Search Results (2,900)

The rapid growth of Distributed Energy Resources (DERs) exerts significant pressure on distribution network margins, requiring predictive and safe coordination. This paper presents a closed-loop framework combining a topology-aware Spatio-Temporal Transformer (STT) for multi-horizon forecasting, a cooperative multi-agent reinforcement learning (MARL) controller under Centralized Training and Decentralized Execution (CTDE), and a real-time safety layer that enforces feeder limits via sensitivity-based quadratic programming. Evaluations on three SimBench feeders, with OLTC/capacitor hybrid control and a stress protocol amplifying peak demand and mid-day PV generation, show that the method reduces tail violations by 31% and 56% at the 99th percentile voltage deviation, and lowers branch overload rates by 71% and 90% compared to baselines. It mitigates tail violations and discrete switching while ensuring real-time feasibility and cost efficiency, outperforming rule-based, optimization, MPC, and learning baselines. Stress maps reveal robustness envelopes and identify MV–LV bottlenecks; ablation studies show that diffusion-based priors and coordination contribute to performance gains. The paper also provides convergence analysis and a suboptimality decomposition, offering a practical pathway to scalable, safe, and interpretable DER coordination. Full article

The network architecture has demonstrated considerable potential for enhancing the strength–ductility synergy in metal matrix composites (MMCs). Intuitively, the intersections of network layers are expected to induce a stress concentration, leading to premature brittle fractures. Introducing chamfers to round the network cells may mitigate the local stress concentration and thereby improve elongation. Here, a numerical simulation framework was developed to investigate the effect of chamfering on the mechanical behavior of a three-dimensional (3D) continuous SiC_3D/Al composite with a network architecture. A Voronoi tessellation algorithm was employed to generate the continuous network structural SiC phase. By inducing ductile and brittle damage criterions in the matrix and reinforcement elements, respectively, the mechanical behavior can be predicted via the finite element method (FEM). The predicted mechanical properties reveal an unexpected trend: chamfering results in a simultaneous reduction in both strength (from 367 MPa to 312 MPa) and elongation (from 4.1% to 2.0%). With chamfering, the enlarged intersection of the network layer bears a lower load, whereas the narrower network plates exhibit higher stress concentrations. As a result, the overall load-bearing capacity of the SiC_3D reinforcement decreases monotonically with an increasing chamfer size f. Furthermore, the non-uniform stress distribution promotes the premature fracture of the SiC_3D, which reduces elongation. Additionally, the crack deflection behavior is suppressed in the chamfered models, leading to decreasing energy dissipation. This unanticipated outcome highlights an important architectural design principle: maintaining uniform geometric dimensions is critical for achieving optimal composite performance. Full article

Reinforced soil retaining walls (RSWs) for railways are key subgrade structures that bear cyclic loads from trains, and their long-term durability directly affects railway operation safety. The mechanical behavior of RSWs under cyclic loading has been extensively investigated in previous studies, primarily focusing on seismic conditions or conventional structural configurations. While these works have established fundamental understanding of load transfer mechanisms and deformation patterns, research on their responses to long-term train-induced vibrations, particularly for concrete-block-panel-wrapped RSWs, an improved structure based on traditional concrete-block-panel RSWs, remains limited. To investigate the dynamic responses of the concrete-block-panel-wrapped RSW, a model test was conducted under cyclic loading conditions where the amplitude was 30 kPa and the frequency was 10 Hz. The model size was 3.0 m in length, 1.0 m in width, and 1.8 m in height, incorporating six layers of geogrid. Each layer of geogrid was 2.0 m in length with a vertical spacing of 0.3 m or 0.15 m. The results indicate that as the number of load cycles increases, deformation, acceleration, static and dynamic stresses, and geogrid strain also increase and gradually stabilize, exhibiting only marginal increments thereafter. The maximum horizontal displacement reaches 0.08% of the wall height (H), with horizontal displacement increasing uniformly along the height of the wall. The vertical acceleration in the non-reinforced soil zone is lower than that in the reinforced soil zone. The horizontal dynamic stress acting on the back of the panel remains minimal and is uniformly distributed along the height of the wall. The maximum geogrid strain was found to be 0.88%, corresponding to a tensile stress amounting to 20.33% of its ultimate tensile strength. The predicted failure surface approximates a bilinear configuration, consisting of one line parallel to the wall face at a distance of 0.3H from the back of the soil bags and another line inclined at an angle equal to the soil’s internal friction angle (φ) relative to the horizontal plane. This study has important reference significance for the application of concrete-block-panel-wrapped RSWs in railways. Full article

