Exergy assessment of infrared assisted air impingement dryer using response surface methodology, Back Propagation-Artificial Neural Network, and multi-objective genetic algorithm

Abstract

This study deals with the exergy analysis of the thin-layer drying process of apple fruit via an infrared-assisted air impingement dryer. In the study, process conditions, namely, drying temperature (50–70 °C), slice thickness (2–6 mm), and recirculation ratio (10–90 %) were considered as independent parameters. The impacts of process parameters were studied over the responses, namely, exergy efficiency, exergy loss, improvement potential, and sustainability index. A comparative study was conducted between a Back-Propagation Artificial Neural Network (BP-ANN) coupled with a multi-objective genetic algorithm (MOGA) and Response Surface Methodology (RSM). It was found that both BP-ANN and RSM had good prediction ability, but BP-ANN performed slightly better with higher R2, lower RMSE, and MAE values. The optimized conditions for BP-ANN-MOGA were found to be a temperature of 50 °C, slice thickness of 3.9 mm, and recirculation ratio of 76.38 %, which yielded a response of exergy efficiency of 62.23 %, exergy loss of 221 kJ, an improvement potential of 105 kJ, and a sustainability index of 2.65. This study showed a better exergy assessment of the developed hybrid dryer from a thermodynamic point of view.