Search Results (328)

Rural logistics faces persistent challenges such as high distribution costs, dispersed demand, and limited transport infrastructure, which hinder efficient last-mile delivery. To address these issues, this study proposes a bus–heterogeneous drone collaborative delivery system that integrates the fixed-route coverage of rural buses with the flexibility of multiple types of drones. The proposed system enables synchronized operations between buses and drones, where buses serve as mobile depots for drone launching and recovery along predefined routes. A mixed-integer programming (MIP) model is developed to jointly optimize bus schedules and drone routing under spatiotemporal synchronization constraints, considering drone endurance, payload capacity, energy consumption, and bus departure times. Due to the NP-hard nature of the problem, an Improved Genetic Algorithm (IGA) is designed, incorporating a three-layer encoding scheme, adaptive crossover and mutation operators, and a local search repair mechanism to enhance convergence and solution feasibility. A real-world case study from Baihe County, Shaanxi Province, China, is conducted to evaluate the performance of the proposed model and algorithm. Comparative experiments under the reported case-study setting show that the proposed bus–heterogeneous drone system achieves notable cost reduction and improved overall delivery performance. Sensitivity analyses further confirm the robustness of the model with respect to drone endurance, drone payload capacity, and bus stop quantity. This research contributes to the literature by bridging the methodological gap between truck–drone coordination and bus-based collaborative delivery, offering an innovative framework for sustainable rural logistics and multi-modal last-mile optimization. Full article

The accurate and efficient acquisition of rock mechanical properties is critical for ensuring the safety and efficiency of underground engineering construction. Traditional laboratory tests are characterized by long cycles, high costs, and an inability to reflect in situ mechanical properties, while existing deep learning models based on while-drilling data suffer from poor noise robustness, insufficient deep feature extraction, and low accuracy in synchronous multi-parameter prediction. To address these limitations, this paper proposes a hybrid deep learning model (CNN-LSTM-MoE) combining a convolutional neural network (CNN), a long short-term memory network (LSTM), and a mixture of experts (MoE) system. The model enables intelligent prediction of elastic modulus, Poisson’s ratio, and yield stress from while-drilling parameters. The proposed model integrates CNN’s local feature extraction capability, LSTM’s temporal dependency modeling capability, and the multi-expert dynamic fusion mechanism of MoE. Furthermore, it incorporates physical constraints from rock fragmentation mechanics and an adaptive multi-objective loss weight optimization strategy to comprehensively enhance the multi-parameter synchronous prediction performance. Experimental results demonstrate that the proposed model achieves coefficients of determination (R²) of 0.8965 for elastic modulus, 0.9193 for Poisson’s ratio, and 0.9813 for yield stress on the laboratory validation dataset, with a mean squared error (mse) of 4.0720. Its prediction performance significantly outperforms benchmark models such as TCN and Transformer time-series architectures. Ablation studies further validate the critical role of the integrated LSTM and MoE modules in improving model accuracy, with the MoE module contributing an average R² improvement of approximately 24%. This study not only provides an effective method for high-precision acquisition of rock mechanical parameters while drilling, but also offers a feasible solution based on numerical simulation for data augmentation to address the common issue of scarce labeled data in deep learning applications within engineering fields. Full article

Due to the complex structure and large number of nodes in distribution networks, it is difficult to achieve full coverage of synchronous phasor measurement units (μPMUs) in actual engineering projects, resulting in limited available measurement data. To address this issue, this paper proposes a distribution network fault location method based on limited measurement information. First, the distribution characteristics of the node positive-sequence voltage measurement deviation (NPSVMD) following a fault occurrence are analyzed. On this basis, a principle for faulted line identification is established by exploiting the common-path property between the measurement point exhibiting the maximum NPSVMD and the reference node. Furthermore, the fault current is equivalently derived using the nodal voltage variation equations (NVVE), and a distance estimation function is constructed by incorporating the NPSVMD values at the measurement nodes on both sides of the faulted line, thereby enabling accurate determination of the fault location. Simulations on the IEEE 33-bus distribution system verify that the proposed method can accurately identify the faulted line and achieve high-precision distance estimation using limited measurement information, demonstrating strong robustness and superior adaptability. Full article

