Search Results (1,975)

Stable wind resources in far-reaching sea areas are important direction for the development of renewable energy, making floating offshore wind turbine (FOWT) a focus of current research. However, the working environment of FOWT is severe. Under the condition of changeable wind and waves, the floating platform exhibits various motion responses, which may reduce power generation efficiency and even lead to structural damage with unpredictable consequences. In this paper, the National Renewable Energy Laboratory (NREL) 5 MW OC4-DeepCwind semi-submersible wind turbine is considered, and a multi-degree-of-freedom (M-DOF) tuned mass damper (TMD) system is designed to simultaneously suppress its roll and pitch motion responses. A multi-objective optimization problem is formulated to unify the frequency tuning accuracy, damping ratio constraints, and mass ratio limits through penalty functions. Then an improved Particle Swarm Optimization algorithm with time-varying acceleration coefficients (TVAC-PSO) is employed to determine the optimal TMD parameters, which dynamically adjusts exploration and exploitation capabilities to overcome the limitations of standard PSO in handling the strongly coupled parameter space. A high-fidelity aero-hydro-servo-elastic simulation model is established using OpenFAST to verify the vibration suppression performance under various sea state conditions. Simulation results demonstrate that the proposed M-DOF TMD system can effectively reduce the roll and pitch motion responses and significantly suppress the resonant peak energy, substantially improving the dynamic performance of FOWT. Full article

High-performance operation of permanent magnet synchronous motors (PMSMs) strongly depends on the reliable availability of rotor position and speed information. Although this information is commonly obtained using physical position sensors, such sensors increase system cost and structural complexity and may reduce long-term reliability, particularly in demanding operating environments. In this study, a model-based, discrete-time, nonlinear gradient observer is adapted for the sensorless estimation of rotor speed and position in PMSMs. The developed Runge–Kutta model-based gradient observer (RKGO) utilizes stator voltage inputs and measured stator currents within a mathematical motor model to estimate the system states. In contrast to conventional sensorless estimation approaches, the adopted observer framework exploits discretization-based gradient dynamics to enhance numerical robustness and convergence behavior under nonlinear operating conditions. The observer design specifically targets stable and accurate state estimation in discrete-time implementations, with a particular focus on low-speed operating conditions. The performance of the adapted method is experimentally evaluated under low-speed operating conditions, including transient and steady-state operation. Real-time implementation is carried out on a dSPACE DS1104 control platform, including loaded acceleration scenarios to assess practical robustness. In addition, a comparative analysis with the Extended Kalman Filter (EKF) and the Runge–Kutta Extended Kalman Filter (RKEKF) is conducted at 60 rad/s under identical experimental conditions. Experimental results show that the RKGO method achieves accurate steady-state speed and position estimation with acceptable transient performance. The findings demonstrate that RKGO can be considered a viable alternative for low-speed sensorless PMSM drive applications. Full article

The digital transformation of oil and gas pipeline networks has generated substantial volumes of unstructured maintenance documentation from communication systems, creating an urgent need for automated summarization to improve operational efficiency. However, domain-specific text summarization for pipeline communication maintenance remains challenging due to scarce labeled data and the high computational cost of fine-tuning large pretrained models. Parameter-efficient fine-tuning alleviates this issue, but its effectiveness strongly depends on appropriate hyperparameter selection. This paper proposes a unified framework that combines weight-decomposed low-rank adaptation with an enhanced Artificial Bee Colony algorithm for automated hyperparameter optimization. The enhanced algorithm addresses two specific limitations of the standard Artificial Bee Colony algorithm: uninformed random initialization that ignores promising regions, and premature abandonment of stagnated solutions that discards partially useful search directions. These two components represent principled design choices, each targeting a distinct bottleneck in applying swarm intelligence search to high-dimensional mixed-type hyperparameter spaces. The method introduces a hybrid initialization strategy to exploit prior knowledge and a stagnation-guided local search mechanism to refine stagnated solutions instead of discarding them, achieving a better balance between exploration and exploitation. Experimental results on a public Chinese summarization benchmark and an industrial oil and gas pipeline communication maintenance corpus show that the proposed approach consistently outperforms full fine-tuning, manually tuned parameter-efficient methods, and several evolutionary optimization baselines in terms of ROUGE metrics. The automated search introduces modest additional computational overhead compared to manual tuning while eliminating expert-dependent hyperparameter configuration and achieving consistent performance gains across both datasets. Overall, the proposed framework provides an efficient and robust solution for adapting large language models to specialized summarization tasks in the context of pipeline communication system maintenance. Full article

