臺灣博碩士論文加值系統

此篇論文以2MW之大型風力發電機為研究載具，發展提升其發電效率之控制法則，提出以前饋倒傳遞類神經網路 (Neural Network)預測短期風向、風速，計算風能變化，整合風機迎風轉向系統的響應時間及推導風機轉向耗能與風能擷取分析，使迎風轉向反應時間較慢的大型風力發電機可依據短期風力風向預測資料，做適當的風機迎風轉向控制，進而達到在降低風機轉向耗能之下擷取最大風能之目的，以節省不必要的偏向運轉。本論文研究方法由長期的風力觀測資料庫，以前饋倒傳遞類神經網路進行短期風速與風向預測，並與歷史資料比較其準確性。由風速與風向預測結果推導在風能擷取與風機轉向耗能正負相抵間之最高電能擷取功率的轉向機制。研究結果顯示，本論文提出之迎風轉向控制法則在平均風速約為5.924m/s的風場下，可比隨風向迎風轉向之風機多出約1.1kWh的淨獲能。

Based on 2MW large-scale wind turbine platform, this research proposed feed-forward back-propagation neural network (NN) algorithm to predict short-term wind direction and wind speed for calculating the wind energy's variation. The estimation results of maximum power capture as well as the analysis of nacelle veering energy consumption are integrated with the response time of wind turbine yaw operation to derive wind energy gains and losses in order to make the appropriate wind turbine yaw control by predicting short-term wind data and finding out the best yaw angle to capture maximum wind energy which included the loss of consumption for turning orientation. This yaw control algorithm is expected to reduce unnecessary turning of large wind turbines which need longer time to change orientation. In additions, the prediction methods based on various structures of the feed-forward neural network from the values of meteorological variables are also described in this work. The result show that the proposed algorithm could have a surplus of about 1.1kWh net energy per five minute compare to the same type specification wind turbine that yaw directly follow with wind direction under the condition of 5.924m/s wind velocity. Finally, there is a simulated human machine interface for showing the conditions of controlled turbine facing and the real wind direction and velocity.

中文摘要 i
Abstract ii
致謝 iii
目錄 iv
圖目錄 vi
表目錄 viii
第一章 緒論 1
1-1引言 1
1-2研究動機 2
1-3文獻回顧 3
1-4論文大綱 6
第二章 風力發電系統架構 7
2-1 風力發電機原理與架構 7
2-2 風力發電機迎風轉向系統結構 10
第三章 風能預測研究方法 14
3-1支持向量機(Support Vector Machine regression algorithm) 14
3-2 決策樹(Decision Tree) 16
3-3類神經網路(Artificial Neural Network) 16
3-3-1 多層感知器類神經網路(Multilayer Perceptrons Network) 18
3-3-2 倒傳遞類神經網路(Back Propagation Network) 20
3-3-3 徑向基類神經網路(Radial Basis Function Network) 21
第四章 前饋倒傳遞類神經網路原理與架構 23
4-1 批次梯度下降倒傳遞演算法(Steepest Decent back propagation) 25
4-2具動量的批次梯度下降演算法(Momentum back propagation) 25
4-3可變學習速率倒傳遞演算法(Variable Learning Rate back propagation) 26
4-4 有彈性的倒傳遞演算法(Resilient back propagation) 26
4-5共軛梯度演算法(Conjugate Gradient back propagation) 27
4-6牛頓法(Newton’s method) 28
4-7擬牛頓法BFGS(Quasi-Newton algorithms , BFGS) 29
4-8一步階正割演算法(One Step Secant) 30
4-9 Levengerg-Marquardt演算法 30
4-10 前饋倒傳遞類神經網路收斂情形比較 31
第五章 類神經模擬 35
5-1類神經研究方法與步驟 35
5-2 類神經網路短期風能預測 36
第六章 風機迎風轉向控制 44
6-1 風力發電機組技術參數 44
6-2 迎風轉向系統轉移函數 45
6-3 風機面向角度控制方式 47
6-4 風機實際反應之模擬 51
第七章 結論與未來展望 57
7-1結論 57
7-2未來展望 58
第八章　參考文獻 59

 

