Search Results (536)

In this study, a fractional-order epidemic compartmental model is formulated using the Caputo derivative to account for the memory effects of the chikungunya virus. Based on Banach contractions, fixed-point theorems are used to prove existence and uniqueness, and fundamental properties such as positivity and boundedness are established. Normalized forward sensitivity indices are employed to evaluate the relative impact of model parameters on the transmission dynamics and control of the disease. To reduce the spreading of infection, an optimal control problem is formulated by introducing time-dependent control measures with four control strategies that include public health prevention, treatment enhancement, and vector-control measures. Necessary conditions for optimality are derived using Pontryagin’s Maximum Principle. The predictor–corrector Adams–Bashforth–Moulton scheme is applied across different fractional orders and effectively reduces infection levels. The influence of the fractional order $\xi$ on the epidemic dynamics is investigated, showing that lower values of $\xi$ slow disease progression through a memory effect inherent in the Caputo operator. Moreover, an artificial neural network (ANN) trained via the Levenberg–Marquardt algorithm independently validates the numerical solutions. Full article

To address the turn-off overvoltage challenge arising from the rapid interruption of Low Voltage DC Solid-State Circuit Breakers (SSCBs), this paper proposes a high-precision behavioral modeling method for domestic SiC MOSFETs. The model is constructed based on the physical structure of the device, integrating a modified EKV-based static current model and a voltage-dependent nonlinear parasitic capacitance model described by piecewise functions. Model parameters are efficiently extracted from datasheets and measurement data using a composite optimization strategy combining the Genetic Algorithm and the Levenberg–Marquardt algorithm. The model is implemented in LTspice, and its accuracy in both static and dynamic characteristics is validated by comparing the simulation waveforms with experimental results. Based on the validated model, the turn-off process is subdivided into four distinct stages, with an equivalent circuit established for each. A systematic analysis reveals the intrinsic physical mechanism of the voltage spike and oscillation, which results from interaction among the drive circuit parameters, system parameters, and the nonlinear capacitances of the device. The research outcomes provide effective theoretical guidance and a design tool for simulation modeling, turn-off stress assessment, and snubber circuit optimization for SSCBs utilizing SiC MOSFETs. Full article

In the domain of river engineering, estimating the total sediment load in rivers is a crucial challenge. For tens to hundreds of kilometers downstream, the additional sand and gravel in the sediment can raise the elevation of channel beds. For highly braided rivers like the Brahmaputra-Jamuna, the accurate prediction of the total sediment load depends on the complex relationships among different hydro-meteorological variables. As a result, manual selection of the lagged features from only antecedent sediment records can produce suboptimal predictions, which can be considered a significant research gap. In addition, the predictive accuracy can be further enhanced through the application of advanced decomposition techniques. To address these deficiencies, we implemented three sophisticated feature selection methodologies: SelectKBest, Mutual Information, and Random Forest utilizing the Boruta Algorithm as an alternative to manual feature selection. Furthermore, we investigated complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), variational mode decomposition (VMD), and the Hodrick–Prescott Filter (HPF) to improve data mining efficiency. Four distinct artificial neural network (ANN) training algorithms were considered: back propagation (BP), cascade correlation (CC), conjugate gradient (CG), and Levenberg–Marquardt (LM), as alternatives to the conventional BP-based training approach. The effectiveness of the variants of the ANN was assessed in comparison to a powerful ensemble learning model, specifically the decision tree (DT). Results indicate that the HPF-enhanced ANN-LM model exhibited the strongest performance metrics when compared to alternative techniques, with values of NRMSE = 0.004, MAE = 455.242 kg/s, NSE = 0.998, and KGE = 0.990. The outcomes from Sobol’s sensitivity analysis suggest that the sediment dynamics in this region can be better predicted through the inclusion of rainfall-based features. Full article

