摘要
Agricultural control systems are characterized by complexity and uncertainly. A skilled grower can deal well with crops based on his own intuition and experience. In this study, an intelligent optimization technique mimicking the simple thinking process of a skilled grower is proposed and then applied to dynamic optimization of temperature that minimizes the water loss in fruit during storage. It is supposed that the simple thinking process of a skilled grower consists of two steps: 1) “learning and modeling” through experience and 2) “selection and decision of an optimal value” through simulation of a mental model built in his brain by the learning. An intelligent control technique proposed here consists of a decision system and a feedback control system. In the decision system, the dynamic change in the rate of water loss as affected by temperature was first identified and modeled using neural networks (“learning and modeling”), and then the optimal value (l-step set points) of temperature that minimized the rate of water loss was searched for through simulation of the identified neural-network model using genetic algorithms (“selection and decision”). The control process for 8 days was divided into 8steps. Two types of optimal values, a single heat stress application, such as 40℃, 15℃, 15℃, 15℃, 15℃, 15℃, 15℃and 15℃, and a double heat stress application, such as 40℃, 15℃, 40℃, 15℃, 15℃, 15℃, 15℃and 15℃, were obtained under the range of 15℃￡T￡40℃. These results suggest that application of heat stress to fruit is effective in maintaining freshness of fruit during storage.
Agricultural control systems are characterized by complexity and uncertainly. A skilled grower can deal well with crops based on his own intuition and experience. In this study, an intelligent optimization technique mimicking the simple thinking process of a skilled grower is proposed and then applied to dynamic optimization of temperature that minimizes the water loss in fruit during storage. It is supposed that the simple thinking process of a skilled grower consists of two steps: 1) “learning and modeling” through experience and 2) “selection and decision of an optimal value” through simulation of a mental model built in his brain by the learning. An intelligent control technique proposed here consists of a decision system and a feedback control system. In the decision system, the dynamic change in the rate of water loss as affected by temperature was first identified and modeled using neural networks (“learning and modeling”), and then the optimal value (l-step set points) of temperature that minimized the rate of water loss was searched for through simulation of the identified neural-network model using genetic algorithms (“selection and decision”). The control process for 8 days was divided into 8steps. Two types of optimal values, a single heat stress application, such as 40℃, 15℃, 15℃, 15℃, 15℃, 15℃, 15℃and 15℃, and a double heat stress application, such as 40℃, 15℃, 40℃, 15℃, 15℃, 15℃, 15℃and 15℃, were obtained under the range of 15℃￡T￡40℃. These results suggest that application of heat stress to fruit is effective in maintaining freshness of fruit during storage.