Coal-mine-gas-monitoring data exhibits missing phenomena due to the harsh underground operating environment. Accurate imputation of missing values in gas-monitoring sequences serves as a key data foundation for guaranteeing the continuity of gas data, enhancing the reliability of disaster early warning, and improving the accuracy of mine safety situation analysis and judgment. Aiming at the prevalent random and segmented missing issues in coal-mine-gas-monitoring time-series data, and the limitation that existing imputation methods struggle to accurately capture the nonlinear spatiotemporal correlations and long-range temporal dependencies of such data, this study proposes a missing data imputation method for coal mine gas time-series data based on the Spatio-Temporal Graph Attention Network—Echo State Network (ST-GAT-ESN). Firstly, this method extracts temporal features of the gas concentration sequence using a Gated Recurrent Unit (GRU). Subsequently, it models multiple monitoring points as graph nodes through a Graph Attention Network (GAT), constructs an adjacency matrix based on airflow propagation relationships, and adaptively learns the spatial dependency weights between monitoring points to realize the deep fusion of spatiotemporal features. Finally, it designs a dual-channel Echo State Network (ESN), synchronously inputs the spatiotemporal fusion features of the missing regions before and after, efficiently fits the nonlinear evolutionary trend of the data by virtue of the echo state property of the reservoir, and solves the output layer weights through ridge regression to achieve accurate imputation of missing values. Experimental results demonstrate that, compared with the single-ST-GAT-ESN, ESN, and ARIMA models, the proposed method achieves the optimal imputation performance in both random and segmented missing scenarios within the missing rate range of 5–50%. The three evaluation metrics—Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE)—are reduced by 30–80% compared with the benchmark models. Moreover, the imputation curve achieves the best fitting performance with the ground-truth curve at a 50% segmented missing rate. This study confirms that the ST-GAT-ESN model effectively enhances the adaptability and robustness to complex missing patterns via spatiotemporal collaborative modeling and a dual-channel fusion mechanism, providing a high-precision and highly stable technical solution for ensuring the integrity of coal-mine-gas-monitoring data, and also provides theoretical references and engineering insights for the missing-value processing of industrial time-series monitoring data. Full article

Sea surface height anomaly (SSHA) observations from Surface Water and Ocean Topography (SWOT) provide a new opportunity for identifying crest lines of internal solitary waves (ISWs). However, L3 LR Unsmoothed SSHA is often affected by residual large-scale trends, rainfall contamination, and stripe noise, which limit segmentation performance. To address this issue, we propose an automatic segmentation workflow for SWOT SSHA. The workflow first applies Gaussian low-pass filtering for scale separation to extract high-frequency SSHA, then uses Otsu adaptive thresholding to segment ISW signals, and finally removes false targets using morphological geometric constraints. Validation based on 230 SWOT images from the northern South China Sea shows that, compared with the conventional method based on subtracting reanalysis fields, the proposed method increases the contrast-to-noise ratio (CNR) of high-frequency SSHA by 1.35 on average (Std = 0.99) and improves signal gain by 13.65 dB on average (Std = 7.71 dB). The method remains robust under complex conditions, including strong typhoons, severe stripe noise, weak shelf signals, and multi-wave interference. In some cases, quasi-synchronous optical imagery further confirms the authenticity of the extracted crest lines. Full article

Although model predictive control (MPC) has been successfully applied in permanent magnet synchronous motor (PMSM) speed control systems, its performance can degrade under high-dynamic operating conditions and uncertain load disturbances. To address these issues, a continuous-time model predictive control (CTMPC) framework is proposed to improve speed tracking accuracy and robustness. From a symmetry perspective, the proposed method leverages the orthogonal symmetry of Laguerre basis functions and the structural invariance of the continuous-time PMSM speed dynamics, enabling a compact and balanced representation of the control trajectory while preserving prediction accuracy. Specifically, a finite set of orthogonal Laguerre functions, combined with an adaptive smoothing factor and soft constraint mechanism, is employed to reduce computational complexity without compromising performance. In addition, a nonlinear disturbance observer is integrated to achieve real-time estimation and feedforward compensation of load torque variations, thereby enhancing disturbance rejection capability. Comprehensive simulation results demonstrate that the proposed approach significantly improves tracking precision, reduces overshoot, and shortens recovery time following load disturbances compared to conventional MPC methods. Full article