A biomimetic adaptive façade applies natural principles to building design using shading devices that dynamically respond to environmental changes, enhancing daylight, thermal comfort, and energy efficiency. While motorised systems offer precision through sensors and mechanical actuation, they consume energy and are complex. In contrast, passively actuated systems use smart materials that respond to environmental stimuli, offering simpler and more sustainable operation, but often lack responsiveness to dynamic conditions. This study explores a sequential approach by initially developing motorised shading concepts before transitioning to a passive actuation strategy. In the first phase, nine mechanically actuated shading device concepts were designed, inspired by the opening and closing behaviour of plant stomata, and evaluated on structural robustness, actuation efficiency, ease of installation, and visual integration. One concept was selected for further development. In the second phase, a biocomposite made of polylactic acid (PLA) and regenerated cellulose fibres was used for Fused Deposition Modelling (FDM) to fabricate 3D-printed modules with passive, moisture-responsive actuation. The modules underwent environmental testing, demonstrating repeatable shape changes in response to heat and moisture. Moisture application increased the range of motion, and heating led to flap closure as water evaporated. Reinforcement and layering strategies were also explored to optimise movement and minimise unwanted deformation, highlighting the material’s potential for sustainable, responsive façade systems. Full article

Nuclear power plant (NPP) shear walls are typically ultra-thick and heavily reinforced, posing significant challenges for conventional cast-in-place (CIP) construction. To overcome these issues, this study proposes a precast concrete shear wall (PCSW) system with bolted connections. Owing to orthogonal wall layouts dictated by functional requirements, these structures are subjected to significant out-of-plane seismic demands, making their performance under such loading a critical design concern. Therefore, this paper investigates the out-of-plane seismic performance of scaled (1:2) models of PCSWs (300 mm thick) under an axial pressure ratio of 0.2 and without axial pressure through low-cycle repeated load tests, and compares them with corresponding CIP shear walls. All specimens exhibited flexural failure, while damage in PCSWs was relatively minor and concentrated within the grouting layer. Compared with CIP specimens, the precast specimens showed more pinching and smaller residual deformation, with cumulative energy dissipation reaching 70–80% of CIP specimens. The flexural load-bearing capacity of the precast specimens was close to that of the CIP specimens, with differences within 5%. The ductility of the precast specimens under axial pressure ratios of 0 and 0.2 was 4.54 and 2.68, respectively, differing from the CIP specimens by 16% and −10%. The stiffness degradation trends of both systems were essentially consistent. Overall, the results demonstrate that the out-of-plane seismic performance of PCSWs with bolted connections is broadly equivalent to that of CIP counterparts, confirming their feasibility for application in NPPs. Full article

Deep neural network-based approaches have obtained remarkable progress in monaural speech enhancement. Nevertheless, current cutting-edge approaches remain vulnerable to complex acoustic scenarios. We propose a Symmetric Combined Convolution Network with ConvLSTM (SCCN) for monaural speech enhancement. Specifically, the Combined Convolution Block utilizes parallel convolution branches, including standard convolution and two different depthwise separable convolutions, to reinforce feature extraction in depthwise and channelwise. Similarly, Combined Deconvolution Blocks are stacked to construct the convolutional decoder. Moreover, we introduce the exponentially increasing dilation between convolutional kernel elements in the encoder and decoder, which expands receptive fields. Meanwhile, the grouped ConvLSTM layers are exploited to extract the interdependency of spatial and temporal information. The experimental results demonstrate that the proposed SCCN method obtains on average 86.00% in STOI and 2.43 in PESQ, which outperforms the state-of-the-art baseline methods, confirming the effectiveness in enhancing speech quality. Full article

