進階搜尋

 
查詢範圍:「   」
顯示範圍:第筆 論文書目資料
顯示格式:全部欄位
共 6 筆
------------------------------------------------------------------------ 第 1 筆 ---------------------------------------------------------------------
系統識別號 U0006-0206200613362500
論文名稱(中文) 應用各種預測理論預測台灣電力系統區域負載
論文名稱(英文) Applying Various Prediction Theories to Forecast Regional Power Demand of Taiwan Power System
校院名稱 國立台北科技大學
系所名稱(中) 機電科技研究所
系所名稱(英) Graduate Institute of Mechanical Engineering
學年度 94
學期 2
出版年 95
研究生(中文) 王長春
學號 91669002
學位類別 博士
語文別 英文
口試日期 2006-05-06
論文頁數 80頁
口試委員 委員-游文雄
委員-洪穎怡
委員-黃培華
委員-林啟瑞
委員-曾百由
指導教授-高文秀
指導教授-吳明川
關鍵字(中) 區域負載
倒傳類神經
模糊理論
灰色理論
關鍵字(英) Regional power demand
Back-propagation neural network
Fuzzy theory
Grey theory
學科別分類 學科別應用科學電機及電子
學科別應用科學機械工程
中文摘要 本論文旨在將各地區多年來之實際用電負載、經濟成長率,工業結構、地區發展、住宅數量及消費者行為等,利用各種不同預測理論求得符合台灣地區之區域電力負載需求的模型,並藉此模型來預測台灣地區之區域電力負載需求。經求得的準確模型並用來預測區域電力負載的主要目的是提供電力系統中,各發電機組排程與協調、負載管理、經濟調度及電力系統安全及控制的重要參考依據,以及因應未來做為發電廠及輸配電線路規劃建置之皋本。所以,區域電力負載預測的準確性,將直接影響到將來各發電廠的運轉成本、穩定度、安全性及輸配電線路之建設費用。
為因應台灣地區之區域電力負載特性,本文特將台灣分成北、中、南、東四個區域,利用倒傳類神經網路、模糊理論及灰色理論,三種理論為建模依據,再依實際已有之電力需求資料求得模型參數值,接著便依據此模型估測未來之電力需求,以供電業主管機關參考,其中,倒傳類神經預測法是一種多層的架構,必須利用鏈狀法則(Chain rule)來計算它的鏈結值變化量,使得輸出與目標值間的誤差降至最低。模糊理論預測法則是把傳統數學從二值邏輯(binary logic)擴展到連續多值(continuous multi-value)領域,再利用歸屬函數(membership function)描述一個概念的特質,亦即使用0和1之間的數值來表示一個元素屬於某一概念的程度,這個值稱為元素對集合的歸屬度(membership grade)。而灰色理論預測法則是針對系統模型之不明確性及資訊之不完整性下,進行關於系統的關係分析(relational analysis)及模型建構(model construction)工作,並藉著預測(prediction)及決策(decision making)方式來深討及瞭解系統的情況,俾能對事物的“不確定性”(not certainty)、多變量輸入(multi-input)、離散資料(discrete data)及數值(Value)的不完整性(not enough)做有效的處理。
本文將採用自1984年到2004年的資料進行建模工作,並透過使用平均的絕對百分比誤差(MAPE)和均方根百分比誤差(RMS)兩種值的比較來驗證所提之三種建模的準確性。最後,我們也將各建模所得之最小之誤差值列表,並驗證出灰色理論預測法則建模於台灣區域電力需求預測上具有較小之誤差值。
英文摘要 In this dissertation, we utilize three kinds of prediction methods, back-propagation neural network, fuzzy theory, and grey theory, to obtain good fitness of the model in accordance with power loading, economic growth rate, industry structure, regional development, housing quantity, and consumer manner, etc. for each region from 1984 to 2004, and make use of these models to predict the regional power load demand in Taiwan. Then, we will use the obtained accurate models for predicting the regional power load to provide generator arrangement with coordinate, load management, economic adjustment, power system security and control, and the most important for the power plant in the power distribution to plan the regional power construction in the future. Therefore, the precision of regional power loading prediction will affect the future operation cost, stability margin, security, and the construction cost of power transmission route.
This thesis concentrates on the question of regional power loading prediction in Taiwan. For convenience, we divide the region of Taiwan into four sub-regions – North, Central, South, and East, and apply the back-propagation neural network, fuzzy theory, and grey theory to obtain the parameters of respective models in accordance with the existing data of power load demand, and then to estimate and examine the power load demand in the future in order to supply power demand data for the government. The back-propagation neural network prediction method is a multi layer structure and uses the chain rule to calculate the changing quantity of chain values so as to force the output and target value to a lower deviation. The fuzzy theory prediction method uses a traditional mathematics from binary logic to extend to continuous multi-value and also uses the membership function to describe an idea. The theory also uses the values between 0 and 1 to represent the elements belonging to which thinking level. This value can be called a membership grade. The grey theory prediction method is based on the uncertainty and in-completed information of model system to progress the system of relational analysis and model construction. It also uses the prediction and decision making method to do the discussion and understanding the system status. For uncertainties, multi-input, and not enough data, it can do the effective disposition.
