Search Results (1,280)

Accurate heading estimation is crucial for the autonomous navigation of small-to-medium tractors. While dual-antenna GNSS systems offer precision, they face installation and safety challenges. Single-antenna GNSS integrated with a low-cost Strapdown Inertial Navigation System (SINS) presents a more adaptable solution but suffers from slow convergence and low accuracy of heading estimation in low-speed farmland operations. This study proposes an adaptive trajectory-constrained heading estimation method. A sliding-window adaptive extended Kalman filter (SWAEKF) was developed, incorporating a heading constraint model that utilizes the GNSS-derived trajectory angle. An enhanced Sage–Husa algorithm was employed for the adaptive estimation of the trajectory angle measurement variance. Furthermore, a covariance initialization strategy based on the variance of trajectory angle increments was implemented to accelerate convergence. Field tests demonstrated that the proposed method achieved rapid heading convergence (less than 10 s for straight lines and 14 s for curves) and high accuracy (RMS heading error below 0.15° for straight-line tracking and 0.25° for curved paths). Compared to a conventional adaptive EKF, the SWAEKF improved accuracy by 23% and reduced convergence time by 62%. The proposed algorithm effectively enhances the performance of GNSS/SINS integrated navigation for tractors in low-dynamic environments, meeting the requirements for autonomous navigation systems. Full article

Large Language Models (LLMs) are increasingly used in higher education, but their pedagogical role in fields like cybersecurity remains under-investigated. This research explores integrating LLMs into a university cybersecurity course using a designed pedagogical approach based on active learning, problem-based learning (PBL), and computational thinking (CT). Instead of viewing LLMs as definitive sources of knowledge, the framework sees them as cognitive tools that support reasoning, clarify ideas, and assist technical problem-solving while maintaining human judgment and verification. The study uses a qualitative, practice-based case study over three semesters. It features four activities focusing on understanding concepts, installing and configuring tools, automating procedures, and clarifying terminology, all incorporating LLM use in individual and group work. Data collection involved classroom observations, team reflections, and iterative improvements guided by action research. Results show that LLMs can provide valuable, customized support when students actively engage in refining, validating, and solving problems through iteration. LLMs are especially helpful for clarifying concepts and explaining procedures during moments of doubt or failure. Still, common issues like incomplete instructions, mismatched context, and occasional errors highlight the importance of verifying LLM outputs with trusted sources. Interestingly, these limitations often act as teaching opportunities, encouraging critical thinking crucial in cybersecurity. Ultimately, this study offers empirical evidence of human–AI collaboration in education, demonstrating how LLMs can enrich active learning. Full article

This study investigates the integration of 3D laser scanning technology in the retrofitting of Ballast Water Treatment Systems (BWTS) on existing commercial vessels, addressing the global challenge of invasive aquatic species. The methodology combines a bibliometric analysis of keywords—indicating recent trends and knowledge gaps, a feasibility study, and detailed engineering design with on-site supervision. A case study is presented on a crude oil tanker, employing a multi-station 3D scanning strategy across the engine and pump rooms—performed using 63 and 45 scan positions, respectively. These data were processed with removal filters and integrated into specialized CAD software for detailed piping design. The implementation of high-fidelity point clouds served as the digital foundation for modeling the vessel’s existing piping infrastructure and retrofitting with the installation of an electrolysis-based BWTS. Results confirm that 3D scanning enables precise spatial analysis, minimizes retrofitting errors, reduces installation time, and ensures regulatory compliance with the IMO Ballast Water Management Convention. By digitally capturing complex onboard environments, the approach enhances accuracy, safety, and cost-effectiveness in maritime engineering projects. This work underscores the transition toward point cloud-based digital twins as a standard for sustainable and efficient ship conversions in the global shipping industry. Full article

