Search Results (228)

Two reconstruction methods for constraint and load parameters of aero-engine pipelines based on intelligent optimization algorithms are proposed in this paper. First, a simplified finite element model (FEM) of the aero-engine pipeline structure is established, and its reliability is validated by comparing simulation data with experimental data. Second, a reconstruction algorithm for spring constraint parameters and pipeline load parameters based on the improved particle swarm optimization (IPSO) algorithm is developed on the MATLAB data analysis and ANSYS simulation platforms, which completes the reconstruction calculation of parameters such as spring constraint stiffness and applied harmonic excitation. For harmonic excitation parameter reconstruction, the maximum error of this algorithm reaches 24.9%, revealing its significant inapplicability to load parameter reconstruction. To solve this problem, a load reconstruction method based on the conjugate gradient method (CGM) is further proposed to achieve accurate reconstruction of pipeline load parameters, which mitigates the large reconstruction error of the IPSO algorithm under working conditions with multiple loads. Under 5% noise interference, the maximum error of the CGM is merely 5.16%. Finally, experimental verification of harmonic excitation amplitude reconstruction is performed using the CGM with lower reconstruction errors. Experimental results indicate that the maximum error is 14.24% for harmonic excitation amplitude reconstruction, which verifies the high applicability of the conjugate gradient algorithm to load reconstruction of aero-engine pipelines. Full article

Accurate remaining useful life (RUL) prediction is critical for the reliable operation of lithium-ion batteries. Traditional data-driven methods often suffer from parameter redundancy and error accumulation in state prediction. This paper proposes a hybrid data-driven RUL prediction framework based on Gaussian process regression (GPR) optimized by the lightning search algorithm (LSA). First, both local and global indirect health features (HFs) are extracted from the external characteristic parameter curves and the incremental capacity curves during battery charging/discharging. Second, the Pearson correlation coefficient is applied to select highly relevant features, forming a compact feature set. Third, a GPR model is developed, and the LSA is introduced to optimize its hyperparameters, overcoming the tendency of the conjugate gradient method to fall into local optima or fail to converge. Experimental results under identical conditions show that the proposed LSA–GPR model achieves a prediction error of 3% or less. Full article

This article reviews the linear solvers available in OpenFOAM and assesses their impact on the convergence behaviour of the SIMPLE algorithm. The discretisation of transport equations in CFD results in large and sparse linear systems, for which the choice of linear solver strongly influences the computational time. Although the solver does not change the final discrete solution, the difference in speed and robustness between the solvers can be more than one order of magnitude. A brief overview is given concerning how the velocity and pressure fields are decoupled in OpenFOAM, followed by a detailed review of the main linear solver families, including direct methods, basic iterative methods, multigrid methods and Krylov subspace methods, with attention to their practical strengths and weaknesses. The performance of the most advanced solvers is evaluated on a full-scale non-reacting kiln case consisting of 2.3 million cells. The pressure-corrector equation is identified as the main bottleneck in the SIMPLE algorithm. The conjugate gradient (CG) solver with a multigrid (MG) preconditioner is found to be the fastest and most stable method, achieving speed-ups of up to a factor of 7 compared to the slower advanced methods. Using MG as a preconditioner also improves the robustness of the Bi-CGStab method. Full article

Proteins with additives, especially in small quantities, are of great interest as a subject of study. Machine learning approaches implemented on Raman spectroscopy data could provide an insight into the chemical structures of such mixtures or conjugates. Although decision tree models could be powerful in solving either classification or regression tasks and could provide accessible predictions, they are prone to overfitting. Ensemble models that implement several decision trees could overcome the determined problem. Five different model types are discussed: RandomForest, GradientBoosting, AdaBoost, Voting, and Stacking. Raman spectroscopy data of whey protein isolates (5 wt.%) with different amounts of hyaluronic acid (0, 0.1, 0.25, and 0.5 wt.%) were used as datasets. In order to generalize the results of the study, WPI samples from three different manufacturers were used. Optimization established that ensembles of 200 decision trees with a maximum depth of four were optimal. The Stacking algorithm, which used RandomForest, GradientBoosting, and AdaBoost as base models with either LogisticRegressor (classification task) or RidgeCV (regression task), was found to be the most efficient in finding differences between the whey protein isolate and its conjugates with hyaluronic acid: specificity of 68.7% and sensitivity of 95.4% (classification task); R² = 0.764 with mean absolute error of 0.068 (regression task). According to the feature importance plots, the Raman bands that were most influential in predicting the results were 1003 cm⁻¹ (phenylalanine, ring breath), 1125 cm⁻¹ (rocking of NH₃⁺), 1206 cm⁻¹ (C–C stretching), 1240 cm⁻¹ (amide III (β-sheet), N–H in-plane bend, C–N stretch), and 1399 cm⁻¹ (aspartic and glutamic acids, C=O stretch of COO–). The findings of this study may contribute to the development of novel methods for quality control and analysis of complex multicomponent systems in various industrial settings. In particular, the ensemble approach can be adapted for monitoring in food processing or as a screening tool in pharmaceutical formulation development. Full article