By using the data from 1984 to 2004 and the Mean Absolute Percentage Error (MAPE) and the Root Mean Squared Percentage Error (RMS) for comparisons, some simulation results are used to illustrate the effectiveness of the proposed scheme. Finally, by tabulating the respective minimum errors of the proposed three prediction methods, it is shown that the grey theory prediction model can be more satisfactory for power forecasting than the other two.
論文目次 Chinese Abstract i
Abstract iii
Chapter 1 Introduction 1
1.1 Recently power demand 3
1.2 The mothods of prediction 4
1.3 The advantage of regional power supply 7
Chapter 2 Power Demand Forcasting 8
2.1 Geographical zoning 9
2.2 Applying various prediction methods 10
Chapter 3 Power Demands Forecasting Using Back-propagation Neural Network 12
3.1 Back-propagation algorithm method 12
3.2 Forward signal transmission 14
3.3 Backward deviated transmission and key value learning 15
3.4 Back propagation neural network prediction 19
3.5 Regional power demand forecasting 22
3.6 Computer simulation 24
3.7 Evaluation of the prediction 25
3.8 Discussion 30
Chapter 4 Fuzzy Power Demands Forecasting 31
4.1 Fuzzy set definition 33
4.2 Membership function 35
4.3 Fuzzifier 40
4.4 Fuzzy set calculation 41
4.5 Fuzzy inference 41
4.6 Defuzzification methods 42
4.7 The model of fuzzy linear regression 43
4.7.1 Fuzzy linear regression method 45
4.7.2 Inference flow of fuzzy theory 48
4.8 Computer simulation 49
4.9 Evaluation of the prediction 52
4.10 Discussion 54
Chapter 5 Grey Power Demand Forecasting 55
5.1 Grey theory research content 56
5.1.1 Grey generating 56
5.1.2 Grey relational analysis 57
5.1.3 Grey model construction 57
5.1.4 Grey prediction 58
5.1.5 Grey decision making 58
5.1.6 Grey control 58
5.2 The related knowledge of grey theory 58
5.2.1 Recognition model 58
5.2.2 Four status 59
5.2.3 Reason and cause relationship and grey system 59
5.3 Grey theory prediction 60
5.4 Computer simulating 68
5.4.1 The model of grey theory prediction 69
5.5 Evluation of the prediction 70
5.6 Results of the prediction 71
5.7 Discussion 73
Chapter 6 Conclusion 75
Chapter 7 Future Work 77
References 78
Autobiography a
Publications and Research Project e
International Program Committee g
參考文獻 1. Website of Taiwan power Company, http://www.taipower.com.tw
2. Chang-Chun Wang “Optimal Operation of Deregulation Taiwan Power System,” Thesis, National Taipei University of Technology, May 2002.
3. Website of Map Education Data, http://www.edu.tw
4. Che-Chiang Hsu and Chia-Yon Chen, “The Application of Grey Theory on the Short-Run Load Forecasting in Taiwan Area,” Taiwan Engineering monthly, No.625, Sep. 2000.
5. Shen-Pu Lin and Chen-An Hong, “Introduction of Neural Network,” 2nd ed., Chuan-Hwa Technology Books, 1995.
6. Hwa-Chong Lo, “The Application of Neural Network—MATLAB,” Chin-Way Technology Co., Sep. 2001.
7. Jin-Chon Jen, “MATLAB Program Design (Elementary),” 1st ed., Chuan-Hwa Technology Books, May 2000.
8. J.S. Jang, “Neuro-Fuggy and Soft Computing,” Chuan-Hwa Technology Books, 1997.
9. Tomonobu Senjyu, Hitoshi Takara, Katsumi Uezato and Toshihisa Funabashi, “One-Hour-Ahead Load Forecasting using Neural Network,” IEEE Transactions on power system Vol.17, pp.113-118, No.1, Feb. 2002.
10. H.S. Hippert, C.E. Pedreira, and R.C. Souza, “Neural Networks for Short-term Load Forecasting: A review and evaluation,” IEEE Transactions on power system. Vol.16, pp.43-55, 2001.
11. James W. Taylor and Roberto Buigga, “ Neural Network Load Forecasting with Weather Ensemble Predictions,” IEEE Transactions on Power System. Vol.17, No.3, Aug. 2002.
