臺灣博碩士論文加值系統

近年來隨著全球暖化問題與環保意識的高漲，節能減碳已成為各國重視的議題，如何就有限的能源做最有效率的規劃與運用。對於以製造為主的台灣企業也面臨著要如何考慮環境永續性以及能源效率性來進行各種重要決策以達到節能的目標。
本研究的目的是要探討金屬零件加工廠機台的電力消耗，建立電力負載曲線(Load profiling)的資料倉儲以及使用資料探勘技術來分析生產製程的電力消耗樣式或行為。透過資料倉儲來觀察屬性不同維度間的關係，並特徵擷取不同的時間維度來比較預測機台的狀態以及正異常狀態效益。最後，並將彙整的預測分析結果，希望可以提供給其他工業機台的模型建立參考。同時也透過電力消耗樣式來找出關鍵影響指標，並轉化成可供使用者更直覺式瞭解資料內容的視覺化圖樣。
本研究完成後，期望可以提供相關企業用電系統之決策參考，其結果亦可作為對工業電力節能的研究之基礎，並將有助於建立工業電力消耗資料倉儲架構並結合多維度情境分析模型與資料探勘技術建立電力節能決策架構。

Owing to the problems of gradual oil depletion and global warming, energy consumption is a critical issue for energy-intensive industries. Accordingly, manufacturers in Taiwan are keen to find solutions for maintaining sustainable development of the environment and increasing energy efficiency to achieve the ultimate goal of energy savings.
The purpose of this study was to explore the power consumption of the metal parts factory machines, establishing electrical load curve (load profiling) of data warehouse and data mining techniques to analyze the use of the production process of the power consumption pattern or behavior. Through data warehouse to observe the relationship between the properties of different dimensions and characteristics capture different time dimensions to compare state machine and the positive predictive abnormal state benefits. Finally, we proposed a preliminary visualization concept to visualized the normal and abnormal load profiling of machines for real-time decision making in the future.
In this study, we proposed a context-aware, domain-driven energy consumption and green production consumption scheduling model and system for decision support. We preliminary deployed the data warehouse framework and incorporate the multidimensional, context-aware energy consumption model with the data mining technique to build prediction models. That is, we aim to detect abnormal energy patterns and machine operational states via energy load profiles to make further energy optimization decisions in real time. The optimal goal is to deploy the framework and then propose actionable energy-saving strategies for the cooperating iron and steel plan to solve real-world problems.

表　　次 vi
圖　　次 viii
第壹章 緒 論 1
第一節 研究背景 1
第二節 研究動機 3
第三節 研究目的 4
第貳章 文獻探討 5
第一節 資料探勘 5
第二節 資料探勘的技術 8
第三節 人工智慧方法電力分析上的應用 13
第四節 能源的管理 16
第參章 研究方法 21
第一節 問題定義與研究架構 21
第二節 資料倉儲 25
第三節 資料的前置處理 28
第四節 特徵擷取 32
第五節 預測的狀態定義 35
第六節 實驗設計 40
第肆章 電力分析模型基於資料探勘建構方法 47
第一節 實驗資料說明 47
第二節 模型的建立 48
第三節 模型實驗設計與分析 49
第四節 關鍵影響因素指標 68
第五節 狀態結構序列與視覺化 69
第伍章 結論 73
第一節 結論 73
第二節 未來研究方向及貢獻 75
參考文獻 77

