Search Results (602)

Reservoir evaporation is a vital component of the hydrological cycle and presents considerable challenges for sustainable water management, especially in arid and semi-arid regions. This study assesses the effectiveness of two Artificial Intelligence (AI) methods: Multilayer Perceptron (MLP) and Adaptive Neuro-Fuzzy Inference System (ANFIS), a combination ANN with fuzzy logic, in estimating daily evaporation from a large reservoir in a semi-arid region. Using eight years of hydrometeorological data from a nearby station, the study employed the ReliefF algorithm as a feature selection method for relevant input variables. The dataset was divided into training, validation, and testing subsets with 5% and 10% validation ratios, using four train–test splits of 70:30, 75:25, 80:20, and 85:15. Various training algorithms (e.g., Levenberg–Marquardt) and membership functions (e.g., generalized bell-shaped functions) were tested for both models. MLP consistently outperformed ANFIS on the test sets, showing higher R² and lower RMSE values. In the best-performing 70:30 split, MLP achieved an R² of 0.8069 and RMSE of 0.0923, compared to ANFIS with an R² of 0.3192 and RMSE of 0.2254. The findings highlight the AI-based approaches’ potential to support improved evaporation forecasting and integration into decision support tools for water resource planning amid changing climatic conditions. Full article

Local scour around bridge piers is one of the primary causes of structural failure in bridges. Therefore, this study focuses on addressing the estimation of maximum scour depth (d_sm), which is essential for safe and resilient bridge design. Many studies in the last eight decades have included metadata collection and developed around 80 empirical formulas using various scour-affecting parameters of different ranges. To date, a total of 33 formulas have been comparatively analyzed and ranked based on their predictive accuracy. In this study, novel formulas using semi-empirical methods and gene expression programming (GEP) have been developed alongside an artificial neural network (ANN) model to accurately estimate d_sm using 768 observed data points collected from published work, along with eight newly conducted experimental data points in the laboratory. These new formulas/models are systematically compared with 74 empirical literature formulas for their predictive capability. The influential parameters for predicting d_sm are flow intensity, flow shallowness, sediment gradation, sediment coarseness, time, constriction ratio, and Froude number. Performances of the formulas are compared using different statistical metrics such as the coefficient of determination, Nash–Sutcliffe efficiency, mean bias error, and root-mean-squared error. The Gauss–Newton method is employed to solve the nonlinear least-squares problem to develop the semi-empirical formula that outperforms the literature formulas, except the formula from GEP, in terms of statistical performance metrics. However, the feed-forward ANN model outperformed the semi-empirical model during testing and validation phases, respectively, with higher CD (0.790 vs. 0.756), NSE (0.783 vs. 0.750), lower RMSE (0.289 vs. 0.301), and greater prediction accuracy (64.655% vs. 61.935%), providing approximately 15–18% greater accuracy with minimal errors and narrower uncertainty bands. Using user-friendly tools and a strong semi-empirical model, which requires no coding skills, can assist designers and engineers in making accurate predictions in practical bridge design and safety planning. Full article

With the growing demand for energy, oil and gas exploration and development are progressively moving into deep and ultra-deep formations, where extreme temperatures and pressures create complex challenges for drilling operations. While drilling fluids are critical for controlling bottom-hole pressure, cooling drill bits, and removing cuttings, accurately characterizing their rheological behavior under high-temperature and high-pressure (HTHP) conditions remains a key focus, as existing research has limitations in model applicability and parameter prediction range under extreme downhole environments. To address this, the study aims to determine the optimal rheological model and establish a reliable mathematical prediction model for drilling fluid rheological parameters under HTHP conditions, enhancing the precision of downhole temperature and pressure calculations. Rheological experiments were conducted on eight field-collected samples (4 water-based and four oil-based drilling fluids) using a Chandler 7600 HTHP rheometer, with test conditions up to 247 °C and 140 MPa; nonlinear fitting via a hybrid Levenberg–Marquardt and Universal Global Optimization algorithm and multivariate regression were employed for model development. Results showed that oil-based and water-based drilling fluids exhibited distinct rheological responses to temperature and pressure, with the Herschel–Bulkley model achieving superior fitting accuracy (coefficient of determination > 0.999). The derived prediction model for Herschel–Bulkley parameters, accounting for temperature-pressure coupling, demonstrated high accuracy (R² > 0.95) in validation. This research provides an optimized rheological modeling approach and a robust prediction tool for HTHP drilling fluids, supporting safer and more efficient deep and ultra-deep drilling operations. Full article