Blasting-induced ground vibrations, typically quantified by peak particle velocity (PPV), pose one of the most critical environmental challenges in surface mining and can damage nearby structures and disrupt surrounding ecosystems. Consequently, the development of reliable and accurate predictive models is essential for designing safe, environmentally responsible, and sustainable blasting operations. This study develops a robust predictive framework using a harmonized database of 506 blasting events, from which 386 high-quality records were retained after preprocessing to model PPV as a function of charge per delay (Q), monitoring distance (R), and rock mass rating (RMR). Several machine learning (ML) algorithms, including artificial neural networks trained using the Levenberg–Marquardt algorithm (ANN-LM), adaptive neuro-fuzzy inference systems (ANFIS), Gaussian process regression (GPR), and decision trees (DT), were evaluated alongside conventional empirical models such as the USBM, Ambraseys–Hendron, Langefors–Kihlstrom, and BIS. To further enhance predictive capability, two optimization strategies, Bayesian optimization (BO) and differential evolution (DE), were applied to the GPR model, producing optimized BO-GPR and DE-GPR variants. Model performance was assessed using the correlation coefficient (r), variance accounted for (VAF), mean absolute error (MAE), and relative root mean square error (RRMSE). Results indicate that the BO-GPR model achieved the best predictive performance during testing for both the two-input (Q, R) and three-input (Q, R, RMR) configurations, with r values of 0.97426 and 0.98381, respectively, and VAF values exceeding 94%. SHAP analysis revealed monitoring distance as the dominant attenuating factor controlling PPV. The optimized framework provides an accurate, interpretable tool for vibration prediction and precision blast design, supporting environmentally responsible, sustainable mining operations. Full article

Thermal infrared remote sensing offers a cost-effective means of regional geothermal reconnaissance, yet a fundamental challenge remains: isolating the weak geothermal surface signal (typically 1–3 °C) from dominant surface noise introduced by seasonal temperature cycles (annual amplitude > 20 °C), topographic variability, land cover heterogeneity, and irregular cloud-affected satellite sampling. Conventional single-scene or arithmetic-mean approaches are highly susceptible to these confounding factors and frequently produce pseudo-anomalies that obscure genuine geothermal targets. To overcome this limitation, we propose a physics-based time-series framework in which a nonlinear annual temperature variation model, T(t) = T0 + A·sin(2πt/τ + φ), is fitted to multi-temporal Landsat 8 thermal infrared data via the Levenberg–Marquardt algorithm. Applied to ~50 cloud-free scenes (2021–2022) processed on the Google Earth Engine over the Shanxi Graben System, northern China, the model simultaneously retrieves the background temperature parameter T0 and seasonal amplitude A—two physically interpretable quantities that encode distinct geothermal signatures more robustly than simple temporal statistics. Sub-regional corrections for the elevation (−4 °C/100 m above 800 m), aspect (R² > 0.95 in piecewise linear segments), and slope further suppress topographic pseudo-anomalies prior to anomaly extraction. Over known high-temperature geothermal fields (Tianzhen and Yanggao; >100 °C at 100 m depth), the method reveals clear T0 offsets of +1–2 °C (3–5% relative) and amplitude deficits of ~2 K (5–10% relative) relative to the background, with model-fitted T0 values averaging ~2 °C higher than arithmetic means due to the correction for seasonal sampling bias. Combined with 5 km fault-proximity buffers, extracted anomaly zones align well spatially with known geothermal sites and major structural corridors of the graben system. However, deeper low-temperature systems (45–50 °C at 300–500 m depth) produce ambiguous signals below the ~1.5 K detection threshold, indicating inherent limitations for deeply buried resources. The fully reproducible, training-data-free workflow is implementable via open satellite archives and cloud computing platforms, making it a transferable low-cost tool for structurally controlled geothermal reconnaissance across extensional basins worldwide. Full article

