Search Results (790)

Accurate State-of-Health (SOH) prediction is essential for deploying retired electric vehicle batteries into reliable second-life energy storage systems. However, this task is challenged by sparse and noisy operational data from onboard Battery Management Systems (BMS). This study systematically evaluates a spectrum of deep learning architectures for SOH forecasting under BMS-style data constraints derived from laboratory cycling data: a BiLSTM on aggregated cycle statistics (Model A), preliminary zero-shot transfer to a single unseen cell (Model B), a waveform BiLSTM with full intra-cycle voltage, current, and temperature trajectories (Model C), a baseline TCN (Model D) and a probabilistic TCN-GPR hybrid (Model E). All models are constrained to identical low-fidelity BMS-style variables extracted from the NASA battery aging dataset. Model C achieves the lowest point accuracy error of 0.46% ± 0.18% MAE across five random seeds, demonstrating that high-resolution waveform inputs capture degradation signatures, notably voltage plateau morphology, transient dynamics, and implicit SOC information, that aggregated features irreversibly lose. Model D using the same waveform inputs and evaluation protocol as Model C, achieves a MAE of 2.99% at a single seed, providing direct architectural comparison evidence that the BiLSTM’s position-sensitive temporal summarization outperforms GlobalAveragePooling1D under these conditions. Model E achieves a higher MAE of 2.12% ± 0.33% but uniquely provides calibrated predictive distributions of 99.4% ± 1.2% coverage, NLL = −1.877 ± 0.038, with approximately uniform 95% predictive intervals (mean width 19.83% SOH across 34 test cycles at seed = 42), reflecting the near-constant posterior variance produced by the large optimized GPR length-scale under the frozen two-stage training design. A paired t-test confirms that Model C statistically significantly outperforms Model E on point accuracy (p < 0.01). Isotonic regression recalibration reduces mean calibration error from 0.138 to 0.010, demonstrating that shape-level miscalibration is correctable post hoc. The central implication for second-life battery deployment is a clear accuracy–uncertainty trade-off: Model C is preferred when point estimates suffice, while Model E is essential for risk-aware decisions requiring confidence intervals. Full article

Carbon pricing can change manufacturers’ material choices, while the costs of managing the residual waste remain geographically uneven. We formulate a manufacturer–regulator bilevel model for a household plastic-waste closed-loop supply chain with quantity-dependent recycled-bale prices, activity-specific carbon accounts, physical interregional waste routing, and a proportional regional cost-burden standard. The lower level is explicitly a single coordinating-regulator linear program rather than a game among independent regions. Its primal constraints, dual constraints, and strong-duality equality are embedded in the manufacturer problem; binary-continuous products are exactly linearized using the manufacturer’s SOS1 price-grid variables. Thus, every reported policy point is obtained from the same 12-region mixed-integer equilibrium formulation. Across 36 central policy combinations, HiGHS reports a zero mixed-integer programming gap, and the largest feasibility and optimality residual is $5.24\times {10}^{-8}$. Raising the carbon tax from 0 to 10 USD/tCO₂ increases the real recycling rate (RRR) from 15.33% to the bale-capacity limit of 29.85% and reduces physical emissions by 11.64%. Tightening the allowed regional burden deviation from 25% to 5% reduces the standard deviation of normalized residual-waste cost burden by 77.89% and interregional residual-waste transfers by 77.05%, but does not change the RRR. This zero-recycling effect overturns the earlier assumption-driven result: a pure routing-based cost-balancing rule cannot mechanically stimulate the manufacturer’s recycled-input demand. A global analysis of 300 parameter sets and five independent regional samples re-solves 1800 equilibrium models; all have a zero solver gap and pass the residual audit. Carbon-induced RRR increases have a median of 17.03 percentage points, while strict-versus-loose burden-threshold changes in RRR are zero in every set. The results distinguish carbon efficiency, regional cost incidence, and fiscal incidence and show that policy complementarity must be demonstrated through endogenous decision links rather than imposed response functions. Full article

