Optimization of heat treatment for fruit during storage using neural networks and genetic algorithms

Heat treatment during storage is effective in delaying the ripening of fruit. In this study, an optimal pattern of the heat treatment for tomatoes was investigated based on their surface color, using an intelligent control technique consisting of neural networks and genetic algorithms. An objective function was given by the reciprocal number of the average value of the color change from green to red. For optimization, the control process was divided into l-steps. First, the time-history change in the surface color, as affected by temperature, was identified using neural networks. Then, l-step setpoints of temperature which maximized the objective function were sought through simulation of the identified neural-network model, using genetic algorithms. This technique allowed an optimal heat treatment to be successfully sought when the diversity of the population was kept at a high level in the evolution process. Two types of optimal heat treatments were obtained. One was the single application of heat, which is similar to the conventional type, and the other was intermittent application, given periodically. Finally, the two optimal treatments were applied to an actual system. The result showed that they gave better results on ripening than continuous cooling. Thus, this control technique seems to be suitable for optimization of the storage process for fruits and vegetables.