Wyniki wyszukiwania - BazTech

1

Intelligent Design of an Ultra-Thin Near-Ideal Multilayer Solar Selective Absorber Using Grey Wolf Optimization Linked to Deep Learning

Gliti Oussama, El Idrissi Mohamed Chafik, Igouzal Mohammed

Ecological Engineering & Environmental Technology

|

2024

|

Vol. 25, iss. 2

70--87

EN

This study explored the development of an optimal effective solar absorber by leveraging recent advancements in artificial intelligence and nanotechnology. A predictive computational approach for designing a multilayer metal-dielectric thin film solar selective absorber, specifically the SiO2/Cr/SiO2/Cr/SiO2/Cu structure was proposed. The adopted approach integrates the transfer matrix method (TMM) as a predictive electromagnetic tool and combines it with the swarm-based heuristic algorithm grey wolf optimization (GWO) linked to machine learning algorithms, specifically the artificial neural network (ANN). Through dynamic modeling and rigorous testing against multiple static versions, the adopted approach demonstrates exceptional predictive performance with an value of 0.999. The results obtained using this novel GWO-ANN approach reveal near-perfect broadband absorption of 0.996534 and low emission of 0.194170594 for the designed thin film structure. These outcomes represent a significant advancement in photo-to-thermal conversion efficiency, particularly for a working temperature of 500 °C and a solar concentration of 100 suns, showcasing its potential for practical applications across various fields. Additionally, the designed structure meets the stringent thermal stability requirements necessary for current Concentrated solar power (CSP) projects. This emphasizes its suitability for integration into existing CSP systems and highlights its potential to contribute to advancements in solar energy technology.

2

Artificial neural network and energy budget method to predict daily evaporation of Boudaroua reservoir (northern Morocco)

En-nkhili Hicham, Nizar Imane, Igouzal Mohammed, Touazit Azzeddin, Youness Nizar, Etebaai Issam

Journal of Water and Land Development

|

2023

|

no. 57

107--115

EN

Evaporation is one of the main essential components of the hydrologic cycle. The study of this parameter has significant consequences for knowing reservoir level forecasts and water resource management. This study aimed to test the three artificial neural networks (feed-forward, Elman and nonlinear autoregressive network with exogenous inputs (NARX) models) and multiple linear regression to predict the rate of evaporation in the Boudaroua reservoir using the calculated values obtained from the energy budget method. The various combinations of meteorological data, including solar radiation, air temperature, relative humidity, and wind speed, are used for the training and testing of the model’s studies. The architecture that was finally chosen for three types of neural networks has the 4-10-1 structure, with contents of 4 neurons in the input layer, 10 neurons in the hidden layer and 1 neuron in the output layer. The calculated evaporation rate presents a typical annual cycle, with low values in winter and high values in summer. Moreover, air temperature and solar radiation were identified as meteorological variables that mostly influenced the rate of evaporation in this reservoir, with an annual average equal to 4.67 mm∙d-1. The performance evaluation criteria, including the coefficient of determination (R2), root mean square error (RMSE) and mean absolute error (MAE) approved that all the networks studied were valid for the simulation of evaporation rate and gave better results than the multiple linear regression (MLR) models in the study area.

3

Development of a Sustainable Solar Water Desalinator Using a Novel Hollow Hemispherical Grid Shell Solar Selective Absorber Designed via Phasor Particle Swarm Algorithm

Gliti Oussama, Igouzal Mohammed, El Idrissi Mohamed Chafik

Ecological Engineering & Environmental Technology

|

2023

|

Vol. 24, iss. 9

130--149

EN

In this pioneering work, we propose a manufacturing plan for a 3D hollow hemispherical solar selective absorber (HSSA). The HSSA stands out as a superior choice compared to planar absorbers, thanks to its numerous benefits and wide-ranging applications, particularly in solar harvesting and photothermal desalination. Importantly, HS-SAs reduce radiative losses by emitting thermal radiation along their curved surfaces, which enhances concentration ratios and minimizes these losses. This study addresses the intricacies of fabricating the HSSA’s 3D convex shape. Our approach draws inspiration from a set of 2D flat solar selective absorbers (SSAs), each fine-tuned to adapt angles and intensities in response to solar radiation. These optimized SSAs are then arranged within a grid shell framework. As an illustrative example, we consider the widely-used selective coating W/Al2 O3-W/Al2O3. We optimize parameters, including layer thicknesses and the incorporation of metal in the absorber, to attain optimal values for photothermal conversion output under varying oblique incidence angles. For this optimization process, we employ the non-parametric particle swarm algorithm known as ‘phasor,’ recognized for its autonomous search for global optima in complex and multimodal optimization problems. Our calculations yield a remarkable photo-thermal conversion efficiency, reaching up to 0.966429. This research is driven by the aspiration to maintain such high efficiency, even in the face of fluctuations in solar radiation incidence and intensity throughout the day. Simplifying calculations, we divide the hemisphere into five spots, optimizing each for peak performance according to its positioning. These collective efforts and innovations culminate in the development of a compact solar water desalination system, engineered for efficient operation, even in the presence of one sun.