Abstract
In this study, an optimal control of heat stress was applied to minimize the water loss of fruit during storage using an intelligent control system. The control system consists of a decision system and a feedback control system. In the decision system, the dynamic change in the rate of the water loss, as affected by temperature, is first identified using neural networks and then the optimall-step set points of temperatures that minimize the rate of the water loss are sought through simulation of the identified neural-network model using genetic algorithms. Here, anl (=6) -step control process was supposed. The length of each step was 24 h. Two optimal values, a single heat stressT= {40, 15, 15, 15, 15, 15°C} and double heat stressT= {40, 15, 40, 15, 15, 15°C}, were obtained as the optimal values under the range of 15 to 40°C. Especially, a temperature operation first rising to the highest level and then dropping to the lowest level in the given range provided a lower rate of the water loss than by keeping constant at the lowest level through whole the control process.
