Search Results (31,863)

Industrial maintenance and predictive diagnostics constitute fundamental pillars of modern manufacturing that prevent equipment failures, minimize operational downtime, and optimize maintenance costs across diverse industrial environments. Vibration-based fault classification plays an important role in industrial operations, necessitating highly sophisticated diagnostic methodologies. This research addresses these industrial imperatives through a comprehensive investigation of novel hybrid deep learning architectures for vibration-based fault classification. This study introduces a strategic integration of Quadratic Neural Networks (QNNs), which demonstrate superior non-linear feature extraction capabilities on a vibration signal compared to traditional convolutional approaches. A systematic evaluation of seven sophisticated architectures establishes a clear performance hierarchy, with QuCNN-LSTM-Transformer emerging as the optimal model achieving 99.26% average accuracy. All proposed models demonstrate excellence, with test accuracies consistently surpassing 95% across all evaluated scenarios. The data analyzed is emprical utilizing sensor data collected from an experimental rig and shows exceptional performance consistency on CWRU and HUST datasets. This investigation establishes a new paradigm in intelligent diagnostics, offering functional guidance and definitive analysis of hybrid architectures that advance industrial fault classification applications. Full article

Against the backdrop of the full implementation of “antibiotic ban” and “zinc restriction” policies in livestock and poultry breeding, and the growing consumer demand for safe livestock and poultry products, the development of natural and efficient green feed additives has become crucial for the sustainable development of the animal husbandry industry. Curcumin, a natural polyphenolic compound extracted from the rhizome of Curcuma longa L., has attracted extensive attention in poultry production due to its various biological activities and safety. This paper thoroughly reviews the chemical structure and physicochemical properties of curcumin, and elaborates on its core molecular mechanisms of action, which mainly involve the regulation of nuclear factor erythroid 2-related factor 2 (Nrf2)/antioxidant response element (ARE), nuclear factor-κB (NF-κB), peroxisome proliferator-activated receptor γ (PPAR-γ), and mitogen-activated protein kinase (MAPK) pathways to exert antioxidant, anti-inflammatory, antibacterial, immunomodulatory and lipid metabolism regulatory effects. It further clarifies the practical application value of curcumin in major poultry species including broilers, laying hens, ducks and quails, showing that curcumin can significantly improve poultry production performance, optimize meat and egg quality, protect intestinal health, and enhance the ability of poultry to resist stress and diseases. Meanwhile, the review notes curcumin’s current application limitations (low bioavailability, poor stability, unclear standardized dosage, and high industrialization cost) and proposes targeted future research directions to address these issues. In conclusion, curcumin is a promising green feed additive alternative to antibiotics, and its large-scale and standardized application in poultry production will effectively promote the green, healthy and sustainable development of the poultry industry. Full article

Hydroponic cultivation is expanding rapidly as a resource-efficient alternative to soil-based farming, but challenges related to nutrient management, abiotic or biotic stresses, and organic production still limit the system’s performance and efficiency. Biostimulants are increasingly being explored as a promising strategy to support productivity and sustainability in soilless systems. This review summarizes the current evidence on the use of plant biostimulants to support crop performance in hydroponic systems. Microbial biostimulants, such as plant growth promoting rhizobacteria, Arbuscular Mycorrhizal Fungi, and Trichoderma spp., have been reported to promote root growth by synthesizing phytohormones, enhance nutrient uptake, and reduce the impacts of salt and heat stress, with reported improvements in biomass and nutrient use efficiency. Seaweed extracts and protein hydrolysates modulate plant hormonal balance, improve antioxidant defense, and have been associated with improvements in yield and quality. Humic and fulvic acids increase micronutrient bioavailability through chelation and stimulate root activity through auxin-like effects. In organic hydroponics, biostimulants may help address the nutrient gap by accelerating organic matter mineralization. Existing key challenges include the lack of hydroponic-specific dosage guidelines and high commercialization costs. Future efforts should further evaluate system-specific strategies, including emerging tools such as artificial intelligence-optimized strategies and the use of clustered regularly interspaced short palindromic repeats-edited microbes to support the long-term sustainability of controlled environment agriculture. Full article

