本篇論文提出具有強健控制器之自我調變小腦模型控制器的差分-積分-微分控制器來控制自主垂直自轉的無人直升機以保證地面人員的安全。所提出的控制器透過改變主轉子來完成控制無人直升機的下降速度。由於差分-積分-微分控制器的參數很難去定義，因此加入小腦模型控制器來解決。然而，不同狀態下的動態會對應到不同差分-積分-微分控制器的參數。基於小腦模型控制器的差分-積分-微分控制器應用在調整差分-積分-微分參數以處裡不同情況下的動態。 此方法將使小腦模型的差分-積分-微分控制器擁有自我調整的能力。而所提出的方法將使任何直升機狀態下花上少許的時間來到所設定的目標速度。三個一維的小腦模型控制器以及強健控制器將運用在此研究上。此控制器的穩定度藉由李亞普諾夫方法來證明。模擬結果可證明所提出的控制器是有效的。

This thesis propose a self-tuning cerebellar model articulation controller based proportional-integral-derivative (CMAC-PID) controller with a robust controller to realize the autonomous vertical autorotation control for a unmanned helicopter to guarantee the security of ground staff. The proposed controller can control the sink rate of the unmanned helicopter by adjusting the main rotor’s pitch. However, the parameters of the PID controllers are difficult to be determined and the fixed parameters of the PID controller are not suitable for all conditions of the system’s dynamic. The PID controller based on the CMAC estimator is applied to solve the problem. This arrangement would lead the CMAC-PID controller has the ability of self-tuning. The present control technique can use less time for reaching the target speed in any helicopter states. Three one-dimension CMAC estimators and a robust controller are adopted in the thesis. By utilizing the Lyapunov theory, the stability of the proposed controller can be guaranteed. The simulation result is implemented to demonstrate the effectiveness of the proposed controller.

ACKNOWLEDGEMENTS i
ABSTRACT (IN ENGLISH) ii
ABSTRACT (IN CHINESE) iii
CONTENTS iv
LIST OF TABLES vi
LIST OF FIGURES vii
LIST OF SYMBOLS ix
CHAPTER
1 Introduction 1
2 Hardware 5
2.1 Unmanned Aerial Helicopter 6
2.2 ArduPilot-Mega 2.5 8
2.3 3DR radio 9
2.4 others 10
2.5 Mission Planner 11
3 PID and CMAC Neural Network 12
3.1 PID Controller 12
3.2 basic CMAC 13
3.3 One-Dimensional CMAC 14
4 Controller Design 19
4.1 Controller design 20
4.2 Stability Theorem 22
5 Simulation Result 26
5.1 Vertical Autorotation Model 26
5.2 Simulation result 30
6 Experiment 49
7 Conclusions 55
REFERENCES 56