Accurate forecasting of energy consumption in sensor-rich environments remains challenging due to strong inter-sensor dependencies, temporal variability, and heterogeneous sensor behavior. This paper proposes a lightweight and interpretable multi-sensor fusion framework for short-term energy consumption forecasting. The heterogeneous sensor dataset is first preprocessed to handle missing values, outliers, and temporal misalignment, followed by synchronization of the multivariate signals on a common timeline to enable consistent learning. The proposed framework systematically investigates multiple strategies for exploiting information from synchronized multi-sensor data without performing explicit feature elimination or time-lag engineering. In particular, three fusion paradigms are considered: (i) Early Fusion, where all sensor measurements are jointly used as input features for a multivariate regression model; (ii) Late Fusion, where individual sensor predictors are trained independently and their outputs are combined using reliability-based weighting; and (iii) an attention-inspired fusion strategy, in which adaptive weights are assigned to sensor-level predictions based on their predictive reliability estimated from training errors and normalized via a softmax function. In addition, classical machine learning models including Random Forest (RF), Support Vector Regression (SVR), and Gradient Boosting (GB) are evaluated under the same experimental conditions to provide a consistent benchmark. Experimental results on a real-world building energy monitoring dataset consisting of nine heterogeneous sensors demonstrate that multi-sensor fusion approaches consistently improve forecasting performance compared to single-model baselines. Among the evaluated strategies, Late Fusion provides stable performance across strongly correlated loads, while the attention-inspired fusion strategy exhibits improved robustness when handling sensors with varying predictive reliability. To ensure robustness and reproducibility, results are reported using multiple chronological validation splits, with performance evaluated in terms of RMSE, MAE, and $R^2$ along with statistical measures including standard deviation and confidence intervals. The proposed framework provides a practical balance between predictive accuracy, interpretability, and computational efficiency, making it suitable for smart building energy management and real-world deployment scenarios. Full article

To address the current surge and speed fluctuation that occur when high-speed surface-mounted permanent magnet synchronous motors (HSPMSMs) switch from I-f open-loop control to sensorless closed-loop control, an adaptive switching method based on the cosine of the angle error is proposed. In this method, the angle error between the I-f open-loop reference angle and the angle estimated by the sensorless observer serves as the regulating variable, and its cosine is introduced to construct an adaptive attenuation factor, so that the rate of current reduction can vary continuously with the angle error. Specifically, a relatively large rate of current reduction is generated in the early stage of the switching process, when the angle error is large, to shorten the switching time. As the angle error decreases, the rate of current reduction is gradually lowered, allowing the current regulation process to better match the convergence process of the angle error and thereby improving switching stability. The proposed switching method is validated on a high-speed air compressor experimental platform. The experimental results show that the proposed method can shorten the switching time, reduce the current surge and speed fluctuation at switching, and exhibit good robustness under varying operating conditions. Full article

To satisfy the stringent functional-safety requirements of steer-by-wire steering systems for advanced autonomous driving, this paper proposes a novel dual-motor collaborative fault-tolerant control strategy. The proposed approach aims to overcome the insufficient fault tolerance of conventional single-motor architectures, as well as the limited dynamic response and disturbance-rejection capability observed in existing multi-motor schemes. The key contribution is an integrated control framework consisting of two components: (i) dual-motor torque synchronization achieved via a fuzzy-PID–based mean-deviation coupling method, and (ii) a super-spiral sliding-mode control law optimized by an adaptive differential-evolution algorithm to enhance the dynamic performance and robustness of the current loop. Experimental results demonstrate that, relative to a non-synchronized baseline, the proposed strategy reduces the inter-motor current mismatch by 8.1–78.6% across multiple operating conditions. Moreover, following fault occurrence, the proposed Self-Adaptive Differential-Evolution-algorithm-based Super-Twisting Sliding-Mode Control method shortens the stabilization time by 50–70%, 9–20%, and 16.7% compared with conventional PID, Super-Twisting Sliding-Mode Control methods, and classical $H_{\infty }$ robust control, respectively. Overall, the developed solution meets functional-safety requirements and provides a highly reliable steering-actuation mechanism for advanced autonomous driving applications. Full article

