在大型空調系統之中,冰水主機通常都是最耗能之元件,各冰水主機初置時雖說容量與能力相同,但在運轉一段時間後,由於不同之水量分配、安裝之位置差異、水泵供給之效率、冰水主機啟動順序與運轉時間等…會使各台冰水主機運轉性能上漸漸產生差異,為清楚了解冰水主機運轉之特性,就必須知道冰水主機於不同設定之下,運轉之情況及溫度之設定,並且利用相關之參數,建立起冰水主機之耗電量模型,所以能夠清楚的掌握空調系統之中各冰水主機運轉之特性,並且在滿足空調負載需求,調度冰水主機,使各台冰水主機運轉在其最佳工作點上,就可使系統消耗之電量達到最低。 本研究使用類神經網路與迴歸分析法建立各台案例中之冰水主機耗電量特性模型,並比較其R2與平均誤差百分率,模型建立完成之後,使用基因演算法執行最佳化負載分配,求解之過程透過基因演算法之複製、交配、突變以及參數之編碼與解碼之運算過程,在滿足空調負載之情況下,求解出冰水主機調度之最低耗電量組合,研究結果顯示,使用類神經網路建立冰水主機耗電量模型,較迴歸分析法建立之冰水主機模型精確外,在基因演算法執行最佳化負載分配時,收斂之世代數與結果也呈現出較佳之表現。
In large HVAC systems, the chiller is usually the most power-consuming component. Although different chillers have similar capacities and performance at the initial stage of operation, due to factors such as varying amount of water distribution, different installation locations, pump supply efficiency, chiller initiation sequence, operating time and so forth after specific amount of operation time, different chillers gradually exhibit varying levels of operational performance. In order to determine the characteristics of chiller operation, one must monitor the status of operation and temperature settings for chillers under different configurations while using relevant parameters to build the power consumption models for chillers. With sufficient understanding of the characteristics of various chiller operation in HVAC systems, it is possible to minimize power consumption by the system by keeping various chillers operating at optimal working conditions through chiller control whilst satisfying the required cooling load. In this research, the author has adopted a neural network and regression analysis to construct models of power consumption for chillers in various case studies in order to compare their R2 and average error. With the models completed, appropriate genetic algorithms were applied to compute the optimal load distribution; through the reproduction, crossover, mutation of the genetic algorithms and the coding/decoding of relevant parameters during the computation process, the author was able to derive the combination of the lowest power consumption for the chiller control (under the premise of satisfying the cooling load requirements). Results of the research revealed that chiller power consumption model constructed from neural network turned out to offer better accuracy compared to model constructed from regression analysis. Not only that, the chiller power consumption model constructed from the neural network also offered better number of converging generations and results in the computation of optimized load distribution using a genetic algorithm.