Masonry buildings have shaped construction history since about 6500 BCE. They offer durability, strength, and cost effectiveness, especially in developing countries. Yet assessing compressive strength during construction remains challenging due to the constituent materials soil, cement, and stone, complicating standardization worldwide. In the present study, an innovative model based on a machine learning algorithm is put forth to predict the compressive strengths of prisms. Some important factors considered as input to the algorithm based on traditional methods are the brick and mortar strengths, prism geometry, mortar bed thickness, and empirically derived height-to-thickness (t) (h/t) ratios. Three different ANN algorithms are coded and trained on the input data, and they are based on the Levenberg–Marquardt algorithm, the resilient backpropagation algorithm, and the conjugate gradient algorithm. The optimal ANN model trained using the conjugate gradient Polak–Ribière algorithm (traincgp) achieves superior performance, with R² = 0.9881, R² = 0.9927, RMSE = 0.9914 MPa, MAE = 0.6039 MPa, MAPE = 20.9141%, VAF = 0.9881, and WI = 0.9970. Sensitivity analysis shows the height-to-thickness (h/t) ratio is the dominant influence on compressive strength, consistent with structural mechanics. The primary contributions are the systematically curated, richly parameterized dataset and its use to produce robust, physically interpretable predictions with established ANN methods. Full article

Accurate prediction of temperature-induced degradation in concrete is essential for improving structural fire safety and supporting reliable post-fire engineering decisions. However, previous studies have generally focused on conventional machine learning applications or limited optimization strategies, while integrated frameworks combining systematic input screening, robust validation, large-scale metaheuristic optimization, and interpretable analysis remain limited. This study aims to develop a comprehensive predictive framework for estimating the temperature-induced weight loss and compressive strength of concrete using advanced machine learning techniques. First, a detailed collinearity analysis was performed to filter the input dataset, eliminate redundant correlations, and improve statistical reliability. For modeling consistency, all fiber-containing mixtures were treated as polymer-fiber systems, and fiber-related variables were interpreted as polymer-fiber descriptors. To reduce overfitting and ensure robust validation, 5-fold cross-validation was applied during training, while 23% of the dataset was reserved as a strictly independent test set. In addition, 25 metaheuristic algorithms were evaluated under a standardized computational budget of 5000 function evaluations to perform neural architecture search. The results showed that the Marine Predators Algorithm (MPA), Symbiotic Organisms Search (SOS), and Kepler Optimization Algorithm (KOA) achieved superior convergence behavior in optimizing hybrid Levenberg–Marquardt-trained networks. SHapley Additive exPlanations (SHAP)-based sensitivity analysis further revealed that matrix-related properties, particularly unit weight and water absorption capacity, were the dominant drivers of thermal degradation. Overall, the proposed framework provides not only a robust benchmarking platform for predictive modeling but also a practically relevant and interpretable tool for post-fire structural assessment and thermally resilient concrete design. Full article

Gangue backfilling has become an important technique for promoting environmentally friendly and low-carbon coal mining. The long-term creep behavior of cemented backfill plays a critical role in maintaining stope stability and controlling surface subsidence during long-term service. Although considerable research has been conducted on cemented tailings backfill, systematic investigations on the triaxial creep evolution, long-term strength characteristics, confining pressure effects, and the applicability of the classical Burgers model for gangue–gypsum cemented backfill under engineering-relevant confining pressures remain limited. In this study, the experimental scheme was designed based on field monitoring data from practical backfill mining operations, which indicate that the in situ backfill generally remains stable without significant deformation or instability under normal working conditions. Multi-stage loading triaxial creep tests were conducted on gangue–gypsum cemented backfill under confining pressures of 1, 2, 3, and 4 MPa. The creep deformation characteristics were analyzed using Chen’s superposition method, while the long-term strength was computed via inflection point method of isochronous stress–strain curves. The parameters of the Burgers creep model were identified using the Levenberg–Marquardt optimization algorithm, and numerical verification was performed using FLAC3D. Our findings demonstrate that the creep deformation process of the backfill consists of three typical stages: instantaneous deformation, attenuated creep, and steady-state creep, and no accelerated creep was observed within the applied stress range. The absolute creep strain surges nonlinearly with increasing stress level (S_L), whereas higher confining pressure significantly suppresses the creep response of the material. Within the investigated stress range, the backfill exhibits mainly linear viscoelastic behavior, and its critical long-term strength is not less than 0.9 times the failure deviatoric stress (qf). Although confining pressure enhances the long-term strength, the strengthening effect weakens as the confining pressure increases. Model fitting outcomes imply that Burgers model precisely describes the creep behavior of gangue–gypsum cemented backfill under all test conditions, with correlation coefficients (R²) exceeding 0.97. The identified parameters show systematic variation with S_L, reflecting stiffness degradation and viscous evolution during loading. Numerical simulation results agree well with the experimental data, providing theoretical guidance for mixture proportion optimization, long-term stability evaluation, and stope support parameter design in gangue backfill mining engineering. Full article