Emergency response missions employing heterogeneous multi-UAVs are challenged by both the tight coupling between task assignment and motion control and the inherent difficulty in obtaining full probability distributions of stochastic disturbances. In practice, only partial moment information—typically the mean, covariance, and support set—can be estimated. To address this, the paper proposes a distributionally robust integrated “decision–control” framework. A bi-level optimization model is established: the upper level minimizes the maximum mission completion time across all platforms, while the lower level solves minimum-time optimal control problems under kinematic constraints, with the two levels coupled through task execution times. Given only the mean, covariance, and support set of disturbances, an ambiguity set is constructed, and by leveraging duality theory and semidefinite programming, the distributionally robust chance constraints on site reachability are equivalently transformed into deterministic safety margins. A two-stage trajectory planning method is further designed to decouple accumulated time estimation from robust constraint enforcement, ensuring computational tractability. Simulation results across multiple disturbance configurations show that, whereas deterministic planning yields an overall mission success rate of only about 0.7%, the proposed framework consistently achieves success rates above 99.9% and effectively balances workload among multiple UAVs. These results validate the practical benefit of the framework in providing reliable emergency response plans under limited distributional information. Full article

With the rapid penetration of electric vehicles (EVs) and renewable energy generation in distribution networks, the coordinated scheduling of flexible EV loads and uncertain renewable resources has become a critical research focus in modern power systems. This study investigates the collaborative optimal dispatch of thermal units, EVs, and renewable power generation. Different from conventional closed-loop game-based bi-level optimization, this paper constructs a transmission–distribution integrated scheduling framework and proposes a sequential hierarchical progressive optimization strategy for EV charging and discharging dispatch to fully tap the cross-level coordination potential of power grids. The upper transmission layer optimizes the joint operation of thermal units, wind power, and photovoltaic units to minimize the overall power supply cost, where the inequality power balance constraint is reasonably adopted to reserve power regulation margin for renewable fluctuation and meet practical engineering operation requirements. To effectively address the severe uncertainty of renewable power output without relying on accurate probability distribution information, information gap decision theory (IGDT) is employed to realize robust scheduling with risk-averse and opportunity-seeking decision adaptability. In the lower distribution layer, a theoretically grounded nodal electricity price (NEP) model integrating node loss sensitivity (NLS) and node load rate (NLR) is applied to substitute iterative power flow calculation, which realizes the spatial optimal allocation of EV charging and discharging nodes while significantly improving computational efficiency. The proposed framework comprehensively minimizes network power loss and user charging cost. Finally, extensive simulations based on the IEEE 33-node distribution system verify the effectiveness, computational superiority, and robustness of the proposed sequential hierarchical coordinated scheduling strategy. Full article

With the increasing penetration of wind and photovoltaic generation, microgrids are playing an increasingly important role in promoting renewable energy accommodation, enhancing operational flexibility, and enabling low-carbon energy management. However, the strong uncertainty of renewable generation and load demand, together with the coupling effects of electricity, hydrogen, and carbon markets, poses significant challenges to the optimal planning and operation of microgrid energy storage systems. To address these issues, this paper proposes a bi-level optimal sizing framework for an electric–hydrogen hybrid energy storage system (EHH-ESS) in a microgrid under multi-market coupling. First, typical wind–solar–load scenarios are generated using a Wasserstein generative adversarial network with gradient penalty (WGAN-GP), so as to capture the stochastic characteristics and temporal correlations of renewable generation and load demand. Then, a multi-market coupling index (MCI), integrating electricity price, hydrogen price, and carbon price signals, is constructed to characterize time-varying economic and low-carbon operating incentives and to guide coordinated dispatch decisions. On this basis, a bi-level multi-objective optimization model is established. The upper level determines the optimal capacities of battery storage, electrolyzers, fuel cells, and hydrogen tanks, while the lower level performs hourly coordinated operation of the microgrid under multi-market conditions. The model considers annual equivalent total cost, renewable energy curtailment rate, and carbon emissions as objective functions, and is solved using the NSGA-III algorithm. Compared with the no-storage benchmark, the proposed scheme improves the annual operating economics and renewable-energy accommodation under the studied market conditions. The proposed method significantly reduces annual operating cost and improves renewable energy accommodation. However, under the current carbon price and grid emission factor settings, the optimal economic solution increases carbon emissions relative to the baseline, indicating a trade-off between economic arbitrage and low-carbon operation. Full article