Multimode fibers with core diameters of 50 μm and 62.5 μm are the core media for short-distance, low-cost, and high-bandwidth optical transmission scenarios. Currently, the detection of their end-face defects is still mainly based on manual microscopic inspection. Most of the existing machine vision detection schemes are aimed at polarization-maintaining fibers (POL), which are easily interfered with by impurities and have insufficient accuracy and efficiency. This study introduces the information entropy in information theory as a constraint for feature selection, proposes the WGMOS digital image detection method, and optimizes the entire process of image acquisition, correction, filtering, adaptive segmentation, and feature extraction. By minimizing the information entropy of background noise and maximizing the information content of defect features, interference is suppressed. Experiments show that compared with the POL detection method, this scheme can exclude more impurities, with the image equalization value increased by ≥38.20% and the signal-to-noise ratio increased by ≥6.0%. It can achieve efficient and accurate detection of multimode fiber end-face defects. Full article

The Vehicle-to-Grid (V2G) technology is considered one of the best solutions for integrating renewable energy systems; however, most literature reports favorable economic results using synthetic data, without accounting for seasonal or market limitations. The current research presents the results of the MATLAB R2023b (Version 23.2, MathWorks, Natick, MA, USA) simulation of the 100-household energy community in Debrecen, Hungary, with 30 electric vehicles (EVs) using entirely simulation-based Lithium Iron Phosphate (LiFePO4) batteries, a simulation-based 150 kW solar photovoltaic (PV) system, and a simulation-based 200 kW wind power system, using real meteorological data for January 2024. The optimization of charging/discharging for electric vehicles was performed using a multi-objective genetic algorithm (GA) over 30 days at a 15 min time resolution, accounting for stochastic loads and temperature effects on battery degradation, with a sensitivity analysis of key parameters. The results of the optimized solution for the electric vehicle charging/discharging were unexpected: the total energy cost increased by 68.9% ($4337.65 to $7327.54), the peak demand increased by 266.2% (31.9 to 116.9 kW), the degradation cost was $479.63, the load factor was reduced from 0.847 to 0.722, and the SOC constraint was violated for 0.758% of measurements. The V2G is not economically viable under current Hungarian pricing and Central Europe winter conditions. Results are robust for varying parameters using sensitivity analysis and Pareto front tracing. The break-even point is achieved when ratios of peak-to-off-peak prices are above 3.5:1. Seasonal policies and market reforms are critical for V2G viability. Importantly, the influence of inherent design deficiencies in the optimization model on the reported results cannot be ruled out. Full article

Detecting changepoints in time series is a fundamental task in statistical modeling and data-driven decision-making. We introduce a novel set partitioning-based model for changepoint detection that leverages combinatorial optimization to identify an optimal set of segments explaining the observed data. Unlike conventional dynamic programming approaches, which rely on restrictive structural assumptions on the cost function to ensure tractability, our formulation is based on Integer Linear Programming. While the standard additivity assumption on segment-wise costs is retained, the proposed framework departs from existing methods in its ability to incorporate both local and global structural constraints directly within the optimization model. In particular, it supports a broad class of constraints, ranging from simple segment-level restrictions to complex global conditions coupling multiple segments, without requiring modifications to the underlying solution scheme. This enhanced modeling capability constitutes the main contribution of the work, significantly increasing the expressiveness of the framework while preserving the tractability of additive cost structures. The model’s design enables high adaptability to different application domains, including finance, bioinformatics, and industrial monitoring. The efficiency of modern MILP solvers, combined with tailored dominance rules, enables the solution of instances with several hundreds of observations in practical time. Computational results indicate that the approach extends tractability beyond previously studied settings, effectively handling classes of instances whose structural constraints could not be accommodated by existing methods, while retaining robustness and interpretability. Full article

