Energy and Exergy Analysis of Apple Drying Using Fluidized Bed Method: A Comparison of GMDH Neural Network and ANN-GA Models

This research, which has practical implications for the food engineering and processing industry, estimated the energy and exergy of apple drying using a Group Method of Data Handling (GMDH) neural network and a hybrid artificial neural network-genetic algorithm (ANN-GA). Osmotic and natural samples were tested in the form of apple cubes with a height of ۵ mm and sides of ۱۰ mm ×۱۰ mm, ۸ mm × ۸ mm, and ۶ mm × ۶ mm dried by fluidized bed method at three air velocities of ۴, ۶, and ۸ m/s and temperatures of ۴۰, ۴۵, and ۵۰℃. The results showed that energy consumption, energy use ratio, exergy efficiency, and exergy loss were elevated by increasing the temperature and air velocity and reducing the sample sizes in natural and osmotic samples, which were directly relevant to the industry. It was also observed that the GMDH neural network for energy consumption, energy use ratio, exergy loss, and exergy efficiency have linear correlation coefficients (R) of ۰.۹۵۰۹۷, ۰.۹۲۲۰۲, ۰.۹۱۴۶۴, and ۰.۹۱۲۵۸, respectively, suggesting that it outperforms the ANN-GA. The weakest performance of the GMDH network was associated with the exergy efficiency. The ANN-GA had the best energy consumption and lowest exergy loss performance.

Keywords:

Apple , Artificial neural network , Genetic Algorithm , drying