Pathological gait classification plays an important role in objective motor function assessment, early clinical screening, and rehabilitation evaluation. However, traditional clinical gait assessment methods are highly dependent on expert experience and may fail to detect subtle gait abnormalities. Moreover, existing inertial measurement unit (IMU)-based gait recognition methods often rely on single-sensor configurations or single-scale temporal models, limiting their ability to capture complex pathological gait patterns. In this study, a convolutional neural network–bidirectional long short-term memory–temporal convolutional network (CNN-BiLSTM-TCN) multi-branch feature fusion framework was proposed for pathological gait classification using a publicly available clinical multi-inertial measurement unit dataset containing 260 subjects. The proposed model employs three parallel branches to extract local instantaneous motion variations, continuous temporal dynamics, and relatively broader temporal dependencies within the 2 s input window, respectively, followed by feature-level fusion and end-to-end joint optimization. Experimental results show that the proposed model achieves a test accuracy of 0.9818 and an F1-score of 0.9700, outperforming conventional machine learning methods, single-branch models, voting-based fusion methods, and other temporal models, including Support Vector Machine (SVM), Temporal Convolutional Network (TCN), and Convolutional Neural Network-long short-term memory (CNN-LSTM). Five repeated experiments with stratified random splits demonstrate minimal performance variation, indicating good robustness and stability. The proposed framework provides a potential approach for pathological gait screening and quantitative rehabilitation assessment. Full article

Automated pulmonary auscultation demands rapid and reliable anomaly detection. Contemporary deep learning frameworks frequently face deployment barriers due to their reliance on memory-intensive Transformer mechanisms and high-cost processing hardware. Addressing this limitation, the present study introduces the Neuro Scatter Mamba Kolmogorov–Arnold Neural Network (NSMK-Net), a lightweight, Transformer-free architecture. The model integrates 1D Wavelet Scattering, bi-directional Selective State Space Models (Mamba), and Kolmogorov–Arnold Networks (KAN). By substituting quadratic self-attention with continuous-time differential discretization, the framework achieves very good computational efficiency under severe hardware constraints. Model optimization followed an eco-friendly “Green-AI” methodology, successfully converging on a standard 4 GB VRAM graphics unit. Regarding real-world deployment, the finalized architecture can be considered as a possible candidate for future “Edge-AI” applications, because it requires only 0.34 MB of parameter storage (89,342 parameters) and executes inference in approximately 48 milliseconds per respiratory cycle. Evaluated on the SPRSound dataset, the proposed model achieved a cycle-level accuracy of 84.67% (Macro-F1: 0.48). When tested under the strict official 60/40 partition of the ICBHI 2017 dataset, the network delivered a global accuracy of 41.56% (Macro-F1: 0.31) alongside an official reported ICBHI Score of 49.38%. These metrics indicate a stable detection capability when processing highly imbalanced clinical data. By replacing fixed activation nodes with learnable edge non-linearities and utilizing linear sequence memory, this new structural approach reduces the dependency on high-end hardware for medical acoustic processing. Full article

Background: Esophageal squamous cell carcinoma (ESCC) remains highly aggressive and continues to limit clinical treatment for substantial cancer-associated morbidity and mortality worldwide. Despite advances in therapeutic interventions the lack of effective molecularly targeted treatments continues to restrict clinical management beyond conventional chemotherapy and radiotherapy. Among these therapeutic targets the ribosomal S6 kinase 4 (RSK4) has gained considerable attention because of its critical involvement in ESCC progression, survival and proliferation, suggesting its potential as a potential target for anticancer drug development. Methods: A series of thiazole-clubbed pyrimidine linked hydrazone hybrids (1–14) were synthesized via 4-aminothiazole-5-carbohydrazide functionalized intermediates and fully characterized and evaluated for their inhibitory activity against RSK4. Results: Biological assessment demonstrated that the synthesized analogues exhibited remarkable potency, with IC₅₀ values between 15.32 ± 1.35 and 54.61 ± 2.17 nM compared with the reference inhibitor BI-D1870 (IC₅₀ = 33.16 ± 1.34 nM). Among the evaluated compounds, 2, 8, 9, 13 and 14 emerged as the most potent candidates and showed pronounced activity towards RSK4. For further insights into the molecular basis of their activity the lead candidates were subjected to computational investigations, such as molecular docking, molecular dynamics simulations, in silico ADMET and ProTox-3.0 characterization. The computational analyses provided structural and pharmacological insights into experimentally observed RSK4 inhibitory activity, like predicted interactions, stability dynamically and preliminary ADMET/toxicity characteristics. This study supports the need for further optimization and experimental validation of the identified RSK4 active lead candidates. Conclusions: These findings highlight the thiazole-clubbed pyrimidine-linked hydrazone scaffold as a potential chemotype for promising scaffolds targeting RSK4 lead discovery, and the identified candidates warrant further investigation into ESCC cellular models to establish anticancer efficacy and pathway-level activity. Full article

