為符合綠色製造與節能減碳目標，政府與企業皆為節電發起構想並積極行動，在本研究中，透過改善措施降低冰機系統的能耗，提高其運作效率，除能為無塵室維護穩定的溫溼度提供保障，亦可幫助科技製造廠降低能源成本，提升其綠色製造的能力。
本研探討冰機系統直接影響效率之可控制因子冷卻水塔水溫，因冷卻水塔水溫調整亦會直接影響冷卻水塔本身效率，為平衡水塔與冰機主機的最佳整體效率，本研究利用AutoML(Automated machine learning)進行冷卻水塔與冰機系統運轉參數進行冷卻水塔最佳水溫設定點模預測。資料方面，為確保模型能計算最佳的運短點，進一步探討參數影響原因與訂定篩選條件，最後排除無效參數並以歷年資料效率最佳的前20%作為訓練資料。
從訓練後得到的數組模型中，以最高得分的演算法堆疊法(Stack)導入使用，利用監控設備回傳訊號導入模型進行冷卻水控制點推算，推算出當下需求條件及外器條件下最佳的運轉點，並依照模型推算目標值實際控制冷卻水塔，得到相較於往年水塔更好的運轉效率。

To align with the objectives of green manufacturing and energy conservation with carbon reduction, both governmental bodies and enterprises have initiated and actively implemented energy-saving measures. In this study, targeted improvement strategies were employed to reduce the energy consumption of the chiller system and enhance its operational efficiency. These measures not only ensure stable temperature and humidity control within cleanroom environments but also contribute to lowering energy costs and advancing the green manufacturing capabilities of technology-based manufacturing facilities.
This research investigates the cooling tower water temperature as a key controllable factor directly influencing the efficiency of chiller systems. Adjustments to this temperature also have a direct impact on the cooling tower’s own performance. Therefore, the primary objective is to achieve an optimal balance between the efficiencies of both the cooling tower and the chiller unit. To this end, Automated Machine Learning was employed to predict the optimal cooling tower water temperature setpoint based on the operational parameters of the cooling tower and the chiller system.
Among the trained models, the Stacking ensemble algorithm achieved the highest performance score and was subsequently adopted. Feedback signals from the monitoring system were incorporated into the model to estimate the optimal operating point under prevailing demand and environmental conditions. The cooling tower was then regulated in real time according to the model’s predicted target values, resulting in a marked improvement in operational efficiency compared with previous years.

[1]H. Cai, S. Shen, Q. Lin, X. Li, and H. Xiao, “Predicting the Energy Consumption of Residential Buildings for Regional Electricity Supply-side and Demand-side Management,” IEEE Access, vol. 7, pp. 30386–30397, 2019.
[2]S. Yordanova, D. Merazchiev, and L. Jain, “A Two-variable Fuzzy Control Design with Application to an Air-conditioning System,” IEEE Transactions on Fuzzy Systems, vol. 23, no. 2, pp. 474–481, April 2015.
[3]Ma Y, Borrelli F, Hencey B, Coffey B, Bengea S, Haves P, “Model Predictive Control for the Operation of Building Cooling Systems,” IEEE Transactions On Control Systems Technology,pp.796 – 803, March 2010
[4]Shikoun NH, Al-Eraqi AS, Fathi IS. BinCOA, “An Efficient Binary Crayfish Optimization Algorithm for Feature Selection,” IEEE Access, vol .33,pp.28621–28635, February. 2024.[Online]. Available: https://doi.org/10.1109/access.2024.3366495
[5]Sondes Gharsellaoui, Majdi Mansouri, Mohamed Trabelsi, Mohamed-Faouzi Harkat, Shady S. Refaat, Hassani Messaoud,“Interval-Valued Features Based Machine Learning Technique for Fault Detection and Diagnosis of Uncertain HVAC Systems, ”IEEE Access, vol .8,pp.171892 – 171902, August 2020. [Online]. Available: https://doi.org/10.1109/ACCESS.2020.3019365
[6]W.T. Ho, F.W. Yu,” Improved Model and Optimization for the Energy Performance of Chiller System with Diverse Component Staging,”ScienceDrect：Energy,vol .217,pp.119376, February 2021. [Online]. Available: https://doi.org/10.1016/j.energy.2020.119376
[7]Chun-Lien Su, Kuen-Tyng Y, “Evaluation of Differential Pressure Setpoint of Chilled Water Pumps in Clean Room HVAC Systems for Energy Savings in High-Tech Industries,” IEEE Transactions on Industry Applications, vol .49, Issue: 3, May-June 2013. [Online]. Available: https://doi.org/10.1109/TIA.2013.2251992
[8]A. Beghi, L. Cecchinato, C. Corazzol, M. Rampazzo, F. Simmini, G.A. Susto,” A One-Class SVM Based Tool for Machine Learning Novelty Detection in HVAC Chiller Systems,”ScienceDrect：IFAC Proceedings Volumes,vol .47,pp.1953-1958, 2014. [Online]. Available: https://doi.org/10.3182/20140824-6-ZA-1003.02382
[9]S.P. Fisenko, A.A. Brin, A.I. Petruchik, “Evaporative Cooling of Water in a Mechanical Draft Cooling Tower,” ScienceDrect：International Journal of Heat and Mass Transfer,vol .47,Issue 1,pp.165-177, January 2004.
[10]Ashish Kumar, Monika Saini, Nivedita Gupta, Deepak Sinwar, Dilbag Singh, Manjit Kaur, “Efficient Stochastic Model for Operational Availability Optimization of Cooling Tower Using Metaheuristic Algorithms,” IEEE Access,vol .10,pp24659-24677, January 2022. [Online]. Available: https://doi.org/10.1109/ACCESS. 2022.3143541
[11]Dariush Fooladivanda, Joshua A. Taylor, “Energy-Optimal Pump Scheduling and Water Flow,” IEEE Transactions on Control of Network Systems,vol .5,pp.1016-1026, February 2017 . [Online]. Available: https://doi.org/10.1109/TCNS.2017. 2670501
[12]Manuel Martin Salvador, Marcin Budka, Bogdan Gabrys, “Energy-Optimal Pump Scheduling and Water Flow,” IEEE Transactions on Automation Science and Engineering, vol . 16 ,pp.946-959,Issue: 2, April 2019.[Online]. Available: https://doi.org/10.1109/TASE.2018.2876430
[13]Xiao Xiang Zhu, Devis Tuia, Lichao Mou, Gui-Song Xia, Liangpei Zhang, Feng Xu, “Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources,” IEEE Geoscience and Remote Sensing Magazine, vol . 5Issue: 4 pp.8-36, December 2017.[Online]. Available: https://doi.org/10.1109/MGRS.2017. 2762307
[14]Kostadin Mishev, Ana Gjorgjevikj, Irena Vodenska, Lubomir T. Chitkushev, Dimitar Trajanov, “Evaluation of Sentiment Analysis in Finance: From Lexicons to Transformers,” IEEE Access, vol .8,pp.131662-131682, July 2020.[Online]. Available: https://doi.org/10.1109/ACCESS.2020.3009626