在現今社會,人類利用各式各樣的能源來滿足生活需求,使得我們對能源有著高度的依賴性,導致有一個潛在風險我們必須去面對,它就是全球暖化。現代的科技業競爭非常激烈,在所有設備中空調耗電量所佔的比例為最大,因此有效減少空調耗電量,必定能提升產業的競爭性。 空調系統全年各項耗電量,以冰水主機53%為主,風機28%為次,水泵及冷卻水塔占19%,本研究引用Lulu學者所提出的負載平衡方程式,以類神經建立各元件的耗電量模型,針對冰水主機、風機和水泵使用模擬退火法來尋找冰水出水溫度、風量和水量的最佳化設定點,並以滿足室內負載需求與最小耗電量為目標,達到節能之目的。 由研究結果顯示,可以明顯的看出整體耗電量降低了18%,而各個模型的準確度R2值都高達0.98以上,準確度相當高,若將實驗分為三天來看,其耗電量節省分別為24%、14%和15%,Day 1之冰水出水溫度設定值為7℃,經由負載平衡方程式計算,實際溫度平均為9.27℃即可滿足室內的需求,所以改善較多,相對的Day 3之冰水溫度設定值在12 ℃,改善的幅度也相對較少,顯示本研究方法可以有效的找出最佳化設定點,並達到節省能源的目的。
Nowadays, people consume a wide variety of energy to meet demand, result a high degree of dependence on energy. Global Warming is a big problem and we have to confront it. The industry is facing fierce market competition today. Among the energy expenses, the power consumption from air-conditioning takes up the largest portion therefore, cutting back expenses by lowering the power consumption from air-conditioning should yield instant effect. In air-conditioning system, the chiller consumes 53% of energy, the pump system 19%, and the air side facilities 28%. The study cited foreign scholars raised the thermal equilibrium equation. This thesis configures the total power consumption of the system as the objective function and achieves the minimum overall air-conditioning system power consumption under the criteria of achieving the cooling capacity that satisfies the loading requirement. By Neural Networks with Simulated Annealing for Optimal Operation of Air - Conditioning System. From the results, we find that power consumption is lowered by 18%. Accuracy of each model are above 0.98, if the experiment is divided into three days of view, the power consumption saving by 24%, 14% and 15%.It shows that this research indeed uncovers the best parameters for air-conditioning system operation that achieves the objective of power-saving.