Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Prediction of air temperature and relative humidity in a solar greenhouse dryer using neuro-fuzzy models

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan

Citation:  2018 ASABE Annual International Meeting  1801493.(doi:10.13031/aim.201801493)
Authors:   Alejandro Guerrero-Santana, Irineo López-Cruz, Agustín Ruíz-García, Efrén Fitz-Rodríguez, Raque Salazar-Moreno
Keywords:   Black-box models, modelling, relative humidity, solar dryer, stevia, temperature.

Abstract. The development of mathematical models allows increasing the knowledge of physical processes associated with the solar drying of agricultural products. Until now, researches have focused mainly about the generation of theoretical models, nevertheless, the parameters of this type of models are numerous and measurement is a complicated task. An alternative are neuro-fuzzy models, which could be generated using experimental data of the drying process, moreover, they could be used for automatic controller design. The objective of this work was to generate Adaptive Neuro Fuzzy Inference Systems (ANFIS) to forecast the humidity and temperature inside the solar dryer during the Stevia‘s leaves drying process. Three experiments of drying Stevia were conducted, each one using 75 kg in a solar greenhouse dryer with polycarbonate cover and parabolic shape with a surface of 108 m2 and natural ventilation. Air temperature and relative humidity were measured inside the dryer, additionally; air temperature, relative humidity, solar radiation and wind speed were measured outside the dryer. Sampling time of data acquisition for both locations was 1 minute. ANFIS models were developed for each output variable in MATLAB software and it was experimentally evaluated. According to correlation coefficient (r), root mean squared error (RMSE), mean absolute error (MAE) and modeling efficiency (EF) statistics it was shown a good agreement between model forecasting and variables measurement, providing a good estimation.

(Download PDF)    (Export to EndNotes)