[1] V.J. Gawron, Human factors issues in the development, evaluation, and operation of uninhabited aerial vehicles. AUVSI 98, Alabama, 1998, pp. 431-438.
[2] D.A. Wiegmann and S.A. Shappell, A human error approach to aviation accident analysis: the human factors analysis and classification system, England, Ashgate publishing company, 2003.
[3] S. A. Shappell and D. A. Wiegmann, “Human factors analysis and classification system - HFACS.” Department of Transportation, Federal Administration: Washington, DC. DOT/FAA/AM-00/7, Feb. 2000, pp 1-15.
[4] Department of Defense, “Unmanned aerial vehicles roadmap,” 2000-2025, Office of the Secretary of Defense, Department of Defense, Washington, DC, April 2001, pp 3-12.
[5] Department of Defense, “Unmanned aerial vehicle reliability study,” Office of the Secretary of Defense, Washington, DC, Feb. 2003, pp 1-21.
[6] A. P. Tvaryanas, “USAF UAV mishap epidemiology”, 1997-2003, Human Factors of Uninhabited Aerial Vehicles First Annual Workshop, Phoenix, Arizona, May 2004
[7] J. G. Leishman, Principles of helicopter aerodynamics, The press syndicate of the university of Cambridge, England, 2000.
[8] K. Dalamagkidis, K. P. Valavanis, and L. A. Piegl, “Nonlinear model predictive control with neural network optimization for autonomous autorotation of small unmanned helicopters,” IEEE Trans. Control Syst. Techn., vol. 19, no. 4, pp 818-831, JULY 2011.
[9] F. C. Chen and C. H. Chang, “Practical stability issues in CMAC neural network control system,” IEEE Trans. Control Syst. Techn., vol. 4, no. 1, pp. 86-91, Sep. 1996.
[10] J. S. Albus, “Data storage in the cerebellar model articulation controller (CMAC),” J. Dyn. Syst. Meas. Control, Trans. ASME vol. 97, no. 3,pp. 228-233, June 1975.
[11] J. S. Albus, “A new approach to manipulator control: The cerebellar model articulation controller (CMAC),” J. Dyn. Syst. Meas. Control, Trans. ASME, vol. 97, pp. 220-227, 1975.
[12] H. C. Lu, J. C. Chang, and M. F. Yeh, “Design and analysis of direct-action CMAC PID controller,” Neurocomputing, vol. 70, no 16-18, pp. 2615-2625, Oct. 2007.
[13] R. J. Wai, C.M. Lin, and Y. F. Peng, “ Robust CMAC neural network control for LLCC resonant driving linear piezoelectric ceramic motor,” IEE Proc. Control Theory Appl., vol. 150, no. 3, pp. 221-232, May 2003.
[14] Y. F. Peng, R. J. Wai, and C.M. Lin, “Implementation of LLCC-resonant driving circuit and adaptive CMAC neural network control for linear piezoelectric ceramic motor,” IEE Trans. Ind. Electron., vol. 50, no. 1, pp. 35-48, Feb. 2004.
[15] S. H. Lane, D. A. Handelman, and J. J. Gelfand, “Theory and development of higher-order CMAC neural networks,” IEE Control Syst. Mag., vol. 12, no. 2, pp. 23-30, Apr. 1992.
[16] T. F. Wu, P. S. Tsai, F. R. Chang, and L.S. Wang, ”Adaptive fuzzy CMAC control for a class of nonlinear systems with smooth compensation,” IEE Proc. Control Theory Appl., vol. 153, no. 6, pp. 647-657, Nov 2006.
[17] H. C. Lu, J. C. Chang, and M. F. Yeh, “Design of a hybrid adaptive CMAC with supervisory controller for a class of nonlinear system,” Neurocomputing, vol. 72, no. 7-9, pp. 1920-1933, Mar. 2009.
[18] D. A. Handelman, S. H. Lane, and J. J. Gelfand, “Integrating neural networks and knowledge-based systems for intelligent robotic control,” IEEE Control Syst. Mag., vol. 10, no. 3, pp. 77-87, Apr. 1990.
[19] F. H. Glanz and W. T. Miller, “Deconvolution and nonlinear inverse filtering using a neural network,” IEEE Int. Symp. Intell. Control, vol. 4, Glasgow, UK, pp. 2349-2352, May 1989.
[20] Y. Iiguni, “Hierarchical image coding via cerebellar model arithmetic computers,” IEEE Trans. Image Processing, vol. 5, no. 10, pp. 1393-1401, Oct. 1996.
[21] H. Shiraishi, S. L. Ipri, and Dong-il D. Cho, “CMAC neural network controller for fuel-injection systems,” IEEE Trans. Control Syst. Techn., vol. 3, no. 1, pp. 32-38, Mar. 1995.
[22] John Y. Hung, Weibing Gao, and W. P. Hung, “Variable structure control: a survey,” IEEE Trans. Ind. Electron., vol. 40, no. 1, pp. 2-22, Feb. 1993.
[23] H. Hu and P. Y. Woo, “Fuzzy supervisory sliding-mode and neural-network control for robotic manipulators,” IEEE Trans. Ind. Electron., vol. 53, no. 3, pp. 929-940, June 2006.
[24] J. J. E. Slotine and W. Li, Applied nonlinear control, Prentice-Hell, New Jersey, 1991, pp 1-13.
[25] J. Y. Hung, W. Gao, and J. C. Hung, “Variable structure control: a survey,” IEEE Trans. Ind.Electron., vol. 40, no. 1, pp. 2-22, Feb. 1993.
[26] L. Y. Sun, S. Tong, and Y. Liu, “Adaptive Backetstepping sliding mode control of static var compensator,” IEEE Trans. Control Syst. Techn., vol. 19, no. 5, pp. 1178-1185, Sept. 2011.
[27] L. X. Wang, “Fuzzy systems are universal approximators,” IEEE Int. Conf. on Fuzzy System, pp. 1163-1170, Mar. 1992.
[28] W. Johnson, Helicopter optimal descent and landing after power loss, NASA TM 73244, pp 1-19, May 1977.
[29] Range Commanders Council (RCC), “Common risk criteria standards for national test ranges: Supplement,” Deptment of Defense, standard 321-07, Jun. 2007.