Ultra-High-Performance Concrete (UHPC) is increasingly used in slender and prestressed structural members due to its superior strength and durability. However, inaccurate or incomplete prediction of creep deformation may lead to excessive long-term deflection, prestress loss, cracking, and potential serviceability or safety risks in buildings and infrastructure. Therefore, reliable prediction methods for UHPC creep are essential for both structural design and long-term performance assessment. In this study, a database containing 60 literature-derived UHPC creep records was compiled to investigate the creep coefficient at approximately 100 days. Pearson correlation analysis revealed strong interdependence among predictors and weak single-variable linear relationships, indicating that creep behavior is governed by nonlinear interactions. A feedforward backpropagation neural network (BPNN) trained using the Levenberg–Marquardt algorithm was developed to predict the creep coefficient. To maintain engineering interpretability, the fib Model Code 2020 (MC2020) formulation was adopted as a code-based benchmark and further calibrated using ridge regression. Results show that the calibrated MC2020 model improves prediction consistency, while the BPNN model provides the highest predictive accuracy. The proposed framework integrates machine-learning prediction with interpretable code-based calibration, contributing to the development of creep modeling approaches for UHPC and providing practical support for the safe design of UHPC structures. Full article

The long-term prestress relaxation of soil anchors embedded in saturated clay is a critical issue affecting the safety of geotechnical structures such as slopes and foundation pits. Traditional integer-order constitutive models are often unable to accurately describe the nonlinear and time-dependent relaxation behavior observed in such anchorage systems. Based on fractional calculus theory, this study establishes a constitutive model for the coupled stress relaxation behavior of soil anchors and saturated clay. The Riemann–Liouville fractional derivative and the two-parameter Mittag-Leffler function are introduced to represent the material memory effect and continuous relaxation characteristics. To achieve reliable parameter identification, a hybrid optimization strategy combining the Adaptive Hybrid Differential Evolution (AHDE) algorithm and the Levenberg–Marquardt (L-M) method is proposed. The proposed model and identification approach are validated using field monitoring data from soil anchors in a slope engineering project at the Guangxi Friendship Pass Port. The results show that the proposed model can accurately reproduce the entire stress relaxation process, with a coefficient of determination of R² = 0.9517. Parameter sensitivity analysis further clarifies the influence of key parameters, including the fractional order and viscosity coefficient. The proposed approach provides a systematic theoretical framework and practical reference for the analysis and prediction of long-term prestress relaxation in soil anchorage systems. Full article

To ensure personnel safety and prevent serious accidents, it is crucial to monitor parameters such as temperature, pressure, and gas composition concentrations in confined spaces. This study proposes a multi-parameter simultaneous inversion algorithm based on tunable diode laser absorption spectroscopy (TDLAS). The algorithm integrates the Levenberg–Marquardt (L-M) fitting method, single-line thermometry and manometry methods, spectral separation, and alternating iteration techniques, with an adaptive feedback mechanism adding to enhance convergence stability. Through this approach, simultaneous inversion of H₂O, CO₂, CO, and O₂ concentrations, temperature, and pressure was successfully achieved. Simulation results demonstrated that the measurement accuracy meets practical requirements. This study provides an effective monitoring method for multi-parameter detection in confined spaces within conventional environments and lays a foundation for expanding the application scope of TDLAS technology. Full article

