A neural network based model for controlling smart building skins

• Main Authors: Chih-kai Hsiao, 蕭志凱
• Other Authors: none
• Format: Others
• Language: zh-TW
• Published: 2008
• Online Access: http://ndltd.ncl.edu.tw/handle/53741826763028181414

碩士 === 國立臺灣科技大學 === 建築系 === 96 === Building skin defines the relation of people and natural environment. It should be adjustable to the changes of people needs and natural environment. Building skins need the ability of learning for the adaptation to different situations under variations of spatial functions, opening, surroundings and occupants of the building. This research advances a feasible framework which can realize smart building skins by providing the ability of learning and automatic controlling to satisfy the demands of people for a comfortable environment by adjusting parameters of the smart building skin. A neural network is used as the control system. We use a set of virtual data to evaluate the system. The result shows that the average accuracy of the system output control increases when the volume of training data increases and shows the system can learn effectively. Furthermore, the standard deviation of the distance between forecast output and target output decreases gradually when the volume of training data increases, and it shows that the output control of the system becomes more stable by continuously learning.