Engineered Cementitious Composite (ECC) exhibits superior tensile strain-hardening behavior and enhanced crack control due to its distinctive multiple cracking characteristic. In contrast, Steel–Glass Fiber Reinforced Polymer (GFRP) Composite Bars (SFCBs) combine the ductility of steel with the corrosion resistance of GFRP. To investigate the synergistic mechanisms for optimizing the performance of concrete structures, this study designed eight SFCB-reinforced ECC-concrete composite beams. Four-point bending tests were conducted to examine the influence of the ECC replacement height in the tension zone (hE/h = 0%, 16.67%, 33.33%, 50%) and the steel ratio in the bottom longitudinal reinforcement (As/Ab = 0%, 9%, 25%, 49%, 100%) on the flexural performance. The experimental results demonstrated the following: (1) Increasing the ECC replacement significantly improved both the ultimate bending capacity and ductility, while exerting a limited effect on flexural stiffness. Specifically, when increased from 0% to 50%, the ultimate bending strength and ductility index increased by 4.79% and 8.09%, respectively. (2) The steel ratio predominantly governed the yield behavior and crack development. Higher steel ratios resulted in increased flexural stiffness prior to yield, higher yield moments, improved ductility at failure, and superior crack control capability before yielding. (3) The synergistic mechanisms were identified: the ECC layer optimizes crack control by distributing crack-induced strains through multiple cracking, while the steel ratio within the SFCB regulates the ductile response. The findings of this study provide valuable theoretical guidance for enhancing the capacity and ductility of building structures. Full article

Wire Arc Additive Manufacturing (WAAM) has been recognized as an efficient and cost-effective metal additive manufacturing technique due to its high deposition rate and scalability for large components. However, the quality and repeatability of WAAM parts are highly sensitive to process parameters such as arc voltage, current, wire feed rate, and torch travel speed, requiring advanced monitoring and adaptive control strategies. In this study, a vision-based monitoring system integrated with a reinforcement learning framework was developed to enable intelligent in situ control of WAAM. A custom optical assembly employing mirrors and a bandpass filter allowed simultaneous top and side views of the melt pool, enabling real-time measurement of layer height and width. These geometric features provide feedback to a tabular Q-learning algorithm, which adaptively adjusts voltage and wire feed rate through direct hardware-level control of stepper motors. Experimental validation across multiple builds with varying initial conditions demonstrated that the RL controller stabilized layer geometry, autonomously recovered from process disturbances, and maintained bounded oscillations around target values. While systematic offsets between digital measurements and physical dimensions highlight calibration challenges inherent to vision-based systems, the controller consistently prevented uncontrolled drift and corrected large deviations in deposition quality. The computational efficiency of tabular Q-learning enabled real-time operation on standard hardware without specialized equipment, demonstrating an accessible approach to intelligent process control. These results establish the feasibility of reinforcement learning as a robust, data-efficient control technique for WAAM, capable of real-time adaptation with minimal prior process knowledge. With improved calibration methods and expanded multi-physics sensing, this framework can advance toward precise geometric accuracy and support broader adoption of machine learning-based process monitoring and control in metal additive manufacturing. Full article

Addressing the challenge of high-precision time-coordinated path planning for manned and unmanned aerial vehicle (UAV) clusters operating in complex dynamic environments during missions like high-level autonomous coordination, this paper proposes a reinforcement learning-based Adaptive Grey Wolf Optimizer (RL-GWO) method. We formulate a comprehensive multi-objective cost function integrating total flight distance, mission time, time synchronization error, and collision penalties. To solve this model, we design multiple improved GWO strategies and employ a Q-Learning framework for adaptive strategy selection. The RL-GWO algorithm is embedded within a dual-layer “global planning + dynamic replanning” framework. Simulation results demonstrate excellent convergence and robustness, achieving second-level time synchronization accuracy while satisfying complex constraints. In dynamic scenarios, the method rapidly generates safe evasion paths while maintaining cluster coordination, validating its practical value for heterogeneous UAV operations. Full article

