A 14-year-long data set containing daily values of meteorological variables was used to train three artificial neural networks (ANNs) for daily, weekly averaged and monthly averaged global solar radiation prediction for Fortaleza, in the Brazilian Northeast region. Local climate is semiarid coastal. Day of the year, maximum temperature, minimum temperature, irradiance, precipitation, cloudiness, extraterrestrial radiation, relative humidity, evaporation and wind speed were adopted as predictors. The ANNs were developed by an in-house code and trained with the Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithm. Besides the lack of explicit predictors able to model El Niño and La Niña phenomena, which have strong influence on local weather, the accuracy of the predictions was considered excellent according to its values of normalized root-mean-square error (nRMSE) and good relative to mean absolute percentage error (MAPE) values. Both error metrics presented the smallest values for the monthly case study.

ResumoNo Brasil existem muitos locais que não são têm acesso a energia elétrica, principalmente em áreas rurais de agricultura familiar. Isto tem acentuado a importância da utilização de fontes de energia renováveis, como a energia eólica. Este trabalho consistiu no projeto, construção e teste de campo de duas pequenas turbinas eólicas de três pás, utilizando dois perfis aerodinâmicos diferentes. O objetivo foi comparar a influência destes perfis no desempenho aerodinâmico das turbinas. Com a Teoria do Momento do Elemento de Pá (BEM), duas turbinas eólicas de pequeno porte foram projetadas e construídas, tento como diferencial os perfis aerodinâmicos utilizados em sua seção: NACA 0012 (simétrico) e 4412 (cambado). Os resultados obtidos em campo, depois de analisados através de métodos estatísticos apropriados, demonstraram que os desempenhos das turbinas são similares em faixas de rotação próximas à de projeto (λ=5). No entanto, em rotações abaixo e acima do projetado o perfil NACA 4412 tem desempenho superior. Palavras-chave: Energia Eólica, perfil aerodinâmico, aerogerador de pequeno porte AbstractIn Brazil, there are many places that do not have access to electric energy, mainly in rural areas with small farms. This situation has accentuated the importance of renewable energy sources, such as wind energy. This work consisted of the design, construction and field testing of two small three-bladed wind turbines with two different aerodynamic profiles. The aim of the study was to compare the profile influence on the turbine aerodynamic performance. Using the blade element momentum (BEM) theory, two wind turbines were designed and built with different cross-section aerodynamic profiles (NACA 0012 (symmetric) and 4412 (chambered)). Following statistical analysis, the results of the field tests demonstrated that the performances of the turbines are similar when the rotational speed is near the designed value (λ=5). However, when the rotational speed is under or above the designed value, the NACA 4412 profile yields superior performance.