臺灣博碩士論文加值系統

本研究設計直流伺服馬達之速度控制系統並達成減少能耗效果。研究應用PWM訊號驅動直流伺服馬達，探討電感量對馬達速度反應影響。採用特定學習架構之直接類神經網路控制，設計直流伺服馬達之速度控制器，以調節馬達保持精確的運轉速度。通常此種直接類神經網路控制器，須要建立控制器及受控系統之參考模型，以參考模型輸出及受控系統輸出誤差進行誤差倒傳遞之線上訓練。本文應用輸入命令與受控系統輸出誤差及誤差微分之線性組合近似線上訓練所須之倒傳遞誤差項(BPE)，可以免於建立受控系統數學模型及模擬器(emulator)，且加快神經鍵加權值之收斂速率。本文以數值模擬證明前述方法對直流伺服馬達之速度控制有良好之效果並探討直流伺服馬達速度控制反應過程能耗。本文以數值模擬比較傳統PI控制與類神經網路控制馬達速度反應過程能耗，模擬結果顯示類神經網路控制有穩定與精確速度反應並達成減少能耗效果。
關鍵字：直流伺服馬達，速度調節, 類神經網路，節能控制

This study designs a DC servo motor speed control system , and utilizes the method for energy saving effect。The PWM signal is applied to the DC drivers, and the inductance of DC motor affect the speed responses with PWM signals is investigated.
A direct neural control (DNC) based on back propagation neural networks (BPN) with specialized learning architecture is applied to control and regulate the speed of DC servo motor. The common DNC system usually needs an emulator, but the proposed neural controller is treated as a speed regulator without the specified reference model. A tangent hyperbolic function is used as the activation function, and the back propagation error (BPE) is approximated by a linear combination of error and error’s differential with high convergent speed.
The simulation results reveal that the proposed method is available to speed regulator keep motor in constant speed, and the energy consumes also investigated. The comparison of energy consumes between the conventional PID control and the DNC system is investigated by simulation. The simulation results also reveal the DNC system can control the DC motor in accurate speed with less energy consume.
Keywords: DC servo motors, Speed regulator, Neural networks, Energy saving controls

目錄
中文摘要 i
英文摘要 ii
謝誌 iii
目錄 iv
圖目錄 vi
第一章 緒論 1
1.1 研究背景 1
1.2文獻探討 2
1.3研究方法 5
1.4研究結果 6
第二章 直流馬達物理模式及驅動原理 7
2.1 直流馬達物理模式 7
2.2 直流馬達驅動 9
2.2.1H-bridge動作原理 9
2.2.2直流馬達PWM驅動 10
2.3 直流馬達驅動能耗 14
第三章 直流馬達驅動能耗分析 17
3.1 直流馬達轉速反應及能耗分析模擬 17
第四章 馬達速度控制與能耗分析 26
4.1 比例積分微分控制(PID controls)原理 26
4.2、直流馬達轉速控制 29
4.3模擬結果與節能分析 32
第五章 智慧型控制應用於馬達速度控制與能耗分析 38
5.1控制系統描述 39
5.2類神經網路控制器與誤差適應法則 40
5.3動態模擬 43
第六章 結論 58
參考文獻 59
附錄 61
簡歷 63

