冰蓄冷系统基于负荷预测和优化的实时控制  

The real time control based on cooling load prediction and optimization in ice storage system

作　　者：石磊[1] 王智伟[1] 赵蕾[1] 刘咸定[1] 

机构地区：[1]西安建筑科技大学环境与市政工程学院

出　　处：《西安科技学院学报》2004年第1期57-60,共4页

基　　金：陕西省教育厅专项基金项目(02JK138)

摘　　要：首先基于西安地区某办公楼空调季节的数据,进行了逐时温度和冷负荷的预测。然后,讨论了温度预测对负荷预测,负荷预测对离线优化的影响。结果表明,人工神经网络冷负荷预测的准确度不受异常天气情况的影响;而负荷预测的准确度直接影响非线性优化的结果;在线修正是至关重要的。最后,给出了实时控制中负荷预测及离线优化结果在线修正的实例。Based on the hourly data of an office building in Xi'an, the hourly temperature and cooling load are predicted. Then, the influences of temperature prediction accuracy on cooling load prediction, cooling load prediction accuracy on off-line optimization are discussed. The results show that the accuracy of cooling load prediction using artificial neural network is not affected by the abnormal weather, the accuracy of cooling load prediction has direct influence on the results of nonlinear optimization. The online correction is of great value. Finally, an example of online correction of cooling load and offline optimization in real-time control is brought forward.

关 键 词：冰蓄冷 形状因子 人工神经网络 冷负荷预测 在线修正 

分 类 号：TP273.1[自动化与计算机技术—检测技术与自动化装置]