To address the deteriorated control performance of permanent magnet synchronous motor (PMSM) drive systems for new energy vehicles (NEVs) under complex conditions caused by multi-source disturbances (internal parameter perturbations and external load mutations), this paper proposes an improved terminal integral sliding mode control (ITISMC-ADERL) strategy integrating a piecewise adaptive terminal integral sliding mode surface and an ADERL. The proposed sliding mode surface adopts interval-adaptive switching between high- and low-order power terms, completely eliminating singularity and integral saturation defects of traditional terminal sliding mode control while ensuring fast convergence, and achieving an optimal structural balance between convergence speed and chattering suppression. The state-dependent ADERL leverages the synergy of error-sliding variable coupled dynamic gain adjustment and variable exponential power compensation, realizing dual-mode adaptive switching of “strong driving for fast approaching far from the sliding surface, weak gain for smooth regulation near the sliding surface”, which significantly improves control accuracy and anti-disturbance robustness. The finite-time convergence of the closed-loop system is rigorously proved via Lyapunov stability theory. Full-operating-condition comparative tests on a TMS320F28379D DSP platform show that the proposed strategy outperforms SMC-ERL, ISMC-ERL and ITISMC-ERL in all test scenarios (no-load startup, acceleration/deceleration, sudden load changes, flux linkage perturbation), meeting the requirements of high-performance NEV drive systems and possessing important engineering application potential. Full article

The Industrial Internet of Things (IIoT) has become a cornerstone of modern industrial automation, enabling real-time monitoring, intelligent decision-making, and large-scale connectivity across cyber–physical systems. However, the growing scale, heterogeneity, and dynamic behavior of IIoT environments significantly expand the attack surface and challenge the effectiveness of conventional security mechanisms. In this paper, we propose DeepSense, a hybrid and adaptive anomaly and intrusion detection framework specifically designed for resource-constrained and heterogeneous IIoT deployments. DeepSense integrates three complementary components: DataSense, a realistic data pipeline and experimental testbed supporting synchronized sensor and network data processing; RuleSense, a lightweight rule-based detection layer that provides fast, deterministic, and interpretable anomaly screening at the edge; and NeuroSense, a learning-driven detection module comprising an adaptive ensemble of 22 machine learning and deep learning models spanning classical, neural, hybrid, and Transformer-based architectures. NeuroSense operates as a second detection stage that validates suspicious events flagged by RuleSense and enables both coarse-grained and fine-grained attack classification. To support rigorous and practical assessment, this work further introduces a comprehensive performance evaluation framework that extends beyond accuracy-centric metrics by jointly considering detection quality, latency, resource efficiency, and detection coverage, alongside an optimization-based process for selecting Pareto-optimal model ensembles under realistic IIoT constraints. Extensive experiments across diverse detection scenarios demonstrate that DeepSense exhibits strong generalization, lower false positive rates, and robust performance under evolving attack behaviors. The proposed framework provides a scalable and efficient IIoT security solution that meets the operational requirements of Industry 4.0 and the resilience-oriented objectives of Industry 5.0. Full article

This study proposes a robust data-driven control framework, LSTM-MPC, designed to enhance the velocity stabilization of Autonomous Underwater Vehicles (AUVs) operating under stochastic marine disturbances. Traditional control methods often struggle with the highly nonlinear and time-varying hydrodynamics of irregular waves. To address this, we employ a Long Short-Term Memory (LSTM) recurrent neural network to capture complex temporal dependencies and provide accurate multi-step-ahead velocity predictions. These predictions are integrated into a Model Predictive Control (MPC) scheme, which optimizes control actions while respecting actuator constraints. A key contribution is the integration of an error-triggered online learning mechanism. Utilizing run-time weight synchronization via MATLAB Coder, the framework dynamically adapts to plant mismatches and high-frequency MEMS noise without an explicit analytical model. The architecture was validated using experimental data from a Pixhawk/ArduSub baseline. Results demonstrate that, under these stochastic conditions, the data-driven approach significantly outperforms the standard PID-based baseline. While adaptive PID variants offer improvements, the suggested framework drastically reduces tracking errors in rotational axes while maintaining high precision in translational velocities. This research confirms that adaptive, data-driven strategies can effectively bridge the gap between simulation and real-world deployment, offering a scalable solution for robust AUV autonomy in unpredictable environments. Full article

