臺灣博碩士論文加值系統

由於類神經網路對於未模組化具有較佳的適應性及強健性，且易於製成硬體供實際的系統使用，近年來許多研究已把其應用於飛行控制上，以增加飛行控制器在不同環境下之適應性。一般對於飛機自動著陸系統（Automatic Landing System）的改進，多著重於利用不同的導引器，藉著這些儀器及一些計算的方法，提供更精確的飛行資料給自動著陸系統，使飛機著陸時能更平穩。這些研究計劃均未將天候因素列入考量。而在著陸控制的改進方面，利用智慧型控制方法的研究並不多。而一般標準的倒傳遞網路（Backpropagation Network）學習過程並非動態行為，只利用一個固定的類神經網路來學習一系統的動態行為，其結果可能不是很好，因此本論文主要提出以時序性倒傳遞演算法（Backpropagation Through Time）的類神經網路控制器，並結合所推導出的線性化反飛機模組（Linear Inverse Aircraft Model），應用於飛機自動著陸系統，以期設計一智慧型的自動著陸控制器，使其具有更優異之適應能力。此智慧型控制器為一多層前饋類神經網路，設計步驟先以離線（off-line）訓練類神經網路來學習飛機之控制能力，之後再採用時序性倒傳遞演算法。此學習模式有極佳的軌跡追蹤能力，經由線性化反飛機模組來獲得類神經網路每一個時序所須之矯正值，以此矯正值計算每一級網路內的鍵結修正值，再將所有鍵結修正值相加，並用以更新類神經網路內的鍵結值。電腦模擬結果顯示。此類神經網路控制器經訓練後能於特定的亂流（wind turbulence）與剪風（wind shear）中，導引飛機自動著陸，符合安全降落之定義範圍內，且其具備有良好之適應能力。

Because of its better adaptability and robustness for unmodeled systems and hardware implementation capability, neural networks have been applied to flight control to increase the flight controller’s adaptation to different environment. Currently, most of the improvements in the Automatic Landing System (ALS) have been on the guidance instruments. By using improvement calculation methods and high accuracy instruments, these systems provide more accurate flight data to the ALS to make the landing more smooth. However, these researches do not include weather factors such as wind shear. There also have not been many researches on the problem of intelligent landing control. The purpose of this thesis is to apply neural network controller to aircraft automatic landing system. Backpropagation Through Time（BTT）algorithm is implemented into the network learning process. The learning scheme uses a three-layer feedforward neural network combined with a linearized inverse aircraft model (LIAM). A complete landing phase is divided into several stages (intervals). Each stage uses same neural network controller. Wind disturbances are added to each stage in the simulation. The LIAM calculates the error signals, which will be used to back propagation through the controller to obtain weight change in each stage. The error continues to be back propagated through all the stages and weight changes for the controller are computed for each stage. The weight changes from all the stages obtained from delta learning rule are added together for the overall updating. Simulation results show that the trained controller can guide the aircraft landing safely through wind disturbances and successfully expand the controllable environment in severe wind disturbances.

摘要 (中文) i
摘要 (英文) ii
誌謝 iii
目錄 iv
圖目錄 vii
表目錄 xii
第一章導論 1
1.1研究動機 1
1.2文獻回顧 3
1.3論文貢獻 5
1.4論文大綱 6
第二章時序性倒傳遞演算法 7
2.1 類神經網路簡介 7
2.1.1 類神經網路模型 7
2.1.2 類神經網路的基本架構 9
2.1.3 類神經網路的運作過程及分類 10
2.2 倒傳遞神經網路 10
2.2.1 倒傳遞演算法則 11
2.3 時序性倒傳遞演算法 13
2.3.1 時序性倒傳遞演算法介紹 14
2.3.2 規則網路與其梯度之計算 14
2.3.3 循環式網路之時序擴展 16
2.3.4 時序性倒傳遞演算法 17
第三章飛行降落分析 20
3.1飛機著陸分析 20
3.2飛機線性動態方程式 22
3.3安全降落的定義 26
3.4風擾的數學模式 27
3.4.1 亂流 27
3.4.2 剪風 29
第四章使用線性化反飛機模組之飛行控制 32
4.1控制方式 32
4.1.1 類神經網路控制器 34
4.2線性化反飛機模組 37
4.3模擬結果 41
4.3.1 傳統控制器 41
4.3.2預訓練結果 43
4.3.3類神經網路控制器模擬結果 45
4.3.4 時序性倒傳遞演算法模擬結果 47
4.4 結果討論 49
第五章亂流中著陸控制 50
5.1著陸訓練分析 50
5.2傳統控制器於亂流中之著陸控制模擬 51
5.3類神經網路控制器於亂流中之著陸控制模擬57
5.3.1 傳統式倒傳遞演算法於亂流下的訓練結果 57
5.3.2 時序性倒傳遞演算法於亂流下之訓練 59
第六章剪風中著陸控制 66
6.1 傳統控制器於剪風中之著陸控制模擬 66
6.2 類神經網路控制器於剪風中之著陸控制模擬 73
6.2.1 傳統式倒傳遞演算法於剪風下的訓練結果 73
6.2.2 時序性倒傳遞演算法於剪風下之訓練 74
第七章結論與建議 81
參考文獻 83

