Publications Scientifiques

Permanent URI for this communityhttps://dspace.univ-boumerdes.dz/handle/123456789/10

Browse

Has files: NoSubject: search.filters.subject.Artificial neural network

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    A machine learning and Particle Swarm Optimization approach for desiccant wheel modeling and performance prediction
    (Elsevier, 2025) Ghersi, Djamal Eddine; Mougari, Nour Elislam; Loubar, Khaled; Amoura, Meriem; Desideri, Umberto
    Accurate modeling of desiccant wheels (DWs) is critical for the design and optimization of energy-efficient dehumidification systems. This study presents a novel approach for predicting DW performance by coupling machine learning (ML) models with Particle Swarm Optimization (PSO) for hyperparameter tuning. To validate the effectiveness of this metaheuristic approach, the performance of the PSO-optimized models was rigorously benchmarked against counterparts tuned using conventional Bayesian Optimization (BO). Four distinct ML models, including Artificial Neural Network (ANN), k-Nearest Neighbors (KNN), Random Forest (RF), and Support Vector Regressor (SVR), were developed to predict the process air outlet temperature (Tp,out) and humidity ratio (ωp,out). The models were trained and validated on a comprehensive dataset, uniquely expanded to include experimental data from low-humidity and low-temperature deep dehumidification conditions. The results demonstrate that the PSO-optimized Artificial Neural Network (PSO-ANN) model provides superior predictive accuracy. For the process outlet temperature, the PSO-ANN model achieved a Coefficient of Determination (R2) of 0.9985 and a Root Mean Square Error (RMSE) of 0.3204 °C. For the outlet humidity ratio, it achieved an R2 of 0.9984 and a RMSE of 0.1497 g/kg. Furthermore, a SHAP (SHapley Additive exPlanations) analysis confirmed that the model’s predictions are physically consistent and interpretable. The developed high-fidelity model serves as a robust and reliable tool for the advanced analysis and design of desiccant air conditioning systems across a wide range of operational scenarios
  • No Thumbnail Available
    Item
    Prediction of Flash Points of Petroleum Middle Distillates Using an Artificial Neural Network Model
    (Pleiades Publishing, 2024) Bedda, Kahina
    An artificial neural network (ANN) model of a multilayer perceptron-type was developed to predict flash points of petroleum middle distillates. The ANN model was designed using 252 experimental data points taken from the literature. The properties of the distillates, namely, specific gravity and distillation temperatures, were the input parameters of the model. The training of the network was carried out using the Levenberg– Marquardt backpropagation algorithm and the early stopping technique. A comparison of the statistical parameters of different networks made it possible to determine the optimal number of neurons in the hidden layer with the best weight and bias values. The network containing nine hidden neurons was selected as the best predictive model. The ANN model as well as the Alqaheem–Riazi’s model was evaluated for the prediction of flash points by a statistical analysis based on the calculation of the mean square error, Pearson correlation coefficient, coefficient of determination, absolute percentage errors, and the mean absolute percentage error. The ANN model provided higher prediction accuracy over a wide distillation range than the Alqaheem–Riazi’s model. The developed ANN model is a reliable and fast tool for the low-cost estimation of flash points of petroleum middle distillates.