of adaptive street lighting systems and offers a benchmark for evaluating the maximum theoretical energy-saving potential under controlled traffic conditions. Full article

Intelligent transportation and aerial remote sensing scenes suffer from complex scene variations, abundant miniature targets and unpredictable out-of-distribution obstacles, which brings tough mathematical challenges to open-world detection tasks. Conventional detection algorithms lack rigorous frequency-domain separation and spatial constraint mathematical formulations, resulting in severe tiny-object feature attenuation, inefficient multimodal feature matching and catastrophic forgetting during incremental category iteration. To solve these mathematical bottlenecks, this paper constructs the TPCA-Net model built upon frequency decomposition and spatial dependency mathematical modelling. The entire framework consists of four fixed core modules: High-Frequency-Aware Multi-Scale Feature Enhancement (HSE), Reparameterized Adaptive Text–Visual Alignment (RTA), Double Wildcard Spatial Dependency Fusion (WSF), and Incremental Forgetting-Free Dual-Path Detection (DPD). From the mathematical perspective, the HSE module adopts discrete cosine transform-based filtering equations to split high-frequency object details from low-frequency background signals and establishes cross-attention spatial constraint formulas to make up for missing contextual information of small targets. The RTA module introduces low-rank decomposition mathematical optimization and reparameterized tensor fusion rules to realize domain-adaptive text embedding calibration and zero-cost cross-modal mapping at the inference stage. The WSF module constructs dual-wildcard self-supervised mathematical loss to finish unsupervised unknown-object identification and builds decoupled semantic–spatial fusion equations to improve the positioning precision of novel targets. The DPD module designs two sets of independent optimization objective functions and category-freezing incremental mathematical constraints to avoid conflicting parameter updates and eliminate forgetting defects in new-class expansion. Validated on COCO, DOTA and AI-TOD datasets, TPCA-Net achieves 56.0% AP on COCO, 79.30% mAP on DOTA, and 40.5% overall AP with 28.7% small-object AP on AI-TOD while delivering an inference throughput of 101.2 FPS on the Tesla T4 edge GPU. The proposed method outperforms existing mainstream open-world detection algorithms in tiny-object and rare-category recognition while maintaining efficient inference speed. Full article

Urban intelligent transportation systems increasingly rely on vehicle-to-infrastructure (V2I) communication for green-light optimal speed advisory (GLOSA) services. However, conventional GLOSA systems are vulnerable to roadside unit (RSU) coverage gaps and communication instability in mixed-traffic environments. In this paper, we propose a heterogeneous communication network cooperation framework that integrates decentralized multi-hop vehicle-to-vehicle (V2V) relaying with conventional V2I communication to extend signal phase and timing (SPaT) dissemination beyond direct RSU coverage. A lightweight gradient-based speed synchronization mechanism supports real-time trajectory adaptation with low computational overhead. The framework is evaluated through microscopic SUMO simulations with explicit communication impairment modeling across varied traffic densities and connected autonomous vehicle (CAV) penetration levels (10–70%). The results demonstrate reductions in travel time reductions of up to 22%, stop frequency of up to 95%, and CO₂ emission exceeding 18% relative to V2I-only GLOSA under 70% CAV penetration. At the lower bound of 10% CAV penetration, the framework still achieves measurable improvements of approximately 4–6% in travel time and 15–20% in stop frequency, confirming practical benefit even under minimal connected-vehicle adoption. The proposed framework maintains advisory continuity through distributed relay dissemination, offering a scalable and communication-resilient enhancement to intelligent transportation coordination in heterogeneous environments. Full article

The reciprocating cutterbar is evolving from a conventional harvesting mechanism into an intelligent end-effector for crop harvesting, mechanical weeding, and selective cutting. However, plant anisotropy, moisture-dependent fracture, root-soil constraints, vibration, and wear still hinder low-energy cutting, long service life, and robust control. This review integrates harvesting and mechanical weeding within a unified analysis of reciprocating cutterbar technologies. It first links plant tissue structure and dynamic fracture to blade penetration, fiber stretching, crack propagation, and energy dissipation. It then examines how cutting speed, sliding-cut angle, blade clearance, and root-soil anchorage jointly affect performance. Advanced testing, response surface methodology, discrete element method, finite element method, and multiphysics simulations are compared for failure analysis, parameter optimization, and contact modeling. The review further assesses bionic blade design, surface strengthening, composite coatings, novel transmissions, multisource perception, and adaptive control. Key barriers include inconsistent plant-mechanics datasets, computationally intensive models, limited field robustness, and conflicts among performance objectives. We therefore identify digital twins, modular electric cutterbars, and closed-loop control as priorities for translating mechanistic insight into reliable field performance. Full article