1. Federal Aviation Administration, “Automatic Landing Systems,” AC 20-57A, Jan. 1971.
2. B. Etkin, “Effect of Wind Gradient on Glide and Climb,” Journal of the Aeronautical Sciences, Vol. 14, No. 6, 1947.
3. T. T. Fujita, “DFW Microburst”, Satellite and Mesometeorology Research Project, 1986.
4. Boeing Publication, “Statistical Summary of commercial Jet Airplane Accidents”, （Worldwide Operations 1959-1999）.
5. H. Buschek and A.J. Calise, “Uncertainty Modeling and Fixed-Order Controller Design for a Hypersonic Vehicle Model,” Journal of Guidance, Control, and Dynamics, vol. 20, no. 1, pp. 42-48, 1997.
6. A.J. Calise and R.T. Rysdyk, “Nonlinear Adaptive Flight Control Using Neural Networks,” IEEE Control Systems Magazine, vol. 18, no. 6, pp. 14-25, 1998.
7. P.J. Werbos, “Neural Networks and Flight Control: Overview of Capabilities and Emerging Applications,” Proc. Of the AIAA Guidance, Navigation, and Control Conf., pp. 912-919, 1995.
8. M.R. Napolitano and M. Kincheloe, “On-Line Learning Neural-Network Controller for Autopilot Systems,” Journal of Guidance, Control, and Dynamics, vol. 18, no. 5, pp. 1008-1015, 1995.
9. 陳柏熹, “The Application of Neural Network on Longitudinal Flight Control System Design,” M.S. thesis, 中興大學, 1994.
10. 謝成德, “Gain Scheduling of Flight Control System with Fuzzy Logic Model,” M.S. thesis, 交通大學, 1996.
11. 譚俊豪, “模糊飛行控制系統的發展及應用於無人飛機之研究,” 國科會研究報告, NSC82-042-E006-148, 1993.
12. M.B. McFarland and A.J. Calise, “Robust Adaptive Control of Uncertain Nonlinear Systems Using Neural Networks,” Proc. American Control Conf., pp. 1996-2000, 1997.
13. Special Issue on Neural Network Hardware, IEEE Trans. Neural Networks, vol. 3, no. 3, 1992.
14. C.E. Cohen, et al., “Automatic Landing of a 737 Using GNSS Integrity Beacons,” Proc. ISPA, 1995.
15. DDC-I, “Advanced Auto Landing System from Swiss Federal Aircraft Factory,” Real-Time Journal, Sprint, 1995.
16. S. Asai, et al., “Development of Flight Control System for Automatic Landing Flight Experiment,” Mitsubishi Heavy Industries Technical Review, vol. 34, no. 3, 1997.
17. D.N. Kaufmann and B.D. McNally, “Flight Test Evaluation of the Stanford University and United Airlines Differential GPS Category III Automatic Landing System,” NASA Technical Memorandum 110354, June 1995.
18. M.G. Cooper, “Genetic Design of Rule-Based Fuzzy Controllers,” Ph.D. dissertation, University of California, Los Angeles, 1995.
19. C.C. Jorgensen and C. Schley, “A Neural Network Baseline Problem for Control of Aircraft Flare and Touchdown,” Neural Networks for Control, pp. 403-425, 1991.
20. Y. Iiguni, H. Akiyoshi, and N. Adachi, “An Intelligent Landing System Based on Human Skill Model,” IEEE Transactions on Aerospace and Electronic System, vol. 34, no. 3, pp. 877-882, 1998
21. K. Hornik, M. Stinchombe and H. White, “Multilayer Feedforward Networks are Universal Approximators,” Neural Networks, vol. 2, no. 5, pp.359-366, 1989.