Underwater acoustic sensor networks (UASNs) have emerged as a pivotal technology for ocean exploration, tactical surveillance, and environmental monitoring. However, the underwater acoustic channel poses severe challenges, including high propagation delay, limited bandwidth, and rapid time-varying multipath fading, which significantly degrade communication reliability. Cooperative communication, which exploits spatial diversity via relay nodes, offers a promising solution to these impairments. In this paper, we investigate the joint optimization of relay selection and power allocation in UASNs to maximize the long-term system energy efficiency and throughput. This problem is inherently complex due to the hybrid action space, which couples the discrete selection of relay nodes with the continuous allocation of transmission power, and the absence of real-time, perfect channel state information (CSI). To address these challenges, we propose a novel deep hybrid reinforcement learning (DHRL) framework utilizing a parameterized deep Q-Network (P-DQN) architecture. Unlike traditional approaches that discretize power levels or relax discrete constraints, our approach seamlessly integrates a deterministic policy network for continuous power control and a value-based network for discrete relay evaluation. Furthermore, we incorporate a prioritized experience replay (PER) mechanism to improve sample efficiency by focusing on rare but significant channel transition events. We provide a comprehensive theoretical analysis of the algorithm’s complexity and convergence properties. Extensive simulation results demonstrate that the proposed DHRL algorithm outperforms state-of-the-art combinatorial bandit algorithms and conventional deep reinforcement learning baselines in terms of system energy efficiency, and also exhibits superior robustness against channel estimation errors. Full article

Multi-objective evolutionary optimization faces significant challenges due to guidance mismatch under complex Pareto-front geometries. This paper proposes a dynamic self-organizing map-assisted evolutionary algorithm (D-SOMA), a manifold-aware framework that harmonizes knowledge-informed priors with unsupervised objective-space characterization. Specifically, a knowledge-informed guided resampling strategy is formulated to bridge stochastic initialization and targeted exploitation. By distilling spatial distribution priors from the decision-variable boundaries of early-stage elite solutions, it establishes a high-quality starting population biased towards promising regions. To capture the intrinsic geometry of the evolving population, a self-organizing map (SOM)-based adaptive subregion characterization strategy leverages the topological preservation of self-organizing maps to extract latent modeling parameters. This strategy adaptively determines subregion centers and influence radii, enabling a data-driven partitioning that respects the underlying manifold structure. Furthermore, a density-driven phase-responsive scale adjustment strategy is introduced. By synthesizing spatial density feedback and temporal evolutionary trajectories, it dynamically modulates the characterization granularity K, thereby maintaining a rigorous balance between geometric modeling fidelity and computational overhead. Extensive experiments on 50 benchmark problems from the DTLZ, WFG, MaF and RWMOP suites demonstrate that D-SOMA is statistically superior to seven state-of-the-art algorithms, exhibiting robust convergence and superior diversity across diverse problem landscapes. Full article

Smart Design methodologies represent a powerful approach for tackling optimization problems and exploring design spaces that would be unmanageable with traditional methods. By integrating computational approaches, optimization strategies and machine learning, it enables the systematic investigation of multiple configurations and the identification of optimal solutions with reduced computational effort. In the present work, Smart Design algorithms are implemented to investigate the influence of geometric parameters on a lattice–honeycomb–square structure. Results coming from finite element analysis and Life Cycle Assessment are exploited to train Random Forest and XGBoost machine learning models in order to find the lattice parameter set that ensures the optimal balance between mechanical performance and sustainability requirements. Full article