Graphite ore grade sorting is a key step toward intelligent mineral processing; however, it faces three representational contradictions: ambiguous classification posteriors at grade boundaries, asymmetric multi-scale feature interaction, and the mismatch between class-agnostic self-distillation assignment and sample-level difficulty. Targeting these, this paper adopts D-FINE as the baseline and introduces three decoupled improvements at its decoder, encoder, and criterion layers. (1) Boundary-Grade-aware Distribution Refinement (BG-FDR) online identifies boundary samples via the Top-2 classification score gap and modulates regression-distribution refinement, yielding +2.69 percentage points in mAP@0.5 with zero additional trainable parameters. (2) Bidirectional Feature Pyramid with Global–Local Spatial Attention (BiFPN-GLSA) builds a learnable weighted bidirectional multi-scale fusion path. (3) Difficulty-Aware Decoupled Distillation with Wise-Inner-Shape-IoU (DADD+Wise-IoU) imposes class- and sample-level difficulty-aware constraints. In the integrated full model, this increases Precision from 66.21% to 71.43% (+5.22 pp), F1 from 73.57% to 77.57%, and mean IoU from 97.81% to 98.35%, while false positives drop by 19.6%; the only parameter overhead (+3.84M) comes from BiFPN-GLSA, with BG-FDR and DADD adding effectively no network weights. Ablation on a self-built 3800-image dataset reveals a non-monotonic AP–Precision relationship: the mAP-optimal configuration (BG-FDR+BiFPN-GLSA, 94.17%) and the Precision-optimal one (DADD+Wise-IoU, 77.54%) do not coincide, providing a quantitative basis for objective-driven module selection in industrial sorting. Full article

Overcoming complex background noise and poor small-target detection in industrial settings, this paper introduces YOLOv8-BBP2, an enhanced YOLOv8 model. To better extract dynamic features, the backbone integrates a BiFormer dual-level routing attention mechanism. Moreover, a learnable Bi-directional Feature Pyramid Network (BiFPN) replaces the standard module, optimizing multi-scale feature integration. A P2 detection head is also added to accurately identify tiny objects, such as early flames and thin smoke. Tested on a custom factory fire dataset, YOLOv8-BBP2 yields 95.231% precision, 94.612% recall, and 89.677% mean average precision (mAP@0.5). These metrics represent respective gains of 3.31%, 4.934%, and 7.451% over the baseline YOLOv8s. Ultimately, with an inference speed of 20 ms per frame, the proposed network ensures highly robust, real-time performance. Full article

Seepage pressure time series of concrete dams are governed by reservoir water level, rainfall, temperature and long-term aging effects, featured by strong nonstationarity and complex multi-scale fluctuations. Existing decomposition–ensemble methods ignore nonlinear coupling among scale components, suffering low prediction accuracy and poor physical interpretability. Current model fusion schemes fail to adapt to differentiated evolution mechanisms of frequency-varying seepage components and cannot fully mine implicit cross-scale nonlinear correlations. To overcome these drawbacks, this study proposes a concrete dam seepage pressure prediction approach integrating ensemble empirical mode decomposition, multi-scale preprocessing, and optimized dual-model selection combining ridge regression and Transformer–BiLSTM. Ensemble empirical mode decomposition adaptively denoises and decouples raw seepage series into high-, medium- and low-frequency IMFs according to oscillation cycles. A normalized Comprehensive Optimization Index is constructed to parallelly train ridge regression and Transformer–BiLSTM for each component and select the optimal submodel dynamically. A fully connected nonlinear fusion layer reconstructs multi-scale predictions to retain inherent component coupling features, replacing traditional simple linear superposition. Engineering cases verify that the proposed model efficiently captures periodic laws of key influencing factors, significantly boosting prediction accuracy and generalization capacity, thus possessing prominent theoretical and practical engineering application values. Full article

As the market of perishable goods in China continues to expand, reducing quality loss during transportation has become an urgent issue for the industry. Multimodal transport, as a key approach to optimizing the transportation structure and lowering logistics costs, has been increasingly adopted in practice. However, multimodal transport involves multiple transfers, and continuous vibration from transportation equipment throughout the transport process, together with impacts during transfer operations, can easily increase the loss of perishable goods, making it highly significant in practice to consider vibration loss during transportation in route planning. Since different transportation equipment generates different levels of vibration acceleration, this study considers the vibration losses caused by road, rail, and air transport. A bi-objective route optimization model for fresh produce multimodal transport is established, aiming to minimize total cost while maximizing product quality satisfaction. A hybrid algorithm combining an improved Strength Pareto Evolutionary Algorithm and a multi-objective adaptive large neighborhood search algorithm is designed to solve the model. The effectiveness of the model and algorithm is verified through case analysis, followed by sensitivity analysis on different time-sensitive factors of vibration damage and vibration acceleration. The results show that, compared with the multi-objective adaptive large neighborhood search algorithm and the non-dominated sorting genetic algorithm, the proposed algorithm can obtain solutions with lower total costs or higher product quality satisfaction. The minimum total cost of the multimodal transport scheme obtained by the proposed algorithm is reduced by 0.27% and 2.4%, respectively, compared with the multi-objective adaptive large neighborhood search algorithm and the non-dominated sorting genetic algorithm, while the maximum satisfaction is increased by 2.1% and 0.35%, respectively. Full article

