Integrated control of the cooling system and surface openings using the artificial neural networks

摘要: Abstract This study aimed at suggesting an indoor temperature control method that can provide a comfortable thermal environment through the integrated of cooling system and surface openings. Four logic were developed, employing different application levels rules artificial neural network models. Rule-based methods represented conventional approach while ANN-based applied for predictive adaptive controls. Comparative performance tests conventional- numerically conducted double-skin-facade building, using MATLAB (Matrix Laboratory) TRNSYS (Transient Systems Simulation) software, after proving validity by comparing simulation field measurement results. Analysis revealed controls openings improved conditions with increased periods decreased standard deviation from center range. In addition, proposed effectively reduced number operating condition changes openings, which prevent failure. The logic, however, did not show superiority in energy efficiency over logic. Instead, they have amount heat removal system. From analysis, it be concluded was able to keep more comfortably stably within range due its features.