Sampling-based planners such as RRT* are attractive for robot navigation in complex spaces, but they often suffer from high randomness, low efficiency, slow convergence, and suboptimal path quality in cluttered environments. To address these limitations, this paper proposes PFMS-RRT*, a progress-aware fused-sampling RRT* with a multi-level strategy extension. The method builds on a bidirectional RRT* framework and introduces three main components: (i) a progress-aware fused sampling scheme that adapts an oriented elliptical sampling region based on inter-tree progress and stagnation, mixes locally guided elliptical samples with globally explorative Halton-sequence samples, and dynamically balances exploration and exploitation; (ii) a three-level goal-guided extension mechanism that escalates from direct steering to local probing and then multi-direction detours to maintain forward progress when obstacles block expansion; and (iii) a smooth tangential artificial potential field (APF) extension used as a fallback, with a failure-driven probabilistic switching rule that increases APF usage after repeated extension failures. Simulations in four representative 2D environments (sparse, corridor-like dense, random dense, and narrow passage) show that PFMS-RRT* consistently yields shorter paths, lower and more stable runtime, and fewer nodes than several RRT* variants while maintaining competitive or improved obstacle clearance. Full article

Environmental monitoring systems require robust uncertainty quantification for effective decision-making in complex ecological processes. Harmful algal blooms represent a critical challenge where prediction uncertainty directly impacts resource allocation and response timing, yet current remote sensing-based prediction systems provide only deterministic classifications without confidence measures. This gap between algorithmic predictions and actionable risk assessment limits operational utility for stakeholders managing water quality under varying risk tolerances. This study developed a transferable probabilistic forecasting framework integrating Sentinel-2 multispectral imagery with quantile regression and ensemble machine learning to generate continuous confidence indicators for cyanobacteria density prediction, demonstrated through its application to Lake Okeechobee, Florida. The methodology combines spectral indices extracted from Sentinel-2 data with XGBoost for quantile regression at 0.05, 0.50, and 0.95 probability levels, and LightGBM for multi-horizon temporal forecasting. Sentinel-2’s 13 spectral bands spanning visible to shortwave infrared wavelengths, combined with its 5-day revisit frequency provide a spectrally rich and temporally dense input space that is well-suited to gradient boosting methods such as XGBoost, which can exploit complex nonlinear interactions among spectral features to distinguish cyanobacterial signatures from background water constituents. LightGBM achieved mean absolute percentage errors of 2.9% for 10-day forecasts and 5.7% for 20-day forecasts, outperforming conventional regression models. The framework generates 90% prediction intervals that enable reliable risk classifications for operational bloom management. This approach bridges the gap between satellite-based algal bloom detection and actionable decision-making by quantifying predictive uncertainty, representing a shift from binary classifications to probability-based environmental monitoring systems that accommodate varying stakeholder risk tolerances in water quality management applications. Full article

The modeling and control of photovoltaic and other engineering systems highly depend on the accuracy of parameter identification. However, parameter extraction for photovoltaic equivalent models typically presents a high-dimensional, strongly nonlinear, and multimodal global optimization problem. Traditional analytical or gradient-based methods are sensitive to initial values and easily fall into local optima. To address this issue, this paper proposes a multi-strategy improvement teaching–learning-based optimization algorithm (SNTLBO). A social learning network structure with symmetric interaction topology is introduced into the classical TLBO framework to characterize the knowledge propagation relationships among individuals. Through this symmetric and balanced information exchange mechanism, learners can be guided not only by the teacher but also by multiple neighbors within the network, enabling more diverse and symmetric exploration of the search space and enhancing population diversity and global search capability. Furthermore, a teacher reputation mechanism is constructed, where historical performance is used to weight teacher influence, strengthening the guidance of high-quality solutions and accelerating convergence. Meanwhile, an adaptive teaching factor is designed to dynamically adjust the teaching intensity based on the distance between the teacher and students in the solution space, maintaining a dynamic balance (symmetry) between exploration and exploitation. To evaluate the performance of the proposed algorithm, SNTLBO is systematically compared with 11 advanced optimization algorithms on two benchmark test suites, CEC2017 (30D, 50D) and CEC2022 (10D, 20D). Non-parametric statistical tests are conducted to assess significance. The results demonstrate that SNTLBO shows competitive advantages in terms of convergence speed, solution accuracy, and stability. Finally, SNTLBO is applied to the parameter estimation of single-diode, double-diode, triple-diode, quadruple-diode, and photovoltaic module models. Experimental results show that the proposed algorithm achieves higher identification accuracy and robustness in terms of RMSE, IAE, and I–V/P–V curve fitting, verifying its effectiveness and practical value for complex global optimization and practical engineering applications. Full article