Accurate transmission-line parameters are essential for reliable, efficient, and sustainable smart grid operation, especially under increasing renewable-energy integration and data-driven grid management. However, line aging, temperature variations, and measurement outliers may cause significant deviations between actual and nominal grid models, thereby degrading the state estimation, power-flow analysis, and operational security assessment. To address these challenges, this paper proposes a robust transmission-line parameter estimation method based on a variable-projection framework. The proposed framework decomposes the original high-dimensional, strongly coupled, and non-convex joint estimation problem into two subproblems associated with line-parameter identification and operating-state calibration. An iteratively reweighted least-squares algorithm based on the Huber M-estimator is introduced to dynamically adjust measurement weights and suppress the influence of outliers. The preconditioned conjugate-gradient method is further employed to avoid the explicit inversion of large-scale normal matrices. Simulations on the IEEE 118-bus system demonstrate that the proposed method achieves a higher parameter-estimation accuracy and stronger robustness than conventional weighted least-squares and joint state-parameter estimation methods. In the base case, the proposed method reduces the RMSRE of line reactance to 0.0794%, compared with 0.1558% for WLS and 0.1126% for JSE. Under the representative 5% gross-error case, the proposed method maintains lower RMSREs of 0.9772%, 0.0875%, and 5.8536% for $R_l$, $X_l$, and $B_{sh}$, respectively. Further sensitivity tests under contamination ratios from 1% to 20%, outlier magnitude factors from 1.5 to 5.0, and different outlier-location patterns confirm that the proposed method maintains a more stable estimation accuracy than WLS, conventional JSE, and Huber-JSE without VPM under diverse bad-data conditions. In downstream operational evaluations, it reduces the branch active-power flow RMSE from 1.6842 MW to 0.7215 MW, voltage-magnitude RMSE from 0.00482 p.u. to 0.00216 p.u., and active-power-loss error from 2.4368% to 0.9327% compared with WLS. These quantitative results indicate that the proposed approach can improve the grid model accuracy under imperfect measurements, thereby supporting reliable and sustainable smart-grid operation. Full article

Vehicular Ad Hoc Networks (VANETs) face significant challenges in high-mobility environments, where dynamic channel conditions, particularly Doppler Shift (DS), degrade communication reliability and increase latency, thereby undermining safety-critical applications. To address these limitations, this paper proposes a neural network (NN)-based link adaptation strategy trained using the Scaled Conjugate Gradient (SCG) algorithm. SCG is selected as a second-order approximation optimizer that leverages curvature information to produce well-conditioned weight updates particularly suited to the small, physics-constrained training dataset. The SCG-optimized model dynamically adjusts transmission parameters to mitigate DS effects, improving real-time adaptability by explicitly incorporating Doppler Shift as a key input feature. Simulation results demonstrate that the proposed approach outperforms both the conventional Auto Rate Fallback (ARF) method and the SampleRate baseline. Specifically, the SCG-based strategy achieves an overall throughput improvement of +34.6% relative to ARF (1.77 Mbps vs. 1.32 Mbps) across all tested conditions, with condition-specific gains of +16.1% at 5 Hz Doppler (0.9 km/h), +21.7% at 750 Hz (137.3 km/h), and +35.2% at 1500 Hz (274.6 km/h), while consistently reducing transmission duration. A formal ablation study confirms that the Doppler Shift feature alone contributes +67% to +78% throughput gain at high mobility (DS > 900 Hz) compared to an SNR-only model. The main contributions of this work are threefold: (i) the explicit integration of Doppler Shift as a first-class input feature for link adaptation; (ii) the application of SCG optimization for fast, stable training of a lightweight feedforward neural network on a compact, physics-constrained dataset; and (iii) the formal ablation study that isolates and quantifies the Doppler feature’s contribution, establishing that the performance gain is attributable to feature engineering rather than the neural network architecture alone. This approach offers a scalable, real-time solution for Doppler-resilient VANET link adaptation. Full article