It is proposed that the process of learning may be represented as a trajectory within the phase space of long-term memory. The research uses an artificial neural network design to explore, in theory, if starting from different points within the phase space affects how quickly learning occurs. Using a Monte Carlo method, 1000 virtual agents were trained using the Levenberg–Marquardt algorithm to recognise a large set of Arabic digits at ten different skill levels. The simulations replicated the typical learning curves observed in human learning and were successful in distinguishing ten levels of skill. First, and in line with previous research, the results provide convincing evidence that learning consolidates a selected set of pathways within the network. Second, and critical to the hypothesis, the distance in the phase space, calculated as the difference in average connectivity between skill levels, is highly predictive of both learning time and performance. The findings strongly support the hypothesis that learning represents progression along a trajectory connecting two points within the phase state landscape. As these properties may be more pronounced in biological systems because of their greater complexity, these results shed new light on individual variance in learning. Full article

Camera calibration is an essential research direction in photonics and computer vision. It achieves the standardization of camera data by using intrinsic and extrinsic parameters. Recently, RGB-D cameras have been an important device by supplementing deep information, and they are commonly divided into three kinds of mechanisms: binocular, structured light, and Time of Flight (ToF). However, the different mechanisms cause calibration methods to be complex and hardly uniform. Lens distortion, parameter loss, and sensor degradation et al. even fail calibration. To address the issues, we propose a camera calibration method based on the Expectation–Maximization (EM) algorithm. A unified model of latent variables is established for the different kinds of cameras. In the EM algorithm, the E-step estimates the hidden intrinsic parameters of cameras, while the M-step learns the distortion parameters of the lens. In addition, the depth values are calculated by the spatial geometric method, and they are calibrated using the least squares method under an optical motion capture system. Experimental results demonstrate that our method can be directly employed in the calibration of monocular and binocular RGB-D cameras, reducing image calibration errors between 0.6 and 1.2% less than least squares, Levenberg–Marquardt, Direct Linear Transform, and Trust Region Reflection. The deep error is reduced by 16 to 19.3 mm. Therefore, our method can effectively improve the performance of different RGB-D cameras. Full article

A galvanometer-based laser 3D projection system requires accurate mapping between galvanometer control signals and workpiece coordinates to ensure reliable on-part marking. This study presents a calibration and verification pipeline that uses a color camera and a depth sensor to reconstruct 3D target points and estimate the extrinsic parameters between the projector and the workpiece. Laser spot centers are localized in color images, and corresponding depth values are acquired after color–depth alignment. The resulting 3D points are back-projected and transformed into the workpiece coordinate frame. A hybrid solver is employed: the Whale Optimization Algorithm (WOA) provides a global initial estimate, followed by Levenberg–Marquardt (LM) refinement to enhance convergence stability under noisy and small-sample conditions. Experimental validation on an independent 13-point set demonstrates sub-millimeter accuracy, with a mean error of approximately 0.37 mm and a maximum error of 0.87 mm. A further rectangular contour projection test confirms consistent performance, yielding a mean error of 0.434 mm and a maximum error of 0.879 mm, with all errors remaining below 1 mm. Full article

Background: The transition toward Industry 4.0 and Supply Chain 5.0 requires performance measurement frameworks that integrate efficiency, digitalization, and sustainability indicators. Although the SCOR^® 4.0 model provides standardized metrics, it lacks predictive capabilities under complex and nonlinear conditions. This study addresses this gap by extending the SCOR^® framework and integrating it into an AI-based predictive model. Methods: A Multilayer Perceptron (MLP) neural network was developed to forecast Supply Chain Performance (SCP) using an expanded set of SCOR^® 4.0 indicators. Additional Level 1 and Level 2 metrics, capturing digitalization and sustainability (including carbon footprint and waste reduction), were incorporated. The MLP model was optimized and trained using the Levenberg–Marquardt algorithm on a synthetically generated dataset derived from deterministic Extended SCOR^® 4.0 formulations, in order to capture complex nonlinear relationships under controlled, simulation-based conditions. Results: Simulation-based validation demonstrates high predictive accuracy, achieving low RMSE, MAE, and MAPE values and strong correlation coefficients. Conclusions: The findings demonstrate the methodological feasibility and internal consistency of integrating extended SCOR^® metrics with an optimized MLP architecture for forecasting multidimensional SCP under simulated conditions in digital and sustainability-oriented supply chains; external validity to real operational environments remains to be established in future empirical studies. Full article