Autonomous exploration in unknown environments remains a challenging problem for UAVs. This paper proposes a hierarchical exploration planning framework that explicitly leverages real-time acquired prior knowledge to improve exploration efficiency. To efficiently represent the structural information embedded in the prior knowledge, two map structures, namely the quasi-prior map and the hybrid-topo map, are designed, enabling more reasonable space partition and facilitating exploration planning. Subsequently, based on the hybrid-topo map, the hierarchical exploration planner computes a global exploration guidance that provides an efficient traversal order over all unexplored regions. The local coverage problem in unknown regions is formulated as a coverage traveling salesman problem (CTSP), where visibility information derived from the hybrid-topo map is exploited to optimize local viewpoint sequences with high coverage efficiency. Finally, a long-horizon trajectory planning strategy is proposed to maintain high flight speed while ensuring safety and dynamic feasibility. Simulations demonstrate that the proposed framework significantly outperforms state-of-the-art exploration methods in terms of exploration efficiency, while ablation studies further validate the effectiveness of each module. Real-world experiments are conducted to confirm the practical capability of the proposed approach. Full article

Bird’s-eye-view (BEV) perception has emerged as a key representation for unified scene understanding in autonomous driving. However, current BEV methods relying solely on monocular cameras suffer from severe degradation under adverse weather and dynamic scenes due to limited depth cues and illumination dependency. To address these challenges, we propose a robust multi-modal BEV perception framework that integrates dual-source 4D millimeter-wave radar and multi-view camera images. The proposed architecture systematically exploits Doppler velocity and temporal information from 4D radar to model dynamic object motion, while introducing a deformable fusion strategy in the BEV space for accurate semantic alignment across modalities. Our design includes four key modules: a Doppler-Aware Radar Encoder (DARE) that enhances motion-sensitive features via velocity-guided attention; a Fog-Aware Feature Denoising Module (FADM) that suppresses modality inconsistency in low-visibility conditions through cross-modal attention and residual enhancement; a Multi-Modal Temporal Fusion Module (TFM) that encodes radar temporal sequences using a Transformer encoder for motion continuity modeling; and a confidence-aware multi-task loss that jointly supervises semantic segmentation, motion estimation, and object detection. Extensive experiments on the DualRadar dataset and adverse-weather simulations demonstrate that our method achieves significant gains over state-of-the-art baselines in BEV segmentation accuracy, detection robustness, and motion stability. The proposed framework offers a scalable and resilient solution for real-world autonomous perception, especially under challenging environmental conditions. Full article

Artificial intelligence computing systems increasingly demand high-bandwidth, high-extinction-ratio, chip-to-chip optical transceivers. Silicon microring modulators (MRMs) are attractive for such transmitters due to their compact footprint and wavelength-division multiplexing capability. However, for a specified extinction ratio, the optical bandwidth for high-Q MRMs and the driver’s RC time constant prevent conventional single-segment MRM drivers from supporting 100 GBaud class PAM4 transmission. This work presents a broadband driver exploiting the feedforward technique for dual-segment MRMs. It extends electro-optical bandwidth while maintaining a high Q-factor and extinction ratio. The input signal is split into low- and high-frequency components that drive the long and short segments of the MRM, respectively. The long segment uses a broadband low-pass driver, whereas the short segment employs a driver with a programmable bandpass response near the Nyquist frequency. The design space is obtained from an equivalent electro-optical model under constant group-delay constraints. Simulations at 1310 nm show that the 3 dB electro-optical bandwidth improves from ~50 to >70 GHz and that a 200 Gb/s PAM4 optical eye diagram exhibits an open eye; the energy efficiency is 1.44 pJ/bit, and the extinction ratio improves from 2 dB to 4.1 dB. The proposed technique provides a tunable electro-optical co-design approach for high-bandwidth-density, high-extinction-ratio silicon photonic transmitters. Full article