Electric vehicles (EVs) rely on a battery pack as their primary energy source, making it a critical component for their operation. To guarantee safe and correct functioning, a Battery Management System (BMS) is employed, which uses variables such as State of Charge (SOC) to set charge/discharge limits and to monitor pack health. In this article, we propose a Multilayer Perceptron (MLP) network to estimate the SOC of a 14.8 V battery pack installed in a robotic vacuum cleaner. Both offline and online (real-time) tests were conducted under continuous load and with rest intervals. The MLP’s output is compared against two commonly used approaches: NARX (Nonlinear Autoregressive Exogenous) and CNN (Convolutional Neural Network). Performance is evaluated via statistical metrics, Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE), and we also assess computational cost using Operational Intensity. Finally, we map these results onto a Roofline Model to predict how the MLP would perform on an automotive-grade microcontroller unit (MCU). A generalization analysis is performed using Transfer Learning and optimization using MLP–Kalman. The best performers are the MLP–Kalman network, which achieved an RMSE of approximately 13% relative to the true SOC, and NARX, which achieved approximately 12%. The computational cost of both is very close, making it particularly suitable for use in BMS. Full article

High-altitude long-endurance (HALE) UAVs require navigation payloads that are both fully autonomous and lightweight. This paper presents a full-parameter calibration method for a dual-axis rotational-modulation RINS/CNS integrated system in which the IMU is mounted on a two-axis indexing mechanism and the reconnaissance camera is reused as the star sensor. We establish a unified error propagation model that simultaneously covers IMU device errors (bias, scale, cross-axis/installation), gimbal non-orthogonality and encoder angle errors, and camera exterior/interior parameters (EOPs/IOPs), including Brown–Conrady distortion. Building on this model, we design an error-decoupled calibration path that exploits (i) odd/even symmetry under inner-axis scans, (ii) basis switching via outer-axis waypoints, and (iii) frequency tagging through rate-limited triangular motions. A piecewise-constant system (PWCS)/SVD analysis quantifies segment-wise observability and guides trajectory tuning. Simulation and hardware-in-the-loop results show that all parameter groups converge primarily within the segments that excite them; the final relative errors are typically ≤5% in simulation and 6–$16\%$ with real IMU/gimbal data and catalog-based star pixels. Full article

In a mother–child underwater bio-inspired robotic system, the equivalent lever arm between the master and slave inertial navigation systems (INSs) varies with launcher attitude changes and structural flexure. This time-varying lever arm introduces hard-to-model systematic velocity errors that degrade the accuracy and filter convergence of velocity difference-based transfer alignment. Traditional rigid body compensation relies on precise, constant lever-arm parameters and fails when booms, launch tubes, or flexible manipulators undergo appreciable deformation or reconfiguration. To address this, we augment a “velocity–attitude joint matching and innovation-based adaptive Kalman filter (AKF)” framework with an attention-based Long Short-Term Memory (LSTM) feed-forward module. Using only a short, real-time Inertial Measurement Unit (IMU) sequence from the slave INS, the module predicts and compensates the velocity bias induced by the lever arm. Numerical simulations of an underwater bio-inspired robot deployment scenario show that, under typical maneuvers (acceleration, turning, fin-flapping, and S-curve), the proposed method reduces the root-mean-square (RMS) misalignment angle error from about 14.5′ to 5.2′ and the RMS installation error angle from 8.8′ to 3.0′—average reductions of about 64% and 66%, respectively—substantially improving the robustness and practical applicability of transfer alignment under time-varying lever arms and flexible disturbances. Full article