Low-altitude micro downbursts pose a severe threat to aviation safety, yet conventional control approaches and standard deep reinforcement learning (DRL) often fail due to explicit modeling difficulties and sparse reward constraints. To address these challenges, this study proposes an explainable, data-driven framework integrating active-reward proximal policy optimization (AR-PPO). A bilevel optimization architecture driven by meta-gradients is developed to dynamically discover optimal reward functions without human intervention. Furthermore, a policy distillation pipeline utilizing wavelet-multivariate singular spectrum analysis (W-MSSA) and classification and regression trees (CART) is proposed to translate high-frequency continuous neural outputs into discrete, pilot-readable rules. Simulation results on a B737-800 model demonstrate that AR-PPO effectively overcomes the “stall trap” by autonomously learning to trade altitude for airspeed, outperforming static-reward baselines and empirical human pilots in extreme, zero-shot windshear encounters (22.0 m/s downdraft). Ultimately, the proposed framework successfully distills black-box AI strategies into verifiable, physics-informed standard operating procedures (SOPs), providing a highly transparent and robust solution for autonomous windshear escape and future competency-based flight training. Full article

Wireless channel state information (CSI) enables device-free industrial safety monitoring, but the same representation can expose worker identity and sensitive locations. Existing CSI privacy methods typically protect fixed semantic targets or perturb the entire representation, providing limited control over what is protected and where modification occurs. This paper proposes PCGM-Net, a policy-conditionedlocal generative masking framework for selective CSI semantic release. To the best of our knowledge, it is the first representation-level Wi-Fi CSI framework to jointly combine explicit semantic privacy policies, a learned position-wise soft mask over the time–subcarrier plane, bounded residual transformation, and trusted retention of the source CSI. The mask determines where intervention is applied, whereas the residual patch determines how the selected regions are transformed. A single model supports identity-only, location-only, and joint protection. Under a test-set-isolated protocol, raw CSI yielded identity and location accuracies of 97.95% and 100.00%, respectively. Across three independently trained protection models selected using validation data only, joint protection retained $74.79\pm 0.96\%$ activity accuracy while reducing identity and location accuracies for the validation-selected evaluator to $6.09\pm 2.40\%$ and $0.29\pm 0.14\%$. Removing the privacy-margin objective restored identity and location accuracies to 98.55% and 100.00%, confirming that suppression arose from targeted semantic optimization rather than incidental signal corruption. An independent temporal bidirectional gated recurrent unit (BiGRU) model recovered $94.09\pm 1.16\%$ activity accuracy after protected-domain adaptation, and the complete pipeline required 2.18 ms mean graphics processing unit (GPU) latency. PCGM-Net therefore provides low-latency, policy-selective inference-time semantic shielding under a bounded, evaluator-dependent threat model rather than irreversible anonymization. Full article

Electric trucks operating as mobile depots for delivery drones are promising for last-mile logistics, yet fleet electrification makes depot charging a critical issue governed by distribution-grid limits. Existing truck–drone routing formulations omit the electrical network, treating energy as exogenous, while grid-aware routing models overlook the combinatorial structure of mobile-depot drone synchronization. This paper introduces an energy-aware bi-level framework for the truck–drone routing problem that closes this gap. A distribution-grid leader solves slot-wise alternating current (AC) optimal power flow (OPF) under time-varying base loads and line deratings, returning a grid-feasible energy headroom and shadow prices. A logistics follower then co-optimizes truck routes, drone sorties, and ramp-constrained charging against this effective price, within a multi-objective cost structure. A damped fixed-point iteration couples the two levels, communicating grid scarcity through a single price signal without the logistics layer solving power-flow equations. On a Tokyo-inspired 100-customer instance with a stressed IEEE 33-bus feeder, the framework confines charging to slots with genuine headroom, reaching at most 81% loading and returning the fleet fully charged, whereas a grid-blind baseline reaches 109% loading. This comparison validates shadow pricing as an effective coordination mechanism. Full article