Well spacing and reinjection rate are two critical parameters controlling the efficiency and sustainability of hot dry rock geothermal development. Taking the Yangbajing geothermal field in Tibet as the geological setting, permeability experiments were conducted on fractured rock masses under multiple operating conditions, and a three-dimensional fully coupled thermo-hydro-mechanical numerical model was established to systematically evaluate the effects of different well spacing–reinjection rate combinations on heat extraction performance. The experimental results show that axial stress is the dominant factor governing specimen deformation and seepage characteristics. Permeability decreases with increasing axial stress, exhibiting an initial sharp decline followed by a gradual reduction. The effect of temperature varies with axial stress level. Under low to moderate axial stress, permeability decreases monotonically with increasing temperature, whereas under high axial stress, it first decreases and then increases. The simulation results indicate that the production temperature remains relatively stable during the early stage of exploitation and subsequently declines, with the rate of decline increasing significantly as the reinjection rate increases or the well spacing decreases. In addition, an exponential positive relationship is identified between well spacing and the optimal reinjection rate. When a 10% decline in production temperature is adopted as the shutdown criterion, the optimal reinjection rate increases from 60 m³/h to 150 m³/h as the well spacing increases from 500 m to 800 m. Based on the simulation results, the theoretical installed capacity of the first deep reservoir in the Yangbajing geothermal field is preliminarily estimated to reach 31.8 MW. Full article

This work investigates the solution and the stability of a generalized system of bi-quadratic–Drygas functional equations in non-Archimedean normed spaces with unknown coefficients. The presence of asymmetric coefficients and reflection terms induces nontrivial coupling effects and symmetry-breaking phenomena, while simultaneously capturing additive, quadratic, and mixed additive–quadratic behaviors. An examination of the coefficients shows that the trivial solution is the only one satisfying the system of equations in asymmetric parameter configurations. For symmetric configurations, by exploiting the ultrametric structure of non-Archimedean norms and applying an iterative method combined with symmetry-based decomposition into even and odd parts, we establish the existence and uniqueness of an exact solution approximating a given mapping. Several known stability results for bi-Drygas functional equations are recovered with improvement as special cases. Full article

Endoscopic images are often degraded by uneven illumination, motion blur, and tissue occlusion, which obscure critical anatomical details and complicate surgical manipulation. This issue is particularly pronounced in single-port endoscopic surgery, where the imaging capability of the camera is further constrained by limited working space. While deep learning-based enhancement methods have demonstrated impressive performance, most existing approaches remain too computationally demanding for real-time surgical use. To address this challenge, we propose an efficient stepwise endoscopic image enhancement framework that introduces an implicit degradation representation as an intermediate feature to guide the enhancement module toward high-quality results. The framework further exploits the temporal continuity of endoscopic videos, based on the assumption that image degradation evolves smoothly over short time intervals. Accordingly, high-quality degradation representations are estimated only on key frames at fixed intervals, while the representations for the remaining frames are obtained through fast inter-frame propagation, thereby significantly improving computational efficiency while maintaining enhancement quality. Experimental results demonstrate that our method achieves an excellent balance between enhancement quality and computational efficiency. Further evaluation on the downstream segmentation task suggests that our method substantially enhances the understanding of the surgical scene, validating that implicitly learning and degradation representation propagation offer a practical pathway for real-time clinical application. Full article