Reconfigurable intelligent surface (RIS)-assisted unmanned aerial vehicle (UAV)-enabled mobile edge computing (MEC) has become an effective architecture for supporting computation-intensive and latency-sensitive applications by enabling flexible deployment and enhanced wireless coverage. However, when non-orthogonal multiple access (NOMA) is incorporated, the joint optimization of computation offloading, wireless resource allocation, RIS phase configuration, and UAV trajectory design becomes highly challenging owing to the strong coupling among decision variables, problem non-convexity, and time-varying system dynamics. To address these challenges, this paper investigates the energy consumption minimization problem in a NOMA-based RIS-assisted UAV-MEC system by jointly optimizing user offloading ratios, transmit power, UAV computing resource allocation, and flight trajectory. A long short-term memory (LSTM)-embedded proximal policy optimization (PPO) algorithm is developed to capture the temporal dependencies of system states and enable adaptive decision-making in dynamic environments. In addition, a closed-form phase conjugation-based optimal RIS configuration is derived and incorporated into the environment model to reduce the action space and improve training efficiency. The simulation results show that the proposed LSTM-PPO method converges faster and achieves lower energy consumption than conventional PPO, deep deterministic policy gradient (DDPG), and fixed offloading schemes, while exhibiting improved stability and scalability in the tested multi-user scenarios. These results demonstrate the effectiveness of combining temporal learning and model-assisted RIS optimization for energy efficient resource management in RIS-assisted UAV-MEC systems. Full article

This study presents an AI-assisted thermodynamic and computational fluid dynamics (CFD) evaluation of a β-type Stirling engine to improve its thermal efficiency and indicated power output. The engine performance was investigated using Restricted Dimensions Thermodynamics (RDT), the Schmidt thermodynamic model, and three-dimensional CFD simulations under various operating and geometric conditions. Key parameters including rotational speed, phase angle, piston diameter, displacer stroke, porosity, and charged pressure were systematically analyzed to determine their influence on engine behavior. A feed-forward artificial neural network (ANN) trained using the Levenberg–Marquardt optimization algorithm was integrated with CFD-generated datasets to predict engine performance and accelerate the optimization process. The AI-assisted optimization was coupled with the Variable Step-size Simplified Conjugate Gradient Method (VSCGM) to identify near-optimal operating conditions while reducing computational cost. Simulation results demonstrated that the optimization process improved the indicated power from 180.33 W to 185.44 W and increased thermal efficiency from 10.32% to 11.54%. The results also showed close agreement between predicted and experimental pressure–temperature profiles, confirming the reliability of the proposed methodology. Furthermore, CFD analyses revealed that increasing piston diameter and optimizing porosity enhanced heat transfer and pressure distribution within the engine chambers, resulting in improved thermodynamic performance. The proposed AI-driven framework provides a reliable and computationally efficient approach for the design and optimization of advanced β-type Stirling engines operating under realistic thermal conditions. 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

We propose a novel subspace derivative-free conjugate gradient method for solving large-scale nonlinear monotone equations with convex constraints. At each iteration, the search direction is constructed by minimizing a quadratic model within a subspace spanned by the current negative function value vector and the two most recent search directions. The algorithm incorporates a hyperplane projection technique to generate feasible iterative points. Under reasonable assumptions, we establish the global convergence and R-linear convergence rate of the proposed method. Extensive numerical experiments on benchmark problems demonstrate that the new algorithm significantly outperforms state-of-the-art derivative-free methods in terms of number of iterations, function evaluations, and CPU time. The results confirm the efficiency and robustness of the proposed approach for solving large-scale monotone systems. Full article

Recursive least-squares (RLS) adaptive algorithms are capable of outperforming least-mean-square (LMS) methods for the identification of long-length impulse responses due to their ability to mitigate the high correlation properties of input signals, such as speech. Despite the encouraging results obtained in terms of tracking speed and accuracy, with respect to LMS methods, most RLS algorithms manifest numerical stability issues. Moreover, when an unknown system changes, the identification process needs to adapt to the new impulse response as soon as possible. The algorithm can require a significant amount of time to generate new accurate results in acoustic echo cancellation (AEC) scenarios. Due to the slow propagation speed of sound, acoustic echo paths are usually modeled using thousands of numerical coefficients, and adaptation energy remains relatively limited. A compromise is usually made between tracking capabilities and steady-state accuracy when choosing the forgetting factor (the most important parameter of the RLS algorithm). This paper analyzes a variable forgetting factor (VFF) RLS type of adaptive filter combined with the conjugate gradient (CG) line search method, which is designed to avoid the classical matrix inversion approach. This VFF-RLS-CG adaptive method is not susceptible to numerical stability issues and is designed to adapt its statistical estimates by determining whether a tracking situation occurs or whether the unknown system is not significantly different. Correspondingly, when necessary, the forgetting factor is decreased for faster adaptation to changes in the working environment. When the filter is estimated to work at steady-state, the above-mentioned parameter’s value is increased in order to boost the accuracy of the adaptive filter. The theoretical model is validated using simulations in AEC scenarios with tracking occurrences and relevant steady-state intervals. Full article