Flood disasters often disrupt road networks and severely reduce ground accessibility, hindering the timely delivery of emergency supplies. To address this challenge, this study investigates a collaborative routing problem involving multiple vehicles and multiple UAVs under road disruptions and formulates a mixed-integer linear programming model that jointly minimizes mission makespan and priority-weighted response time for critical nodes. The model explicitly captures road feasibility, vehicle speeds affected by flood depth, multi-point UAV sorties, payload-dependent energy consumption, and vehicle–UAV spatiotemporal synchronization. To balance solution quality and scalability, a dual-track solution framework is developed: exact optimization is used for small instances, while a adaptive large neighborhood search algorithm with embedded dynamic programming is designed for larger instances. A case study based on the 2024 Guangdong flood with 135 demand points shows that the heuristic can obtain high-quality solutions efficiently and outperforms time-limited MILP solutions on large instances. Comparative experiments further demonstrate that multi-point sorties, integrated coordination, and embedded sortie refinement are all crucial to performance improvement. Sensitivity analysis indicates that setting the trade-off coefficient α within 0.2–0.8 provides a robust balance between overall mission efficiency and timely response to critical nodes. Full article

Accurate measurement of ocean wave parameters is paramount for offshore engineering design and marine environmental monitoring. Distributed pressure sensing technology provides a robust data foundation for analyzing the spatio-temporal characteristics of wave fields through synchronized observations at multiple stations. However, multi-sensor data exhibit high-dimensional spatio-temporal coupling, posing significant challenges for traditional single-point signal processing methods in capturing the topological associations between measurement sites. To address these limitations, this study develops a framework for spatio-temporal feature modeling and wave height reconstruction based on Graph Neural Networks (GNNs). The proposed framework integrates the spatial configuration of sensor arrays with graph-theoretic topological representations. By fusing geometric distances and signal correlations, an adaptive adjacency matrix is constructed to establish a dynamically adjustable graph structure. On the feature extraction level, a spatio-temporal fusion method combining multi-scale graph convolutions and gated temporal modeling is proposed. The experimental results obtained on the Blancs Sablons Bay multi-sensor dataset demonstrate that the proposed method significantly outperforms traditional approaches, achieving lower prediction errors and validating the effectiveness of graph-structured modeling in distributed wave sensing. Full article

Aiming at solving the problems of severe chattering, irreconcilable convergence speed, and steady-state accuracy in traditional sliding-mode control (SMC) for the speed regulation system of permanent magnet synchronous motors (PMSMs) in rail transit traction, as well as its poor adaptability to complex disturbances such as frequent acceleration/deceleration and sudden load changes under traction conditions, a sliding-mode control strategy integrating improved piecewise terminal integral sliding-mode control (IPTISMC) with an adaptive smooth exponential reaching law (ASERL) is proposed. Taking the surface-mounted PMSM for rail transit traction as the research object, the d-q axis mathematical model is established, and a terminal integral sliding surface with a piecewise nonlinear function is designed, which resolves the problems of complex solutions and steady-state errors of the traditional sliding surface through a piecewise cooperative mechanism for large and small error stages. The designed ASERL realizes adaptive gain adjustment based on the state variables of the sliding surface and replaces the sign function with the hyperbolic tangent function, thus alleviating the inherent contradiction between convergence and chattering in the fixed-gain reaching law. The global stability and finite-time convergence of the system are rigorously proved based on Lyapunov stability theory. Furthermore, comparative experiments involving no-load operation, acceleration and deceleration, sudden load application and removal, and parameter perturbation are carried out on a DSP experimental platform for SMC-ERL, ISMC-ERL, IPTISMC-ERL and the proposed IPTISMC-ASERL. Experimental results show that the proposed IPTISMC-ASERL strategy can significantly improve the dynamic response and steady-state control accuracy of the PMSM speed regulation system for rail transit traction, effectively suppress chattering to enhance riding comfort, and simultaneously strengthen the system’s anti-disturbance capability and parametric robustness. It can fully meet the engineering control requirements for high precision and high stability of PMSMs in rail transit traction applications. Full article