A novel technique based on artificial intelligence for modeling the required temperature of a solar bread cooker equipped with concentrator through experimental data

摘要

In the present study, a combination of the modified sine and cosine algorithm (MSCA) and teaching-learning-based optimization (TLBO) algorithm is integrated with the neuro-fuzzy system to obtain three hybrid models. The proposed model predicts the effects of design parameters including the bottom galvanized protective edge of the cooking plate, top insulator cap of the cooking plate, position of the cooking plate, time duration of bread cooking and weather conditions on the dependent parameter which is the required temperature of a solar bread cooker equipped with a concentrator. For this purpose, the networks are trained on the basis of the experimentally measured data. The goal is to assess the ability of the hybrid networks for modeling cooking plate required based on the input variables. The quality of the bread produced by the solar cooker is evaluated by proper selection of the design parameters. The results show twelve breads per hour each with 200 g weight of dough can be produced by the cooker for at least six hours in every sunny day in eight months of the year, and also, the best hybrid network predicts the results with a low error which guarantees the performance of the applied hybrid model. (C) 2020 Institution of Chemical Engineers. Published by Elsevier B.V. All rights reserved.