參考文獻
1.蔡宛妮，應用自我組織網路於直接負載控制績效評估之研究，中原大學電機工程研究所碩士論文，2001。
2.Beccali, M., Cellura, M., Brano, V. L., & Marvuglia, A., Forecasting daily urban electric load profiles using artificial neural networks. Energy Conversion and Management, 2004, pp. 2879-2900.
3.Cannata, A., Gerosa, M., & Taisch, M., SOCRADES: A framework for developing intelligent systems in manufacturing. IEEE International Conference, 2008, pp.1904-1908.
4.Chang, F.-J., Chen, Y.-C., Estuary water-stage forecasting by using radial basis function neural network. Journal of Hydrology, 2003, pp.158-166.
5.Cortes, C., & Vapnik, V., Support-vector networks, Machine learning,20(3), 1995,pp.273-297.
6.Di Orio, G., Cândido, G., & Barata, J., The Adapter module: A building block for Self-Learning Production Systems, Robotics and Computer-Integrated Manufacturing, 2015.
7.De Silva, D., Yu, X., Alahakoon, D., & Holmes, G., A data mining framework for electricity consumption analysis from meter data. Industrial Informatics, IEEE Transactions on, 2011, pp. 399-407.
8.Domınguez, M., Fuertes, J. J., Dıaz, I., Cuadrado, A. A., Alonso, S., & Morán, A. Analysis of electric power consumption using self-organizing maps, World Congress, 2011, pp. 12213-12218.
9.Figueiredo, V., Rodrigues, F., Vale, Z., & Gouveia, J. B., An electric energy consumer characterization framework based on data mining techniques, Power Systems, IEEE Transactions on, 2005, pp.596-602.
10.Götze, U., Koriath, H. J., Kolesnikov, A., Lindner, R., & Paetzold, J., Integrated methodology for the evaluation of the energy-and cost-effectiveness of machine tools, CIRP Journal of Manufacturing Science and Technology, 2012, pp.151-163.
11.Hecht-Nielsen, R., Counterpropagation networks, Applied optics, 1987, pp.4979-4984.
12.Hopfield, J. J., & Tank, D. W., Computing with neural circuits- A model, Science, 1986, pp.625-633.
13.Keim, D., Information visualization and visual data mining, Visualization and Computer Graphics, IEEE Transactions on, 2002, pp.1-8.
14.Le, C. V., & Pang, C. K., An energy data-driven decision support system for high-performance manufacturing industries, International Journal of Automation and Logistics, 2013, pp.61-79.
15.Laughman, C., Lee, K., Cox, R., Shaw, S., Leeb, S., Norford, L., & Armstrong, P., Power signature analysis, Power and Energy Magazine, IEEE, 2003, pp.56-63.
16.Le, C. V., Pang, C. K., Gan, O. P., Chee, X. M., Zhang, D. H., Luo, M., ... & Lewis, F. L., Classification of energy consumption patterns for energy audit and machine scheduling in industrial manufacturing systems, Transactions of the Institute of Measurement and Control, 2013, pp.583-592.
17.McCulloch, W. S., & Pitts, W., A logical calculus of the ideas immanent in nervous activity, The bulletin of mathematical biophysics, 5(4),1943, pp.115-133.
18.Monedero, I., Biscarri, F., León, C., Guerrero, J. I., González, R., & Pérez-Lombard, L., Decision system based on neural networks to optimize the energy efficiency of a petrochemical plant, Expert Systems with Applications, 2012, pp.9860-9867.
19.Nagi, J., Yap, K. S., Tiong, S. K., Ahmed, S. K., & Mohamad, M. Nontechnical loss detection for metered customers in power utility using support vector machines. Power Delivery, IEEE Transactions on, 2010, pp.1162-1171.
20.Nizar, A. H., & Dong, Z. Y., Identification and detection of electricity customer behaviour irregularities, Power Systems Conference and Exposition,2009, pp.1-10.
21.Nizar, A. H., Zhao, J. H., & Dong, Z. Y., Customer information system data pre-processing with feature selection techniques for non-technical losses prediction in an electricity market, International Conference on. IEEE, 2006, pp. 1-7.
22.O'Driscoll, E., Kelly, K., & O'Donnell, G. E., Intelligent energy based status identification as a platform for improvement of machine tool efficiency and effectiveness, Journal of Cleaner Production, 2015.
23.Powell, K. E., Thompson, P. D., Caspersen, C. J., & Kendrick, J. S., Physical activity and the incidence of coronary heart disease, Annual review of public health, 8(1),1987, 253-287.
24.Räsänen, T., Ruuskanen, J., & Kolehmainen, M., Reducing energy consumption by using self-organizing maps to create more personalized electricity use information, Applied Energy, 2008, pp.830-840.
25.Sequeira, H., Carreira, P., Goldschmidt, T., & Vorst, P., Energy Cloud: real-time cloud-native Energy Management System to monitor and analyze energy consumption in multiple industrial sites, Proceedings of the 2014 IEEE/ACM 7th International Conference on Utility and Cloud Computing, 2014, pp. 529-534.
26.Schmitt, R., Bittencourt, J. L., & Bonefeld, R., Modelling machine tools for self-optimisation of energy consumption, Glocalized Solutions for Sustainability in Manufacturing, 2011, pp.253-257.
27.Velázquez, D., González-Falcón, R., Pérez-Lombard, L., Gallego, L. M., Monedero, I., & Biscarri, F., Development of an energy management system for a naphtha reforming plant: A data mining approach, Energy Conversion and Management, 2013, pp.217-225.
28.Vikhorev, K., Greenough, R., & Brown, N., An advanced energy management framework to promote energy awareness, Journal of Cleaner Production, 2013, pp.103-112.
29.Weinert, N., Chiotellis, S., & Seliger, G., Methodology for planning and operating energy-efficient production systems, CIRP Annals-Manufacturing Technology, 2011, pp.41-44.