22. R.M. Sanner and J.E. Slotine, “Gaussian Networks for Direct Adaptive Control,” IEEE Trans. Neural Networks, vol. 3, no. 6, pp. 837-863, 1992.
23. M.S. Lan, “Adaptive Control of Unknown Dynamical System via Neural Network Approach,” Proc. American Control Conf., pp. 910-915, 1991.
24. 葉宜成, 類神經網路模式應用與實作, 儒林圖書有限公司, 2000年4月七版.
25. R. P. Lippmann, “An Introduction to Computing with Neural Nets”,
IEEE ASSP Magazine, pp. 4-17, April 1987.
26. 陳燕慶, 鹿浩, 神經網路理論及其在控制工程中的應用, 儒林圖書有限公司, 1992年6月初版.
27. S. Haykin, Neural Networks: A Comprehensive Foundation, Printice-Hall, Inc., 1999.
28. J.G. Kuschewski and S.H. Zak “Application of Feedforward Neural Network to Dynamical System Identification and Control” IEEE Transactions on Control System Technology, vol. 1. no 1, pp. 37-49, March 1993.
29. W.T. Miller, R.S. Sutton, and P.J. Werbos, Neural Networks for Control, the MIT Press, 1991.
30. 蘇木春, 張孝德, 機械學習：類神經網路、模糊系統以及基因演算法, 全華科技圖書股份有限公司, 1999.
31. W. S.McCulloch and W. Pitts, “A logic calculus of the ideas immanemt in nervous activity,” Bulletin of Mathematical Biophysics, vol. 5, pp. 115-133,1943.
32. F. Rosenblatt, “The perceptron： A probabilistic model for information storage organization in the brain,” Psychological Review, vol. 65, pp. 386-408, 1958.
33. D.E. Rumelhart, G.E. Hinton, and R.J. Williams, “Learning representations by back-propagating errors,” Nature, 323, pp. 533-536, 1986
34. P.J. Werbos, “Backpropagation Through Time: What It Does and How to Do It,” Proceedings of the IEEE, vol. 78, no. 10, pp. 886-901, September 1990.
35. D.H. Nguyen and b. Widrow, “Neural Networks for Self-Learning Control Systems Magazine, pp. 18-23, April 1990.
36. J.G. Juang and C.S. Lin, “Giat synthesis of a biped robot using backpropagation through time algorithm,” Proc. IEEE Int. Conf. On Neural Network, vol. 3, pp. 1710-1715, 1996.
37. 張務本, “A Study of Neural Network Applications to Automatic Landing System,” M.S. thesis, 海洋大學, 2000.
38. W.C. Hsueh, “Stability and Control of Aircraft in Gust and Windshear Flows,” M.S. thesis, 成功大學, 1992.
39. R.C. Nelson, Flight Stability and Automatic Control, 4th edition, pp.314-315, Mcgraw-Hill International Editions, 1998.
40. Y.H. Chen and S. Pandey, “Robust Control Strategy for Take-Off Performance in a Windshear,” Optimal Control Applications and Method, vol. 10, no. 1, pp. 65-79, 1989.
41. D. Mc Ruer, I. Ashkenas, and D. Graham, Aircraft dynamics and automatic control, Princeton University Press, Princeton, NJ, 1973.
42. R. Bulirsch, F. Montrone, and H. Pesch, “Abort Landing in the Presence of Windshear as a Minimax Optimal Control Problem,” Journal of Optimization Theory and Applications, vol. 70, no. 1, pp.1-23, 1991.
43. M.B. Ghalia, A.T Alouani, “Robust control design of an autolanding system,”, Proceedings Twenty-Fifth Southeastern Symposium on System Theory, pp. 248-252. March 1993.
44. A. Dogan, P.T Kabamba, “Escaping a microburst with turbulance,” Proceedings of the 2000, American Control Conference, vol. 2, pp. 1349-1535, 2000.
45. J. Imae, S. Nakatani, J. Takahashi, “GP based flight control in the windshear,” IEEE SMC''99 Conference Proceedings. vol. 2, pp. 650-653, 1999.
46. Zhao, Y.; Bryson, A.E. “Aircraft control in a downburst on takeoff and landing,” Proceedings of the 29th IEEE Conference on Decision and Control, vol. 2, pp. 753—757, 1990.