As a common signal sensing device in pulsed eddy current detection, coil sensors often have parameter offset problems in practical applications. The error in the receiving coil parameters will have a great impact on the early signal. In order to ensure the accuracy of the early signal, this paper first analyzes the response characteristics of the receiving coil and the influence of the coil parameters on the accuracy of signal deconvolution and establishes the mathematical relationship between the response signal and the characteristic parameters, and between the characteristic parameters and the receiving coil parameters under active underdamped oscillation. Subsequently, the parameter feature extraction errors under different state switching capacitors were compared through simulation analysis, the state switching capacitor value was determined, and the receiving coil parameter solution method based on the Levenberg–Marquardt (LM) algorithm was determined based on the parameter feature extraction results. The experimental results demonstrate that the proposed method achieves a capacitance estimation error of just 0.0159% and an inductance error of 0.158%, effectively minimizing early signal distortion and enabling precise identification of receiving coil parameters. Full article

Metal-oxide surge arresters (MOSAs) are critical devices for overvoltage protection in power systems, and the aging characteristics of their zinc oxide (ZnO) varistors under impulse and power-frequency voltages exhibit significant differences. However, traditional methods for monitoring the aging state of surge arresters suffer from limitations such as insufficient sensitivity and vulnerability to harmonic interference. Therefore, this study conducted accelerated aging experiments on ZnO varistor samples under negative-polarity impulse currents. Key parameters were measured, including the DC reference voltage, the DC leakage current, nonlinear coefficients, and the full current under harmonic-containing power-frequency voltage at a voltage ratio of 0.6. The resistive component was accurately extracted from the full current using a separation method based on the Levenberg–Marquardt (LM) optimization algorithm. Spectral analysis was then performed on both the full current and the extracted resistive current components. The experimental results demonstrate a significant polarity effect in the aging of ZnO varistors under unipolar impulse currents. The LM optimization algorithm enables precise extraction of the resistive current component from the full current. Furthermore, compared to the fundamental and third harmonic components, the amplitude of the DC component within the resistive current exhibits the highest sensitivity to aging, establishing it as a viable aging criterion. Full article

Quartz is a widely used mineral in dosimetric and geochronological applications due to its stable luminescence properties under ionizing radiation. This study presents an artificial neural network (ANN)-based approach to predict the optically stimulated luminescence (OSL) decay curves of quartz extracted from Mediterranean beach sand samples in Turkey. Experimental OSL signals were obtained from quartz samples irradiated with beta doses ranging from 0.1 Gy to 1034.9 Gy. The dataset was used to train ANN models with three different learning algorithms: Levenberg–Marquardt (LM), Bayesian Regularization (BR), and Scaled Conjugate Gradient (SCG). Forty-seven decay curves were used for training and three for testing. The ANN models were evaluated based on regression accuracy, training–validation–test performance, and their predictive capability for low, medium, and high doses (1 Gy, 72.4 Gy, 465.7 Gy). The results showed that BR achieved the highest overall regression (R = 0.99994) followed by LM (R = 0.99964) and SCG (R = 0.99820), confirming the superior generalization and fits across all dose ranges. LM performs optimally at low-to-moderate doses, and SCG delivers balanced yet slightly noisier predictions. The proposed ANN-based method offers a robust and effective alternative to conventional kinetic modeling approaches for analyzing OSL decay behavior and holds considerable potential for advancing luminescence-based retrospective dosimetry and OSL dating applications. Full article

Due to insufficient absolute positioning accuracy, industrial robots frequently face challenges in efficiently performing drilling and riveting operations during the assembly of aircraft and other large-scale workpieces. To enhance the absolute positioning accuracy of industrial robots, this paper proposes a novel kinematic calibration method for industrial robots based on the Improved Grey Wolf Optimization (IGWO) algorithm. Specifically, the method employs an enhanced selection and update strategy to avoid convergence stagnation and local optimum traps. The proposed method features a novel boundary search strategy, which leverages the Dimension-oriented Learning (DL) search strategy to enhance search speed and stability. Through parameter identification and calibration experiments, the effectiveness of the method was validated using an ABB IRB4600 industrial robot and a Leica laser tracker. Additionally, compared with the Levenberg–Marquardt (LM) algorithm, Particle Swarm Optimization (PSO), and Genetic Algorithm (GA), the IGWO algorithm demonstrates faster convergence and superior optimization performance. According to the calibration experimental results, by applying the IGWO algorithm, the absolute positioning accuracy of the industrial robot is ultimately improved from 1.918 mm to 0.475 mm and the absolute positioning accuracy is improved by 75.2%. Full article