Wind power forecasting is critical to renewable energy generation, as accurate predictions are essential for the efficient and reliable operation of power systems. However, wind power output is inherently unstable and is strongly affected by meteorological factors such as wind speed, wind direction, and atmospheric pressure. Weather conditions and wind power data are recorded by sensors installed in wind turbines, which may be damaged or malfunction during extreme or sudden weather events. Such failures can lead to inaccurate, incomplete, or missing data, thereby degrading data quality and, consequently, forecasting performance. To address these challenges, we propose a method that integrates a pre-trained large-scale language model (LLM) with the spatiotemporal characteristics of wind power networks, aiming to capture both meteorological variability and the complexity of wind farm terrain. Specifically, we design a spatiotemporal graph neural network based on multi-view maps as an encoder. The resulting embedded spatiotemporal map sequences are aligned with textual representations, concatenated with prompt embeddings, and then fed into a frozen LLM to predict future wind turbine power generation sequences. In addition, to mitigate anomalies and missing values caused by sensor malfunctions, we introduce a novel frequency-domain learning-based interpolation method that enhances data correlations and effectively reconstructs missing observations. Experiments conducted on real-world wind power datasets demonstrate that the proposed approach outperforms state-of-the-art methods, achieving root mean square errors of 17.776 kW and 50.029 kW for 24-h and 48-h forecasts, respectively. These results indicate substantial improvements in both accuracy and robustness, highlighting the strong practical potential of the proposed method for wind power forecasting in the renewable energy industry. Full article

The internal temperature of a vehicle is influenced by various factors such as the external environment (temperature, solar radiation, and humidity) and the air conditioning habits of the driver. Even when the air conditioning system is set to a specific temperature, the internal temperature can vary depending on the time, weather, and driver’s manipulation of the system. In this study, we developed and evaluated a deep learning-based vehicle cabin temperature prediction system using CAN (Controller Area Network) data collected from the vehicle and temperature data from thermometers installed on the roof and seats of an electric vehicle (EV). The models used in the temperature prediction system were evaluated by applying various deep learning architectures that consider the characteristics of time series data, and their accuracy was measured using the mean absolute percentage error (MAPE) metric. Additionally, a low-pass filter was applied to the prediction results, which reduced the MAPE from 4.2798% to 4.1433%, indicating an improvement in prediction accuracy. Among the deep learning models, the model with the highest performance achieved an MAPE of 3.5287%, corresponding to an approximate error of 0.88 °C at an actual temperature of 25 °C. The results of this study contribute significantly to enhancing the accuracy and reliability of EV interior temperature predictions, enabling more precise simulations, and improving the thermal comfort and energy efficiency of EVs. The proposed temperature-prediction system is expected to contribute to the comfort of EV users and overall performance of vehicles, thereby strengthening the role of EVs as a sustainable means of transportation. Full article

In submerged tunnel construction, the installation accuracy of pre-embedded components directly impacts subsequent engineering quality and operational safety. However, current on-site construction still primarily relies on manual measurement and two-dimensional drawings for guidance, resulting in significant positioning errors, delayed information transmission, and inefficient installation inspections. To enhance the digitalization and intelligence of submerged tunnel construction, this paper proposes a BIM- and AR-based human–machine collaborative management method for pre-embedded components in submerged tunnel segments. This method establishes a site-wide panoramic model as its foundation, enabling intelligent matching of component model geometry and semantic information. It facilitates human–machine interaction applications such as AR-based visualization for positioning and verification of pre-embedded components, information querying, and progress simulation. Additionally, the system supports collaborative operations across multiple terminal devices, ensuring information consistency and task synchronization among diverse roles. Its application in the Mingzhu Bay Submerged Tunnel Project in Nansha, Guangzhou, validates the feasibility and practical utility of the proposed workflow in a pilot case, and indicates potential for further validation in broader construction settings. Full article