1. 朱翊誌，「含風力發電為電網之孤島運轉策略」，國立中山大學電機工程學系，碩士論文，中華民國98年6月。
2. Andrew Kusiak, Zijun Zhang, “Short-Horizon Prediction of Wind Power_ A Data-Driven Approach” IEEE TRANSACTIONS ON ENERGY CONVERSION, VOL. 25, NO. 4, December 2010
3. C. Pérez-Llera, M.C. Fernández-Baizán, J.L. Feito , V. González del Valle, “Local Short-Term Prediction of Wind Speed A Neural Network Analysis” TECHNIQUES AND METHODOLOGIES, iEMSs 2002 sessions (part two)
4. S. Salcedo Sanz, A’. Pe’rez-Bellido, E. Ortiz-Garc, A. Portilla-Figueras, L. Prieto, D. Paredes, F. Correoso “Short-term Wind Speed Prediction by Hybridizing Global and Mesoscale Forecasting Models with Artificial Neural Networks” Hybrid Intelligent Systems, Eighth International Conference on 2008. HIS '08.
5. Felix A.Farret, Luciano L.Pfitscher, Daniel P.Bernardon ,
“Sensorless active yaw control for wind turbines” , Industrial Electronics Society, The 27th Annual Conference of the IEEE 2001. IECON '01.
6. Feifei Bu, Wenxin Huang, Yuwen Hu, Yunqing Xu, Kai Shi, Qianshuang Wang , “Study and Implementation of A Control Algorithm for Wind Turbine Yaw Control System”, World Non-Grid-Connected Wind Power and Energy Conference, WNWEC 2009
7. Andrew Kusiak, Haiyang Zheng, Zhe Song ,“Power optimization of wind turbines with data mining and evolutionary computation”, Renewable Energy, 2010
8. Andrew Kusiak, Haiyang Zheng, Zhe Song, “ Short-Term Prediction of Wind Farm Power: A Data Mining Approach” IEEE TRANSACTIONS ON ENERGY CONVERSION, VOL. 24, NO. 1, MARCH 2009.
9. Mrs. Patil SangitaB&; Technology Prof. Mrs. Surekha. R. Deshmukh. “Use of Support Vector Machine for Wind Speed Prediction”, Power and Energy Systems (ICPS), International Conference on 2011.
10. 羅華強， 類神經網路-MATLAB的應用，三版，高立圖書有限公司，中華民國一百年十二月。
11. 台北市校園數位氣象網，http://weather.tp.edu.tw/Scripts/active.php?TitleImg=title01。
12. 湘電風能(福建)有限公司，http://www.xemc-windfj.com/product/product.php?lang=cn&;itemid=108
13. 韓兵，「直驅永磁風力發電機組偏航系統的設計」，中國湖南大學，碩士學位論文，中華民國一百年五月十一日。
14. 廖明夫，黃巍，董禮，「風力機偏航引起的失穩振動」， 西北工業大學旋轉機械與風能裝置測控研究所太陽能學報，第04期，2009年。
15. Kung Chris Wu, Rony K. Joseph, Nagendra K. Thupili , “Evaluation of Classical and Fuzzy Logic Controllers for Wind Turbine Yaw Control”, Aerospace Control Systems, the First IEEE Regional Conference on 1993.
16. 義大利迎風轉向電機廠商Bonfiglioli , http://www.bonfiglioli.com/en/corporate
17. T. Harris ,J.H. Rumbarger ,C.P. Butterfield , “Wind Turbine Design Guideline DG03: Yaw and Pitch Rolling Bearing Life”, Technical Report NREL/TP-500-42362 ,December 2009
18. 吳繼平，「應用類神經網路及基因演算法預測風速與風力發電量」，中原大學電機工程學系，碩士學位論文，中華民國九十六年七月。
19. 張家豪，「風力發電機動態行為之研究」，國立台灣科技大學電機工程系，碩士學位論文，中華民國九十四年七月七日。
20. 陳清嚴，「風力發電機功率輸出模式之建立與應用」，國立台灣科技大學電機工程系，碩士學位論文。中華民國九十七年一月十七日。
21. 周家得，「以支向機為基礎並結合特徵擷取之語音辨識系統」，國立台灣科技大學資訊工程系，碩士學位論文，中華民國九十五年一月十一日。
22. George Sideratos , Nikos D. Hatziargyriou, “An Advanced Statistical Method for Wind Power Forecasting”, IEEE TRANSACTIONS ON POWER SYSTEMS, VOL. 22, NO. 1, February 2007
23. Colin Marson, Lisergy Consulting, “Wind Turbine Pitch and Yaw Drive Manufacturers” , http://www.geartechnology.com, January/February 2010
24. 永傳能源股份有限公司，福海離岸風力發電計畫http://www.taiwangenerations.com/project.php
25. Wind Power Weather Center，http://www.windpowerweather.com/
26. L.M. Saini , M.K. Soni, “Artificial neural network based peak load forecasting using Levenberg-Marquardt and quasi-Newton Method”, Generation, Transmission and Distribution, IEE Proceedings- (Volume:149 , Issue: 5 )
27. Martin T. Hagan , Mohammad B. Menhaj ,“Training Feedforward Networks with the Marquardt Algorithm”,IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 5, NO. 6, November 1994.
28. J. P. S. Catalão, H. M. I. Pousinho, V. M. F. Mendes , “An Artificial Neural Network Approach for Short-Term Wind Power Forecasting in Portugal” Intelligent System Applications to Power Systems, ISAP '09. 15th International Conference on 2009.
29. WU Xin, LIU Yanping, TENG Wei, “Modified Hill Climbing Method for Active Yaw Control In Wind turbine” Control Conference (CCC), Chinese , March 2012.
30. 「呼呼海風賺綠金」，台灣光華雜誌，http://www.sinorama.com.tw/show_issue.php?id=201160006022c.txt&;cur_page=2&;table=1&;distype=&;h1=&;h2=&;search=&;height=&;type=&;scope=&;order=&;keyword=&;lstPage=&;num=&;year=2011&;month=06。
31. Pérez-Llera, C., Fernández-Baizan, M. C., Feito, J. L., &; Gonzalez, V. “Local short-term prediction of wind speed: a neural network analysis.” In Proceedings of the iEMSs Vol. 2, pp. 124-129 ,June 2002.
32. Han-Soon Choi, Jeong-Gi Kim, Jang-Hwan Cho,Yoon-su Nam,“Active Yaw Control of MW class Wind Turbine”, Control Automation and Systems (ICCAS), International Conference on 2010.
33. 中華太陽能聯誼會 ，http://www.solar-i.com/wi.htm。
34. 張德豐，MATLAB神經網路應用設計，二版，機械工程出版社，北京，2011年12月。
35. 黃靖哲，「全橋半控型整流器及阻抗源變流器整合之風力發電系統」國立交通大學機械系，碩士學位論文，中華民國一百零一年三月。
36. 曾炫錡，「順滑模態觀測速度控制應用於無轉速感測之直驅式可變速風力發電機」，國立交通大學機械系，碩士學位論文，中華民國一百零一年六月。
37. 江國維，「基於倒階法則之積分型順滑模態控制應用於可變速風力發電機」，國立交通大學機械系，碩士學位論文，中華民國一百零