Accurate determination of the quantum yield (${\mathrm{\Phi }}_f$) in scattering media is essential for numerous scientific and industrial applications, but it remains challenging due to re-absorption and scattering-induced biases. In this study, we present a GPU-accelerated Monte Carlo simulation framework that solves the full fluorescence radiative transfer equation (FRTE), incorporating spectrally dependent absorption, scattering, and fluorescence cascade processes. The model accounts for re-emission shifts, energy scaling due to the Stokes shift and implements a digital optical twin of the experimental setup, including the precise description of the applied integrating sphere. Using Rhodamine 6G in both ethanol and PDMS matrices, we demonstrate the accuracy of the method by comparing simulated reflectance and transmission spectra with independent experimental measurements. ${\mathrm{\Phi }}_f$ and emission distributions are optimized using a Levenberg–Marquardt algorithm. The obtained quantum yields agree well with literature values for Rhodamine 6G. This approach eliminates the need for empirical correction factors, enabling the reliable determination of actual, undistorted emission spectra and the ${\mathrm{\Phi }}_f$ in complex scattering media. Full article

While horizontal roughing filters (HRFs) remain widely acclaimed for their exceptional efficiency in water treatment, especially in developing countries, they are inherently susceptible to clogging, which necessitates timely maintenance interventions. Conventional methods for managing clogging in HRFs typically involve evaluating filter head loss coefficients against established water quality standards. This study utilizes artificial neural network (ANN) for the prediction of clogging duration and effluent turbidity in HRF equipment. The ANN was configured with two outputs, the clogging duration and effluent turbidity, which were predicted concurrently. Effluent turbidity was modeled to enhance the network’s learning process and improve the accuracy of clogging prediction. The network steps of the iterative training process of ANN used different types of input parameters, such as influent turbidity, filtration rate, pH, conductivity, and effluent turbidity. The training, in addition, optimized network parameters such as learning rate, momentum, and calibration of neurons in the hidden layer. The quantities of the dataset accounted for up to 70% for training and 30% for testing and validation. The optimized structure of ANN configured in a 4-8-2 topology and trained using the Levenberg–Marquardt (LM) algorithm achieved a mean square error (MSE) of less than 0.001 and R-coefficients exceeding 0.999 across training, validation, testing, and the entire dataset. This ANN surpassed models of scaled conjugate gradient (SCG) and obtained a percentage of average absolute deviation (%AAD) of 9.5. This optimal structure of ANN proved to be a robust tool for tracking the filter clogging duration in HRF equipment. This approach supports proactive maintenance and operational planning in HRFs, including data-driven scheduling of backwashing based on predicted clogging trends. Full article

Artificial neural networks (ANNs) adjust to the underlying behavior in the dataset using a training rule or optimizer. The most popular first-and second-order optimizers, Adam (AD) and Levenberg–Marquardt (LM), were compared with the aim of predicting extreme flash floods of a runoff-dominated hydrological system. A fully connected multilayer perceptron with a shallow structure was used to reduce complexity and limit overfitting. The inputs of the ANN were determined by rainfall–water level cross-correlation analysis. For each optimizer, the hyperparameters of the ANN were selected using a grid search and the cross-validation score on a novel criterion (PERS PEAK) mixing the persistency (PERS) and the quality of flood-peak restitution (PEAK). For an extreme and unseen event used as a test set, LM outperformed AD by 25% on all performance criteria. The peak water level of this event, 66% greater than that of the training set, was predicted by 92% after more training iterations were done by the LM optimizer. This shows that the ANN can predict beyond the ranges of the training set, given the right optimizer. Nevertheless, the LM training time was up to five times longer than that of AD during grid search. Full article

Regarding the distortion correction problem of large field of view wide-angle cameras commonly used in railway visual inspection systems, this paper proposes a novel online calibration method for non-specially made cooperative calibration objects. Based on the radial distortion divisor model, first, the spatial coordinates of natural spatial landmark points are constructed according to the known track gauge value between two parallel rails and the spacing value between sleepers. By using the image coordinate relationships corresponding to these spatial coordinates, the coordinates of the distortion center point are solved according to the radial distortion fundamental matrix. Then, a constraint equation is constructed based on the collinear constraint of vanishing points in railway images, and the Levenberg–Marquardt algorithm is used to found the radial distortion coefficients. Moreover, the distortion coefficients and the coordinates of the distortion center are re-optimized according to the least squares method (LSM) between points and the fitted straight line. Finally, based on the above, the distortion correction is carried out for the distorted railway images captured by the camera. The experimental results show that the above method can efficiently and accurately perform online distortion correction for large field of view wide-angle cameras used in railway inspection without the participation of specially made cooperative calibration objects. The whole method is simple and easy to implement, with high correction accuracy, and is suitable for the rapid distortion correction of camera images in railway online visual inspection. Full article