The increasing deployment of hybrid renewable energy systems has introduced significant challenges in optimal energy dispatch and load balancing due to the intrinsic stochasticity and temporal variability of renewable sources, along with the multi-dimensional optimization requirements of simultaneously achieving economic efficiency, grid stability, and environmental sustainability. This paper presents GreenMind, a scalable Deep Reinforcement Learning framework designed to address these challenges through a hierarchical multi-agent architecture coupled with Long Short-Term Memory (LSTM) networks for predictive energy management. The framework employs specialized agents responsible for generation dispatch, storage management, load balancing, and grid interaction, achieving an average decision accuracy of 94.7% through coordinated decision-making enabled by hierarchical communication mechanisms. The integrated LSTM-based forecasting module delivers high predictive accuracy, achieving a 2.7% Mean Absolute Percentage Error for one-hour-ahead forecasting of solar generation, wind power, and load demand, enabling proactive rather than reactive control. A multi-objective reward formulation effectively balances economic, technical, and environmental objectives, resulting in 18.3% operational cost reduction, 23.7% improvement in energy efficiency, and 31.2% enhancement in load balancing accuracy compared to state-of-the-art baseline methods. Extensive validation using synthetic datasets representing diverse hybrid renewable energy configurations over long operational horizons confirms the practical viability of the framework, with 19.6% average cost reduction, 97.7% system availability, and 28.6% carbon emission reduction. The scalability analysis demonstrates near-linear computational growth, with performance degradation remaining below 9% for systems ranging from residential microgrids to utility-scale installations with 2000 controllable units. Overall, the results demonstrate that GreenMind provides a scalable, robust, and practically deployable solution for predictive energy dispatch and load balancing in hybrid renewable energy systems. Full article

Directional frequency analysis and recording (DIFAR) is a widely used sonobuoy in modern underwater acoustic monitoring and surveillance. The sonobuoy is installed in the area of interest, collects underwater data, and transmits the data to nearby aircraft for data analysis. In this process, transmission of a large volume of raw data poses significant challenges due to limited communication bandwidth. To address this problem, existing studies on autoencoder-based methods have drastically reduced amounts of information to be transmitted with moderate data reconstruction errors. However, the information bottleneck inherent in these autoencoder-based methods often leads to significant fidelity degradation. To overcome these limitations, this paper proposes a novel autoencoder method focused on the reconstruction fidelity. The proposed method operates with two key components: Gated Fusion (GF), proven critical for effectively fusing multi-scale features, and Squeeze and Excitation (SE), an adaptive Channel Attention for feature refinement. Quantitative evaluations on a realistic simulated sonobuoy dataset demonstrate that the proposed model achieves up to a 90.36% reduction in spectral mean squared error for linear frequency modulation signals compared to the baseline. Full article

Unmanned Aerial Vehicles (UAVs) are promising nodes for Integrated Sensing and Communication (ISAC), but accurate Direction-of-Arrival (DoA) estimation on a small airframe is challenged by platform loading, motion, attitude, and multipath. Traditionally, DoA algorithms have been developed and evaluated for stationary, ground-based (or otherwise mechanically stable) antenna arrays. Extending them to UAVs violates these assumptions. This work designs a six-element Uniform Circular Array (UCA) at 2.4 GHz (radius $\approx 0.5\lambda$) for a quadrotor and introduces a Pose-Aware MUSIC (MUltiple SIgnal Classification) estimator for DoA. The novelty is a MUSIC formulation that (i) applies pose correction using the drone’s instantaneous roll–pitch–yaw (pose correction) and (ii) applies a Doppler correction that accounts for platform velocity. Performance is assessed using data synthesized from embedded-element patterns obtained by electromagnetic characterization of the installed array, with additional channel/hardware effects modeled in post-processing (Rician LOS/NLOS mixing, mutual coupling, per-element gain/phase errors, and element–position jitter). Results with the six-element UCA show that pose and Doppler compensation preserve high-resolution DoA estimates and reduce bias under realistic flight and platform conditions while also revealing how coupling and jitter set practical error floors. The contribution is a practical PA-MUSIC approach for UAV ISAC, combining UCA design with motion-aware signal processing, and an evaluation that quantifies accuracy and offers clear guidance for calibration and field deployment in GNSS-denied scenarios. The results show that, across 0–25 dB SNR, the proposed hybrid DoA estimator achieves <$0.5^{\circ }$ RMSE in azimuth and elevation for ideal conditions and ≈$5^{\circ }$–$6^{\circ }$ RMSE when full platform coupling is considered, demonstrating robust performance for UAV ISAC tracking. Full article

