一般在討論撲翼機拍翅性能時，通常會給定一個預設路徑以得到較好的效能；而本論文則採用人工智慧─基因演算法來搜尋不同風速下的最佳拍翅路徑。目前國內撲翼機相關研究幾乎都以撲翼機構和翅膀結構材料為主，在穩定控制方面極少有人深入探討，尤其是在智慧型最佳化拍翅軌跡方面。本研究率先引進人工智慧中的基因演算法概念於撲翼機穩定控制上，希望能有別於以往的給定固定拍翅路徑，模仿鳥類真實拍翅動作；取而代之的是藉由基因演算法做為基礎，自行開發出一套「自我學習程式」來搜尋最佳拍翅軌跡，並在不違背大自然演化的前提下，以消耗最小能源並獲得最大升力及推力為目標而努力，不斷地自我改良，直到演化出最佳的拍翅路徑，使撲翼機更具仿生能力，以適應在各種風速下產生之最大升力及推力。本論文採用此人工智慧程式以方便設計撲翼機；未來在設計撲翼機載具時，若參考本論文之研究經驗，相信能獲得更好的飛行效能、更大的酬載量及更高的機動性。

The usual manner of research into flight performances of an ornithopter is to offer a default flapping-wing path in prior. To achieve a better flapping efficiency and flight performance, we use an artificial intelligence-genetic algorithm in this thesis to find the optimal flapping-wing path under various wind speeds.
Recently, most researchers focus on materials, structures and mechanical platforms of flapping-wings. As to stability control, there is few study inspection of optimizing the flapping-wing path intelligently so far. In this thesis, the genetic algorithm will be adopted to search an optimal path for the flapping wing. As an artificial intelligence, the genetic algorithm is adequate to the evolutionary optimization path issue. It can record cyclic paths, and evolve them into an optimized path via the energy consumption minimization and thrust and lift maximization rather than manual adjustments on principle of the nature law. Moreover, the self-learning flapping wing makes ornithopter become a genuine biomimetic with the greatest robust flight ability in various wind conditions. These features make our ornithopter become a precursor in the field of the flapping-wind flight.
We take advantage of the artificial intelligence to facilitate the design of an ornithopter. Designing a flapping-wing aircraft with better flight performances, higher mobility and larger capacity can be acquired if one takes the experiences given by this thesis into account.

[1] http://www.ns.umich.edu/htdocs/releases/story.php University of Michigan,Website
[2] Mouret, J.-B., Doncieux, S., Muratet, L., Druot, T., and Meyer, J.-A., “Evolution of neuro-controllers for flapping-wing animats. ”,2004
[3] Ramji Kamakoti, Mats Berg, Daniel Ljungqvist, Wei Shyy.,“ A Computational Study for Biological Flapping Wing Flight.”,2000
[4] 路非遙,“振動翼微型飛行載具之空氣動力特性測試與分析”, 國立成功大學航空太空工程研究所碩士論文, 2001
[5] 林哲旭,“振翅翼飛行載具之探討”, 國立成功大學航空太空工程研究所碩士論文, 2005
[6] 賴志昇,“引擎動力遙控撲翼機之開發與研究”,大同大學機械工程研究所碩士論文, 2005
[7] 許書凱,“振翼機構之類型合成與運動分析”, 崑山科技大學機械工程系碩士論文, 2004
[8] 劉峰齊, 單自由度拍撲翼機構之創新設計”, 崑山科技大學機械工程系碩士論文, 2004
[9] http://qmems.pme.nthu.edu.tw/index.htm 清華大學微機電系統工程研究所葉哲良教授網站
[10] 楊龍杰,何仁揚,劉冠君,柯凱鐘,“微飛行器拍撲翼的現地升力量測研究”, 行政院國家科學委員會專題研究計畫,2005
[11] 賴旻琦,“六自由度電控撲翼機平台之研製:馬達控制命令產生器及機構模擬”,國立成功大學航空太空工程研究所碩士論文, 2007
[12] http://www.cybernet-ap.com.tw/zh.php CYBERNET思渤科技網站
[13] http://www.terasic.com.tw/tw/ TERASIC友晶科技網站
[14] http://www.abri.gov.tw/utcPageBox/CHIMAINHP.aspx 內政部建築研究所網站
[15] http://www.jr3.com/ JR3, Inc, Website
[16] Michael Negnevitsky原著,顧力栩等譯, “人工智慧 :智慧型系統導論”,全華發行,2007
[17] 楊龍杰,「拍出精彩、飛出丰采」-拍翼式微飛行器之研究, 國科會學門研究成果成功案例專欄報導,2008
[18] http://animatlab.lip6.fr/AccueilEn AnimatLab網站
[19] 陳繹亘,“六自由度電控撲翼機平台之研製:馬達控制器及與模擬”,國立成功大學航空太空工程研究所碩士論文, 2008
[20] 楊憲東,“六自由度電控撲翼機平台之研製”,行政院國家科學委員會專題研究計畫,2007
[21] Tobalske, B. W. and Dial, K.,“Flight kinematics of black-billed mag-pies and pigeons over a wide range of speeds”, J. exp.Biol., 199, 263-280, 1996
[22] J.D. DeLaurier.,“An Aerodynamic Model For Flapping-Wing Flight”, 1993
[23] Yuval Davidor., “Genetic algorithms and robotics :a heuristic strategy for optimization”, World Scientific,1991
[24] Zbigniew Michalewicz., “Genetic algorithms + data structures = evolution programs”, Springer-Verlag,1992
[25] Takashi Kenjo and Shigenobu Nagamori., “Brushless motors :advanced theory and modern applications”, Sogo Electronics Press,2003
[26] David B. Fogel., “Evolutionary computation :toward a new philosophy of machine intelligence”, Wiley-Interscience,2006
[27] Riccardo Poli., “Foundations of genetic programming”, Springer,2002
[28] 黃永安,馬路,劉慧敏編著,“MATLAB 7.0/Simulink 6.0建模仿真開發與高級工程應用”,清華大學出版社出版發行,2005
[29] 洪維恩編著, “MATLAB 7 程式設計”, 旗標出版發行,2007
[30] Lung-Wen Tsai., “Robot analysis :the mechanics of serial and parallel manipulators”, Wiley,1999
[31] 陳之藩,李白男著, “LISP 程式設計初階 :人工智慧常用語言”,遠東出版發行,1992
[32] 黃崇冀編著, “機器學習 :人工智慧.專家系統.資料檢索之理論與實驗”,儒林出版發行,1988
[33] Wolfgang Banzhaf ... [et al.]., “Genetic programming : an introduction on the automatic evolution of computer programs and its applications”, Morgan Kaufmann Publishers,1998
[34] Michael Affenzeller ... [et al.]., “Genetic algorithms and genetic programming :modern concepts and practical applications”,Chapman & Hall/CRC,2009
[35] James B. Dabney and Thomas L. Harman.,“ Mastering Simulink”, Pearson/Prentice Hall,2004
[36] David E. Goldberg.,“Genetic algorithms in search, optimization, and machine learning”, Addison-Wesley,1989
[37] Ashish Tewari.,“ Modern control design with MATLAB and SIMULINK”, John Wiley,2002
[38] 鮑爾( R. P. Paul)原著;許政行譯,機器人操縱器:數理.程式與控制, 科技出版發行,1984
[39]李顯宏編著, “MATLAB 7.X 程式設計延伸技巧”,文魁資訊出版,2006
[40] George Lindfield John Penny原著;黃俊銘編譯, “Numerical methods using MATLAB;數值方法-使用MATLAB 程式語言”,全華出版,2007