This work explores a sustainable route for producing recycled AlNiCo-based magnetic composites by incorporating end-of-life AlNiCo-5 particles into a polyamide 12 (PA12) matrix, thereby eliminating conventional debinding requirements. The study emphasizes material circularity through the reuse of mechanically recovered magnetic waste and polymeric residues. Virgin PA12 powder was used as the matrix material for high magnetic filler loadings of 40, 60, and 70 wt.% AlNiCo-5, while stearic acid was introduced to enhance interfacial compatibility and overall processability. The resulting composites were shaped into filaments and processed via material extrusion additive manufacturing, demonstrating that commercially available fused filament fabrication systems can successfully handle highly filled metal-polymer blends when supported by appropriate formulation and process parameter optimization. The findings confirm the feasibility of manufacturing flexible, functional, and resource-efficient magnetic components using widely accessible equipment, highlighting a promising pathway toward the cost-effective recycling and reuse of AlNiCo magnetic materials. Full article

Previous approaches to flexible-lined channel design typically isolate least-cost cross-section optimization from parameter uncertainty, or restrict reliability analysis to specific cases, limited failure modes, and proprietary codes. This paper presents VegyRap, an open-source QGIS-based plugin with an intuitive graphical user interface that unites these traditionally disjointed, sequential tasks into a single computational framework. The tool guides designers sequentially through: (i) terrain-driven longitudinal profile optimization using dynamic programming; (ii) least-cost cross-sectional optimization for riprap and vegetated linings; and (iii) multi-mode probabilistic reliability analysis coupled with dual risk–cost Pareto optimization. To seamlessly handle the stochastic behavior of uncertain variables, the framework features built-in statistical distributions and allows users to flexibly evaluate up to four distinct failure modes: overtopping, erosion, sedimentation, and near-critical flow oscillation. The framework’s capabilities are demonstrated through nine diverse design examples, incorporating benchmark validations against published studies and a comprehensive real-world case study in Wadi Al-Arja, Saudi Arabia. Results highlight that for vegetated channels, a hierarchical two-phase design logic is essential to satisfy both establishment-phase stability (Class E) and long-term conveyance (Class B). While benchmark comparisons show VegyRap achieves consistent cost reductions of 10–15% over traditional methods, the case study demonstrates that deterministic least-cost solutions can carry non-negligible failure probabilities. By utilizing marginal efficiency analysis to identify cost-effective enhancements, the integrated Pareto-based dual optimization produces transparent trade-off surfaces, empowering practitioners to transition from a single least-cost solution to a defensible, risk-calibrated preferred alternative. Full article

With the rapid development of complex engineering systems, many real-world optimization problems are characterized by high dimensionality, strong nonlinearity, and variable coupling. To address these challenges, this paper proposes a Public Management–Augmented Multi-Strategy Adaptive Enterprise Development Optimization algorithm (PMAED), which integrates adaptive differential evolution, an eigen-based rotated search strategy, and a hierarchical performance governance mechanism to enhance convergence efficiency and robustness. Experimental results on the CEC2020 and CEC2022 benchmark suites demonstrate that PMAED achieves superior performance across different problem types and dimensionalities. In the Friedman ranking test, PMAED consistently obtains the best average rank (1.90 and 1.60 on CEC2020; 2.00 and 1.92 on CEC2022 for 10D and 20D, respectively), outperforming all compared algorithms. The Wilcoxon rank-sum test further confirms that PMAED achieves statistically significant improvements on the majority of benchmark functions. In high-dimensional scenarios, PMAED shows remarkable optimization accuracy, for example, achieving a mean fitness value of 1.15 × 10³ on the 20-dimensional CEC2020 F1 function, significantly outperforming classical methods. In addition, PMAED is applied to a three-dimensional UAV path planning problem. The results show that the proposed method achieves the lowest average path cost (277.62) and the smallest standard deviation among all algorithms, indicating superior stability and reliability. The planned paths are smoother, safer, and more efficient compared to those generated by other methods. Overall, the proposed PMAED provides a robust and efficient solution for complex continuous optimization problems and demonstrates strong potential for real-world engineering applications. Full article