To investigate the influence of laser cladding overlap rate on the microstructure and corrosion resistance of cladded layers, Ni60-WC composite coatings with different overlap rates (30%, 50%, and 70%) were prepared on E690 offshore steel in this study. The relationship between the corrosion resistance and microstructure of the cladded layers fabricated at different overlap rates was analyzed using an electrochemical workstation, scanning electron microscope, X-ray diffractometer, and energy dispersive spectrometer. The results demonstrate that the overlap rate exerts a significant impact on the corrosion resistance of the cladded layers, and the corrosion resistance of the cladded layers gradually improves with the increase in overlap rate. The cladded layer prepared with a 70% overlap rate exhibits excellent corrosion resistance, featuring the highest open-circuit potential (−0.31 V vs. SCE), the lowest corrosion current density (3.35 μA/cm²), the largest capacitive arc radius in the electrochemical impedance spectroscopy (EIS), and a relatively flat surface after corrosion tests. Microstructural characterization results indicate that the increase in overlap rate promotes grain refinement and the formation of reinforcing phases (e.g., M₂₃C₆). The coating with a 70% overlap rate possesses the densest microstructure and abundant flocculent carbides, which act as an effective barrier against the penetration of corrosive media, thereby endowing it with optimal performance. Full article

Securing Industrial Control Systems (ICSs) is critical, but it is made challenging by the constant evolution of cyber threats and the scarcity of labeled attack data in these specialized environments. Standard intrusion detection systems (IDSs) often fail to adapt when transferred to new networks with limited data. To address this, this paper introduces an adaptive intrusion detection framework that combines a hybrid Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM) model with a novel transfer learning strategy. We employ a Reinforcement Learning (RL) agent to intelligently guide the fine-tuning process, which allows the IDS to dynamically adjust its parameters such as layer freezing and learning rates in real-time based on performance feedback. We evaluated our system in a realistic data-scarce scenario using only 50 labeled training samples. Our RL-Guided model achieved a final F1-score of 0.9825, significantly outperforming a standard neural fine-tuning model (0.861) and a target baseline model (0.759). Analysis of the RL agent’s behavior confirmed that it learned a balanced and effective policy for adapting the model to the target domain. We conclude that the proposed RL-guided approach creates a highly accurate and adaptive IDS that overcomes the limitations of static transfer learning methods. This dynamic fine-tuning strategy is a powerful and promising direction for building resilient cybersecurity defenses for critical infrastructure. Full article

The current study examines the influence of tool rotational speed (TRS) and reinforcement volume fraction (%vol.) of SiC on particle distribution in the stir zone (SZ) of AZ91 Mg alloy. Two parameter sets were analyzed: S1 (500 rpm TRS, 13% vol.) and S2 (1500 rpm TRS, 10% vol.), with a constant tool traverse speed (TTS) of 60 mm/min. SPH simulations revealed that in S1, lower TRS resulted in limited SiC displacement, leading to significant agglomeration zones, particularly along the advancing side (AS) and beneath the tool pin. Cross-sectional observations at 15 mm and 20 mm from the plunging phase indicated the formation of reinforcement clusters along the tool path, with inadequate SiC transference to the retreating side (RS). The reduced stirring force in S1 caused poor reinforcement dispersion, with most SiC nodes settling at the SZ bottom due to insufficient upward movement. In contrast, S2 demonstrated enhanced particle mobility due to higher TRS, improving reinforcement homogeneity. Intense stirring facilitated lateral and upward SiC movement, forming an interconnected reinforcement network. SPH nodes exhibited improved dispersion, with particles across the SZ and more evenly deposited on the RS. A comparative assessment of experimental and simulated reinforcement distributions confirmed a strong correlation. Results highlight the pivotal role of TRS in reinforcement movement and agglomeration control. Higher TRS enhances stirring and promotes uniform SiC dispersion, whereas an excessive reinforcement fraction increases matrix viscosity and restricts particle mobility. Thus, optimizing TRS and reinforcement content through numerical analysis using SPH is essential for producing a homogeneous, well-reinforced composite layer with improved surface properties. The findings of this study have significant practical applications, particularly in industrial material selection, improving manufacturing processes, and developing more efficient surface composites, thereby enhancing the overall performance and reliability of Mg alloys in engineering applications. Full article

