×
The submission system is temporarily under maintenance. Please send your manuscripts to
Go to Editorial ManagerMaximum Power Point Tracking (MPPT) techniques are essential for maximizing energy extraction from photovoltaic (PV) systems under diverse environmental conditions. This paper reviews three widely used MPPT methods Perturb and Observe (P&O), Fuzzy Logic Control (FLC), and Artificial Neural Networks (ANN) highlighting their effectiveness in addressing challenges such as temperature fluctuations, varying irradiance, and shading. The P&O method is noted for its simplicity and low computational requirements, but it suffers from oscillations around the maximum power point under rapidly changing conditions. FLC offers enhanced adaptability and robustness by mimicking human decision-making, performing well in dynamic environments with moderate complexity. ANN-based methods demonstrate superior tracking efficiency and fast convergence, particularly under complex and highly variable conditions, due to their ability to learn and generalize from data. These findings underscore the importance of continued development of MPPT techniques, especially intelligent and hybrid approaches, to meet the growing demand for sustainable energy. Thus, solar energy remains a highly viable solution for modern energy needs.
This study implements the soft computing techniques such as Artificial Neural Network (ANN) and an adaptive Neuro-Fuzzy (ANFIS) approach. Thus to model the rutting prediction with the aid of experimental uniaxial creep test results for asphalt mixtures. Marshall samples, having Maximum Nominal Size of 12.5 mm, have been selected from previous studies. These samples have been prepared and tested under different conditions. They were also subjected to different loading stress (0.034, 0.069, 0.103) MPa, and tested at various temperature (10, 20, 40, and 55) °C. The modeling analysis revealed that both approaches are powerful tools for modeling creep behavior of pavement mixture in terms of Root Mean Square Error and Correlation Coefficient. The best results are obtained with the ANFIS model.
Artificial neural networks (ANN) as new techniques employed for the development of predictive models to estimate the needed parameters in geotechnical engineering to be used for comparison with laboratory and field tests and consequently reduce the cost, time, and effort. Flexible computing techniques are using an alternative statistical tool to analyze and evaluate experimental data from 102 consolidation tests on a variety of undisturbed soils from Ramadi city. The regression equations are developed to estimate the compression index and the compression ratio from index data. Multi-Layer Perceptron (MLP) network model is used to calculate compression index and a compression ratio of soils and comparing with the multiple linear regression statistical model MLR. It is found that the MLP showed a higher performance than MLR in predicting Cc and Cr and model accuracy between 0.81 to 16 percent. This will provide a good method for minimizing the potential inconsistency of correlations.
This paper is intended to study the effect of using upstream and downstream sheet pile in double soil layer on the seepage, uplift pressure exit gradient at toe of hydraulic structure using computer program SEEP/W software._x000D_ Depended on the software program tests were carried out with three different value of each following parameter: upstream sheet pile depth, downstream sheet pile depth, permeability for first and second soil layer, depth of first and second soil layer, with using constant upstream head and distance between the two sheet pile. For each test the quantity of seepage, exit gradient and uplift pressure at toe of hydraulics structure were determined. Based on the results of these runs an empirical equations developed to determine the quantity of seepage, uplift pressure and exit gradient at toe of hydraulic structure by using SPSS software. Also, Verify the SEEP/W results and the suggested equations with artificial neural network (ANN). The verification show difference less than 5% , 2% and 6% for exit gradient, discharge and uplift pressure respectively at toe of hydraulic structure.
In the present work the effect of Corrosion & Scale Inhibitor was evaluated by using of the commercial product (Kurita S2050) that mainly containing of (Na2HPO4) sodium phosphate as corrosion inhibitor and (C6H11NaO7) sodium glocunate as scale inhibitor & dispersant. The dosing rate of this chemical was controlled according to the treatment system depend mainly on the monitoring of LI & RI indexes for (30) days treatment in the cooling tower unit of Al-Dora Oil refinery-Baghdad. The corrosion rate and the corrosion inhibitors efficiency were calculated by measurement of weight loss in standard test coupon (AISI 1010). After 30 day of the Field Test, the result show that the treatment program performance was effective in the corrosion & scale inhibition through an acceptable corrosion rate less than 0.018 in gmd. Also the result of corrosion rate was analyzed statistically by using of (ANN) to formulate a prediction equation to corrosion rate identification.
The daily peak load forecasting for the next day is the basic operation of generation scheduling. The approach of using ANN methodology alone is limited which has generated interest to explore hybrid system. In this paper a search of genetic programming to a short term load forecasting is presented. A genetic architecture with the fitness normalization has been used to find as optimum data peak load of Baghdad city. The optimize data applied to the ANN to be trained and tested to estimate the daily peak load of Baghdad city. Different cases for load forecasting are considered with the aid of MATLAB 7 package to get the estimation of the next day. So an improvement method of genetic optimization is proposed to get a better solution for the load estimation rather than artificial neural network.
The oil industry has a direct impact on the economic feasibility of other sectors and is considered to be the most important energy source used to turn the wheels of other industries. Therefore, it was necessary to pay attention and continuously develop this industry, to find the best modern techniques for designing, pre-commissioning and controlling process, to improve efficiency, preserve energy and achieve the highest production of costly components with the highest purity of the product. This study aims to provide a literary analysis of the stages of development and progress of the dynamics and control of the petroleum industry, in particular the distillation column, because it is multivariable with high interaction between control cycles, nonlinear behaviour and large gains. Control processes have undergone many developments and modernizations to achieve the best results. Various control methods have been used, ranging from simple proportional-integral-derivative controller (PID) to advanced control strategies such as model predictive control (MPC), multivariate model predictive control (MMPC), fuzzy logic control (FLC), quadratic dynamic matrix control (QDMC), artificial neural network control (ANN) and other advanced control techniques. The authors concluded from the review that the advanced control strategies superior than the conventional methods.
This work suggests a Deep Learning (DL) architecture based on You Only Look Once YOLOv11 for Skin Cancer (SC) detection. The similarity between malignant and benign lesions makes visual inspection a failure to distinguish between them. To solve this problem, the proposed approach uses a 3-step pre-processing stage, namely hair removal, color normalization, and Contrast Limited Adaptive Histogram Equalization (CLAHE) contrasts, has been conducted to eliminate artifacts and improve image quality. Balanced data augmentation on the training set of the PROVe-AI dataset. In this process, YOLOv11 with C3k2 module and C2PSA module showed significant results in optimized multi-scale feature collection and spatial interest. The experimental outcome demonstrates that the proposed model has a classification accuracy of 93.09% and led the baseline models, such as Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Artificial Neural Network (ANN). The proposed optimized YOLOv11 architecture allows for skin cancer detection in a computationally efficient framework with promising preliminary results so that the proposed approach can be a beneficial Artificial intelligence (AI) tool for early diagnosis, particularly in a lack of high-tech medical facilities.