Modern power systems increasingly integrate renewable energy sources (RESs), electric mobility, and dynamic market participation. Dynamic electricity pricing, reflecting real-time market conditions, is increasingly important for prosumers worldwide, enabling flexible and efficient energy management. The growing adoption of electric vehicles (EVs) and bidirectional charging technologies (V2G, V2H) allows EVs to act as mobile battery energy storage systems (mBESSs). This study presents a Python 3.11-based application for simulating and analyzing energy flows in residential systems with photovoltaic (PV) installations, EVs acting as mBESS, and optional stationary battery energy storage systems (BESSs), using real 2024 data on consumption, PV production, and market prices. The energy management system (EMS) employs a rule-based algorithm to optimize energy use and economic benefits, adjusting dispatch between PV systems, the grid, mBESSs, and BESSs based on price coefficients $\alpha$ and $\beta$. Simulation scenarios were developed based on two EV availability patterns: Profile 1, representing users unavailable during standard working hours, and Profile 2, representing users with intermittent availability for brief excursions. The results demonstrate substantial electricity cost reductions: For a Nissan Leaf e+ with Profile 1, annual costs decrease by approximately 20% compared to a system without EVs. With PV generation and Profile 2, costs drop by 57% relative to the baseline, while adding a stationary BESS further reduces costs by nearly 95%. It should be noted that the results were obtained assuming zero energy costs for propulsion. Therefore, the economic benefits reported here represent an upper-bound estimate and would be lower under real-world driving conditions. These findings highlight that coordinated EMS operation with EVs as mBESSs, supported by optional BESSs, can maximize economic performance and provide prosumers with a practical framework for flexible and efficient energy management. Full article

In insurance portfolios, classifying customers without a prior history at a given company is particularly challenging due to the absence of historical behavior, extreme class imbalance, heavy-tailed loss distributions, and strict operational constraints. Traditional machine learning approaches, including the baseline methodology proposed in previous studies, typically optimize global predictive accuracy and therefore fail to capture business-critical outcomes, especially the identification of high-risk clients. This study extends the existing approach by evaluating two complementary business-aware classification strategies: (i) a balanced bagging ensemble specifically designed to handle class imbalance and maximize expected profit under explicit customer-omission constraints, and (ii) a lightweight Transformer-based architecture capable of learning richer feature representations. Both approaches incorporate the asymmetric financial cost structure of insurance and operate under operational selection limits. The empirical analysis is conducted on a proprietary large-scale auto insurance dataset comprising 51,618 customers and is complemented by validation on nine synthetic datasets to assess robustness. Model performance is evaluated using statistical tests (ANOVA, Friedman, and pair-wise comparisons) together with business-oriented metrics. The results show that both proposed approaches consistently outperform the baseline methodology (p < 0.001) in terms of profit, with the ensemble offering a better balance of performance and efficiency, while the Transformer shows stronger robustness and generalization under data perturbations. The balanced ensemble provides the most favourable trade-off between predictive performance, robustness, interpretability, and computational efficiency, making it suitable for deployment in regulated insurance environments, while the Transformer achieves competitive results and exhibits stronger generalization under data perturbations. The proposed approach aligns machine learning with actuarial portfolio optimization by explicitly integrating profit-driven objectives and operational constraints, offering two practical and scalable solutions for risk-based decision-making in real-world insurance settings. Full article

Trajectory planning in dynamic multi-vehicle interaction environments faces three critical challenges, including the difficulty of quantifying spatial risk distributions, the complexity of characterizing behavioral uncertainty arising from the multimodal maneuvers of surrounding vehicles, and the challenge of simultaneously optimizing multiple competing objectives such as safety, efficiency, comfort, and energy consumption. To address these challenges, this paper proposes an Improved Driving Risk Field-based Multi-objective Trajectory Optimization (IDRF-MTO) method. First, a joint spatiotemporal social attention mechanism achieves unified modeling of spatial interactions, temporal dependencies, and spatiotemporal coupling, combined with a lateral–longitudinal intent strategy for multimodal trajectory prediction. Second, an improved dynamic risk field model is constructed comprising three components: a vehicle risk field that incorporates spatial orientation and motion direction factors for anisotropic risk representation, along with a collision tendency factor that converts objective risk into effective risk; a predicted trajectory risk field that achieves anticipatory quantification of future risk from surrounding vehicles through confidence-weighted fusion; and a driving environment risk field that encapsulates road geometry, static obstacles, and environmental conditions. Finally, a multi-objective cost function embedding risk field gradients is formulated, and multi-objective coordinated optimization is realized through a three-dimensional spatiotemporal situation graph with adaptive safety sampling. Simulation results demonstrate that the proposed method enhances safety while simultaneously improving comfort and efficiency and reducing energy consumption, exhibiting excellent planning performance in complex dynamic environments. Full article