This paper proposes an accelerated Riemannian conjugate gradient method based on the Barzilai-Borwein (BB) technique, termed ABBSRCG, for unconstrained optimization on Riemannian manifolds. Building upon classical Riemannian conjugate gradient frameworks, the method enhances step-size selection through a Wolfe-condition-informed strategy and incorporates a dynamic mechanism that adaptively adjusts the computed step length. The resulting algorithm achieves both high efficiency and numerical stability. Compared to conventional approaches such as the Fletcher-Reeves (FR)- type Riemannian conjugate gradient method, the Dai-Yuan (DY)- type Riemannian conjugate gradient method, ABBSRCG maintains the sufficient descent property regardless of whether a line search is used or not. Under mild assumptions, we establish the global convergence of ABBSRCG for u-strongly geodesically convex functions on Riemannian manifolds. Experiments on sphere and oblique manifolds show that ABBSRCG requires fewer iterations and achieves higher computational efficiency than existing Riemannian conjugate gradient methods, confirming its efficiency and reliability for large-scale Riemannian optimization problems. 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

Marine electric-source time domain electromagnetic (TDEM) surveys typically involve the simultaneous movement of transmitters and receivers, which generates a large number of transmitter–receiver pairs. This acquisition geometry creates notable challenges for 3D inversion, mainly because of the large data volume and high computational cost. However, the electromagnetic “sensitive region” for each transmitter–receiver pair is much smaller than the full survey area. Based on this feature, we propose an efficient 3D inversion approach using the footprint technique. By clearly defining the sensitivity region, referred to as the footprint domain, for each pair, the method builds the sensitivity matrix only within localized subsurface regions that significantly affect the observed response. This approach greatly reduces both forward modeling cost and memory requirements. The forward modeling adopts an integral equation method combined with cosine transforms for fast 3D field computation, while the inversion framework uses a regularized conjugate-gradient algorithm, further accelerated by parallel computing under footprint domain constraints. Numerical simulations also examine the effects of offset, time channel, seawater thickness, and resistivity on the footprint domain, helping clarify the spatiotemporal diffusion behavior of TDEM fields in shallow marine environments. Tests on representative models show that the proposed method remains stable and accurate under complex geological conditions while significantly improving computational efficiency. In particular, the footprint domain technique improves inversion speed by about 55% compared with full domain inversion. These results indicate that the proposed approach provides a reliable and scalable option for large-scale 3D inversion of marine TDEM data. Full article

The increasing demand for poultry meat, driven by its favorable nutritional profile, including low cholesterol and high protein content, has resulted in intensified production volumes and, consequently, elevated ammonia (NH₃) emissions. Artificial intelligence-based predictive approaches offer an effective alternative to conventional treatment-oriented methods by enabling faster and more accurate estimation of NH₃ removal performance. This study aimed to predict the ammonia removal efficiency of broiler litter generated during a production cycle under controlled laboratory-scale conditions using artificial neural networks (ANNs) trained with different learning algorithms. Four ANN models were developed based on the Levenberg–Marquardt (LM), Fletcher–Reeves (FR), Scaled Conjugate Gradient (SCG), and Bayesian Regularization (BR) algorithms. The results showed that the LM-based model with 12 hidden neurons achieved the highest predictive performance (R² = 0.9777; MSE = 0.0033; RMSE = 0.0574; MAPE = 0.0833), while the BR-based model with 10 neurons showed comparable accuracy. In comparison with the FR and SCG models, the LM algorithm demonstrated superior predictive accuracy and generalization capability. Overall, the findings suggest that ANN-based modeling is a reliable, data-informed approach for estimating NH₃ removal efficiency, providing a potential decision-support framework for ammonia mitigation strategies in poultry production systems. Full article