This study aimed to train and validate two artificial neural network (ANN) models, one with four hidden layers and the other with five hidden layers, to predict the daily photovoltaic power output of a 20 Kw photovoltaic power plant with bifacial photovoltaic modules with tilt angle variation from 0° to 90° in two Moroccan cities, Ouarzazate and Oujda. To validate the two proposed models, photovoltaic power data calculated using the System Advisor Model (SAM) software version 2023.12.17 were employed to predict the average daily power of the photovoltaic plant for December, utilizing MATLAB software Version R2020a 9.8, and for the tilt angles corresponding to the latitudes of the two cities studied. The results differ from one model to another according to their mean absolute error (MAE), root mean squared error (RMSE), and coefficient of determination (R²) values. The artificial neural network model with five hidden layers obtained better results with a R² value of 0.99354 for Ouarzazate and 0.99836 for Oujda. These two proposed models are trained using the Levenberg Marquardt (LM) optimizer, which is proven to be the best training procedure. Full article

This paper presents a decentralized energy management system (EMS) based on Multilayer Perceptron Artificial Neural Networks (MLP-ANNs) and a Modified Cheetah Optimizer (MCO) to account for uncertainty in renewable generation and load demand. The proposed framework applies an MLP-ANN with Levenberg–Marquardt (LM) training for high-precision forecasts of photovoltaic/wind generation, ambient temperature, and load demand, greatly outperforming traditional statistical methods (e.g., time-series analysis) and resilient backpropagation (RP) in precision. The new MCO algorithm eliminates local trapping and premature convergence issues in classical optimization methods like Particle Swarm Optimization (PSO) and Genetic Algorithms (GAs). Simulations on a test microgrid verily demonstrate the advantages of the framework, achieving a 26.8% cost-of-operation reduction against rule-based EMSs and classical PSO/GA, and a 15% improvement in forecast accuracy using an LM-trained MLP-ANN. Moreover, demand response programs embodied in the system reduce peak loads by 7.5% further enhancing grid stability. The MLP-ANN forecasting–MCO optimization duet is an effective and cost-competitive decentralized microgrid management solution under uncertainty. Full article

This present study proposes different machine learning-based predictors for the assessment of the residual compressive strength of Self-Compacting Concrete (SCC) subjected to high temperatures. The investigation is based on several literature algorithmic approaches based on Artificial Neural Networks with distinct training algorithms (Bayesian Regularization, Levenberg–Marquardt, Scaled Conjugate Gradient, and Resilient Backpropagation), Support Vector Regression, and Random Forest methods. A training database of 150 experimental data points is derived from a careful literature review, incorporating temperature (20–800 °C), geometric ratio (height/diameter), and corresponding compressive strength values. A statistical analysis revealed complex non-linear relationships between variables, with strong negative correlation between temperature and strength and heteroscedastic data distribution, justifying the selection of advanced machine learning techniques. Feature engineering improved model performance through the incorporation of quadratic terms, interaction variables, and cyclic transformations. The Resilient Backpropagation algorithm demonstrated superior performance with the lowest prediction errors, followed by Bayesian Regularization. Support Vector Regression achieved competitive accuracy despite its simpler architecture. Experimental validation using specimens tested up to 800 °C showed a good reliability of the developed systems, with prediction errors ranging from 0.33% to 23.35% across different temperature ranges. Full article

This paper addresses the trajectory tracking control problem of a six-degree-of-freedom Gough–Stewart Platform (GSP) by proposing a control strategy that combines a sliding mode (SM) controller with a rapid forward kinematics solution algorithm. The study first develops an efficient forward kinematics method that integrates Support Vector Regression (SVR) with the Levenberg–Marquardt algorithm, effectively resolving issues related to multiple solutions and local optima encountered in traditional iterative approaches. Subsequently, a SM controller based on the GSP’s dynamic model is designed to achieve high-precision trajectory tracking. The proposed control strategy’s robustness and effectiveness are validated through simulation experiments, demonstrating superior performance in the presence of model discrepancies and external disturbances. Comparative analysis with traditional PD controllers and linear SM controllers shows that the proposed method offers significant advantages in both tracking accuracy and control response speed. This research provides a novel solution for high-precision control in GSP applications. Full article