Entropic soft-min operators are widely used to obtain smooth approximations of minimum and argmin mechanisms in optimization, machine learning, and reinforcement learning. The quality of this approximation is controlled by an inverse temperature parameter that governs the trade-off between smoothness and fidelity, yet its selection is usually based on global heuristics or worst-case bounds that do not account for the geometry of the candidate cost vector. This study investigates the calibration of the inverse temperature parameter from a geometry-aware perspective, with explicit guarantees on the approximation error between the entropic soft-min and the exact minimum value. After establishing the structural properties of the relaxation error, including monotonicity with respect to the inverse temperature and its dependence on the geometry of the near-optimal set, we introduce a conformal calibration rule that selects the smallest inverse temperature, ensuring that a prescribed upper quantile of the approximation error remains below a target tolerance with distribution-free finite-sample validity. The resulting selector adapts to the geometry distribution represented in the calibration population and provides a principled alternative to mean-based and worst-case tuning rules. Numerical experiments, including geometry-controlled benchmarks and a contextual bandit setting illustrating the impact of geometry-aware calibration on decision-making under estimated action values, show that the proposed method accurately tracks oracle calibration temperatures, preserves the desired operator-level coverage, and makes explicit how geometric heterogeneity governs the effective sharpness required by the soft-min approximation. Additional shifted evaluations illustrate the role of exchangeability in the validity guarantee and the consequences of transferring temperatures across populations with different near-optimal geometries. Full article

In response to the reduced system inertia and increased frequency security risks in high-renewable power systems, as well as the limitations of single energy storage technologies, a coordinated optimal scheduling method for electrochemical energy storage (EES) and compressed air energy storage (CAES) considering the minimum inertia requirement (MIR) is proposed. The method constructs a coordination framework, leveraging the fast response of EES and the sustained support and equivalent inertia contribution of CAES. An MIR evaluation model considering RoCoF and frequency nadir constraints is established, and the inertia deficit is converted into fast reserve demand, forming an inertia–reserve coupling mechanism. To address nonlinear frequency constraints, an adaptive piecewise linearization method is adopted to transform the model into a mixed-integer linear programming problem. Case studies show that, compared with the benchmark hybrid energy storage scheduling strategy without inertia–reserve coordination, the proposed method reduces thermal generation cost by 4.5% and renewable curtailment by 74.8%. Moreover, the proposed APWL method improves computational efficiency by 47% compared with the conventional PWL method. Full article

To address the coupled challenges of renewable power volatility, high operating cost, and electrolyzer degradation in grid-connected wind–PV hydrogen production systems, this paper proposes a hierarchical day-ahead scheduling strategy under time-of-use (TOU) electricity prices. The upper layer performs price-responsive economic dispatch to coordinate renewable utilization, battery operation, grid transactions, and aggregate hydrogen-production power with the objective of minimizing lifecycle operating cost. The lower layer introduces a health-aware non-uniform rotation mechanism to allocate the aggregate power command among electrolyzer units, thereby reducing fluctuation exposure and balancing lifetime consumption across the array. Practical constraints, including multi-state electrolyzer operation, unit-commitment logic, battery state-of-charge dynamics, hydrogen storage limits, and system power balance, are explicitly considered. A case study of a wind–PV hydrogen production project in Northern China shows that the proposed strategy shifts electricity purchases to valley-price periods and promotes electricity export during peak-price periods. Compared with the benchmark strategy, hydrogen production during low wind–PV generation periods increases from 342,000 to 381,000 Nm³, the share of fluctuating operating time decreases from 62.5% to 12.5%, and the average daily start–stop frequency declines from 8.0 to 4.8. Consequently, the degradation penalty is reduced by about 40%, and lifecycle operating cost decreases by 27.3%. Full article