Wheat blast, caused by Magnaporthe oryzae pathotype Triticum (MoT), poses a major threat to wheat (Triticum aestivum) cultivation, particularly in South America and Bangladesh. The rapid evolution and spread of the pathogen necessitate the development of durable and broad-spectrum resistance in wheat cultivars. This review summarizes current insights into the multi-layered defense mechanisms of wheat, encompassing resistance (R) genes, pattern-triggered immunity (PTI), and effector-triggered immunity (ETI) against MoT. The R-genes provide race-specific resistance through ETI, while both ETI and PTI are required to form integral layers of the plant immune system that synergistically reinforce host defense network. Recent advances in genomics, transcriptomics, and molecular breeding have facilitated the discovery and deployment of key R-genes and signaling components involved in PTI and ETI pathways. Integrating these immune strategies through gene pyramiding, marker-assisted selection (MAS), and genome editing offers a promising route towards enhanced and durable resistance in hosts. Harnessing and optimizing these multilayered immune systems will be pivotal to securing wheat productivity amid the growing threat of wheat blast. Full article

Carbon fiber-reinforced polymer (CFRP) composites have excellent mechanical properties, but their performance is hampered by delamination caused by weak interfacial bonding and resin-rich region (RRR). This research has proposed an interleaving film to improve interlaminar structure and mechanical properties by adding polyacrylonitrile (PAN) fiber into the epoxy interlayer of the CFRP laminates. The PAN fiber/epoxy resin (PANER) interleaving film could be prepared, which was beneficial to hinder crack initiation paths and improve the load transfer. Flexural and compression performance testing results showed optimum performance was obtained when 2 wt.% PAN fiber was added, and an increment of 28.6% was obtained in the flexural strength and 11.7% increment in compressive strength. The damaged energy absorption was improved up to 21.4% and 11.3% for the flexural and compressive properties, respectively. The overall thickness increments in the interlayer with PANER interleaving film were approximately 4–9 μm. X-Ray micro-computed tomography and scanning electron microscopy observations exhibited the potential of PAN fiber in the reduction of RRR, resulting in modes replacement from delamination-dominant failure to crossing-multi-layer failure. In all, PANER interleaving film at the interlayer has been confirmed to be an effective approach to produce a simple reinforcement technology for FRP laminates. Full article

To clarify the influence of reinforcement corrosion on the mechanical performance of road tunnel linings, localized tests on reinforcement-induced concrete expansion are conducted to identify cracking patterns and their effects on load-bearing behavior. Refined three-dimensional finite element models of localized concrete and the entire tunnel are developed using the concrete damaged plasticity model and the extended finite element method and validated against experimental results. The mechanical response and crack evolution of the lining under corrosion are analyzed. Results show that in single-reinforcement specimens, cracks propagate perpendicular to the reinforcement axis, whereas in multiple-reinforcement specimens, interacting cracks coalesce to form a π-shaped pattern. The cover-layer crack width exhibits a linear relationship with the corrosion rate. Corrosion leads to a reduction in the stiffness and load-bearing capacity of the local concrete. At the tunnel scale, however, its influence remains highly localized, and the additional deflection exhibits little correlation with the initial deflection. Local corrosion causes a decrease in bending moment and an increase in axial force in adjacent linings; when the corrosion rate exceeds about 15%, stiffness damage and internal force distribution tend to stabilize. Damage and cracks initiate around corroded reinforcement holes, extend toward the cover layer, and connect longitudinally, forming potential spalling zones. Full article