On-field calibration for SINS often uses right hexahedron, but the influence of the structure errors, such as mutual position tolerances towards parallelism or the perpendicularity of two arbitrary planes of the hexahedron, on the calibration accuracy is often neglected. In this paper, a hexahedron structure error model and a comprehensive corresponding SINS calibration error model are developed based on hemispherical resonator gyroscope (HRGs). The proposed method introduces the comprehensive hexahedron errors through defining the normal vectors of the exterior surfaces of the hexahedron. A 24-position calibration scheme is designed to identify accelerometer-related errors, while a 48-rotation scheme is developed to identify gyro-related errors. The complete calibration procedure enables simultaneous identification of hexahedron structure errors, installation misalignments, scale factor errors, and biases. Experimental validation is conducted using a high-precision three-axis turntable, which simulates the hexahedron structure errors. The results show that the proposed method significantly improves the calibration accuracy of both accelerometers and HRGs compared with traditional methods. Furthermore, it reduces the accuracy requirements for the hexahedron structure, thus lowering the cost of SINS on-field calibration. Full article

In manufacturing face-hobbing hypoid gears, the coupling between tooth flank errors and installation errors has a significant impact on dynamic meshing behavior, yet quantitative models for their synergistic effects remain scarce. This study elucidates the combined effects of three-dimensional (3D) installation errors and real tooth flank deviations on transmission error. First, a geometric model of the real tooth flank, incorporating midpoint pitch deviation, is established based on theoretical flank equations and coordinate transformations. Then, a finite element model integrating 3D installation errors is developed. Finally, the combined effects of installation errors and real tooth flanks on meshing performance are analyzed. Results reveal a dual role of installation errors: when compensating for midpoint pitch deviation, the peak-to-peak transmission error (PPTE) decreases by 3.78%, while the contact pattern length and area increase. Under certain conditions, despite a 26.28% increase in PPTE, the contact pattern length grows by 2.29%, accompanied by a notable reduction in maximum contact stress on the tooth flanks. Full article

Effective training is essential for addressing the continuous requirement for enhancing productivity and safety in construction. Virtual reality (VR) has emerged as a powerful tool for simulating site environments with high fidelity. While previous studies have explored the potential of VR in construction training, there is potential to incorporate advanced construction theories, such as lean principles, which are critical for optimizing work processes and safety. Thus, this study aims to develop an integrated VR-lean training system that integrates lean principles into traditional VR training, focusing on improving productivity and ergonomic safety—two interrelated challenges in construction. This study developed a virtual training environment for scaffolding installation, employing value stream mapping—a key lean tool—to guide trainees in eliminating waste and streamlining workflows. A before-and-after experimental design was implemented, involving 64 participants randomly assigned to non-lean VR or integrated VR-lean training groups. Training performance was assessed using productivity and ergonomic safety indicators, while a post-training questionnaire evaluated training outcomes. The results demonstrated significant productivity improvements in integrated VR-lean training compared to non-lean VR training, including a 12.3% reduction in processing time, a 21.6% reduction in waste time, a 20.8% increase in productivity index, and an 18.4% decrease in number of errors. These gains were driven by identifying and eliminating waste categories, including rework, unnecessary traveling, communication delays, and idling. Additionally, reducing rework contributed to a 7.2% improvement in the safety risk index by minimizing hazardous postures. A post-training questionnaire revealed that training satisfaction was strongly influenced by platform reliability and stability, and user-friendly, easy-to-navigate interfaces, while training effects of the integrated training were enhanced by before-session on waste knowledge and after-training feedback on optimized workflows. This study provides valuable insights into the synergy of lean principles and VR-based training, demonstrating the significant impact of lean within VR scenarios on productivity and ergonomic safety. The study also provides practical recommendations for designing immersive training systems that optimize construction performance and safety outcomes. Full article