參 考 文 獻

1. D. Psaltis, A. Sideris, and A.A. Yamamura, “A Multilayered Neural Network Controller,” IEEE Control Systems Magazine, vol. 8, no. 2, pp. 17-21, April 1988.
2. K. S. Narebda, and K. Parthasarathy, “Identification and Control of Dynamical Systems Using Neural Networks”, IEEE Trans. Neural Networks, vol. 1, no. 1. pp. 4-27, 1990.
3. T. Fukuda, and T. Shibata, “Theory and Applications of Neural
Networks for Industrial Control Systems”, IEEE Transactions on
Industry Electronics, vol. 39, no. 6, Dec 1992.
4. G. Cybenko, “Approximation by Superpositions of A Sigmoidal Function”, Mathematics of Controls, Signals and Systems, vol. 2, no. 4, pp. 303-314, 1989.
5. J. de Villiers, E. Barnard, “Backpropagation Neural Nets with One and Two Hidden layers”, IEEE Trans. Neural Networks, vol. 4, no. 1. pp. 136-141, Jan .1993.
6. Y. Zhang, P. Sen, and G. E. Hearn, “An On-line Trained Adaptive Neural Controller”, IEEE Control Systems Magazine, vol. 15, no. 5, pp. 67-75, October 1995.
7. F. J. Lin, W. J. Hwang and R. J. Wai, “Ultrasonic Motor Servo
Drive with On-Line Trained Neural Network Model-Following
Controller”, IEE Proc.-Electr. Power Appl., vol. 145, no. 2, pp.
105-110, 1998.
8. F. J. Lin and R. J. Wai, “Hybrid controller using neural network
for PM synchronous servo motor drive”, Instrument Electric ]
Engine Process Electric Power Application, Vol. 145, No. 3, pp.
223-230, 1998.
9. Rao, D. H.,Kamat, H. V., “A Neural-PID speed controller for DC
Drives”, Power Electronics, Drives and Energy Systems for
Industrial Growth, 1996., Proceedings of the 1 Conference on, Vol.
2, pp.757-763, 1995

10. J.H.F. Cavalcanti, “Intelligent Control System Using PID and
Neural Controllers”, Circuits and Systems, Proceedings of The
38 th Midwest Symposium on, Vol. 1, pp. 425-428, 1995.
11. E. G. Janardan, F. Gajendran, and P. M. S. Nambisan, “State
Feedback Using Artificial Neural Network for Speed Control of DC
Motor”, Power Electronics, Drives and Energy Systems for
Industrial Growth, Proceedings of the 1 Conference on, Vol. 2,
pp.753-756, 1995.
12. S. Weerasooriya, and M. A. EI-Sharkawi, “Identification and
Control of a DC Motor Using Back-propagation Neural Networks”,
IEEE Trans. Energy Conversion, vol. 6, pp. 663-669, Dec. 1991.
13. A. Rubai, and R. Kotaru, “Online Identification and Control of
a DC Motor Using Learning Adaptation of Neural Networks” IEEE
Transactions on Industry Applications, vol. 36, no. 3, June 2000.
14. R. S. Ahmed, K. S. Rattan, and I. H. Khalifa, “Real-Time Tracking
Control of A DC Motor Using A Neural Network”, IEEE Aerospace
and Electronics Conference, vol. 2, pp.593-600, 1995.
15. M. A. Hoque, M. R. Zaman and M. A. Rahman, “Artificial Neural
Network Based Controller For Permanent Magnet DC Motor Drives”
IEEE Industry Application Conference, Thirtieth IAS Annual
Meeting, vol. 2, pp.1775-1780, 1995.
16. M. A. EI-Sharkawi, “Neural Network Application to High
Performance Electric Drives Systems”, Industrial Electronics,
Control, and Instrumentation, Proceedings of The IEEE
International Conference on , Vol. 1, pp.44-49, 1995.
17. M. A. Rahman, and M. A. Hoque, “On-Line Self-Tuning ANN-Based
Speed Control of a PM DC Motor ” IEEE/ASME Transactions on
Mechatronics, vol. 2, no. 3, pp. 169-178. September 1997.
18. M. Bertoluzzo, G. S. Buja, F. Todesco, “Neural Network Adaptive
Control of A DC Drive”, Industrial Electronics, Control, and
Instrumentation, Proceedings of The IEEE International
Conference on , Vol. 2, pp. 1232-1236, 1994.
19 .Ming-Huei Chu, Yi-Wei Chen , Yuan Kang, Zhi-Wei Chen, “The
Research of Sampling Frequency for A DC Servo Motor Speed Control
System Based on Neural Networks”, The 6th International Conference on Natural Computation (ICNC'10), 10-12 August 2010.(Ei)