12. S. Barghinia, P. Ansarimehr, H. Habibi and N. Vafadar, “ Short Term Load Forecasting of Iran National Power System using Artificial Neural Network, ” in Proc. IEEE Power Tech, Vol. 3, Porto, Portugal, 2001.
13. A.S. Bretas and A.G Phadke, “Artificial Neural Networks in Power System Restoration,” IEEE Transaction on power Delivery, Vol.18, No.4, pp.1181-1186, Oct. 2003.
14. Tzu-Yi Shi and Yun-Chon Bir, “A Study on Establishing Energy Demand Forecasting Mode in Taiwan,” Atomic Energy council MOEA, 1995.
15. Li-Min Shay, “A Study on the Power Demand of Taiwan,” Atomic Energy Council MOEA, 1984.
16. Taiwan Power Company Engineering Monthly, Taiwan Power Company, Vol. 609, May 1999.
17. Long-term Load Forecasting, Taiwan Power Company Planning Division, 1999 and 2000.
18. Annual Statistics, Taiwan Power Company Planning Division, 2004
19. Marketing Strategy of Next Decade, Taiwan Power Company Planning Division, Feb.2004.
20. Kuo-sun Chuang, “Load Forecasting by Combination of Grey and Fuzzy Theory,” Thesis, National Taipei University of Technology July. 2001.
21. Chuin-Liang Lin, “Intelligent Control,” Chuang-Hwa Technology Book Co. Dec. 2004.
22. Timothy J. Ross, “Fuzzy Logic with Engineering Applications,” International Edition McGraw-Hill, Inc. 1997.
23. Kyung-Bin Song, Young-Sik Baek, Dug-Hun Hang and Gilsoo Jang, “Short-Term Load Forecasting for Holidays Using Fuzzy Linear Regression Method,” IEEE Transactions on power systems. Vol.20, No.1, Feb. 2004.
24. D.H. Hong et al, “Fuzzy Linear Regression Analysis for Fuzzy Input-Output Data using Shape Preserving Operations,” Fuzzy set and System, Vol.122, pp.513-526, Sept. 2001.
25. Kuen-Li Wen, Yi-Fung Huang, Fan-Shiung Chen Yuan-pin Lee, Jyh-Horng Lian and Jia-Ruei Lia, “Grey Prediction,” Chuan-Hwa Technology book Co. Sep. 2002.
26. Han-Shiung Wu, Ju-Long Deng and Kuen-Li Wen, “Grey theory analysis,” Kao-Li book Co., 1995.
27. You-Shian Huang and Chau-guang Chen, “Grey System Application and Development,” Fuzzy System Journal, Vol.4, No.1, pp.1-7, 1998.
28. Che-Chiang Hsu and Chia-yon Chen, “The Application of Grey Theory Prediction for Power Demand in Taiwan Area,” Energy monthly, Vol.29, No.4, pp.95-108, Oct. 2000.
29. Yuk-Tong Lee, Ching-Lien Huang and Li Wang, “The Application of Gray Model Forecast Control on Power System Stability,” Thesis, National Cheng-Kung University. 1993.
30. Kuo-Pin Chuang, “Load Forecasting by Combination of Grey and Fuzzy Theory,” Thesis, National Taipei University of Technology, Jun. 2001.

------------------------------------------------------------------------ 第 2 筆 ---------------------------------------------------------------------
系統識別號 U0006-0407200616420300
論文名稱(中文) 適用於網路型模糊控制系統之模糊增益調節器
論文名稱(英文) A Fuzzy Gain Tuner for Networked Fuzzy Control system
校院名稱 國立台北科技大學
系所名稱(中) 機電整合研究所
系所名稱(英) Graduate Institute of Mechatronic Engineering
學年度 94
學期 2
出版年 95
研究生(中文) 郭盼容
學號 93408016
學位類別 碩士
語文別 中文
口試日期 2006-07-03
論文頁數 131頁
口試委員 指導教授-姚立德
委員-曾傳蘆
委員-蘇順豐
委員-王乃堅
關鍵字(中) 網路控制系統
模糊控制
基因演算法
自動導航車
關鍵字(英) networked control system
fuzzy control
genetic algorithm
automatic guided vehicle
round-trip time
學科別分類 學科別應用科學電機及電子
學科別應用科學機械工程
中文摘要 針對控制系統以網路做為通訊媒介的環境,本文提出一個自動增益補償的模糊增益調節器(Fuzzy Gain Tuner, FGT)來因應網路隨機的延遲量,所造成網路控制系統不穩定甚至不可控制的響應結果。而此FGT以網路傳輸一趟所花費的時間(Round-trip time, RTT)做為網路延遲狀況的輸入,利用RTT可以分析出網路的壅塞及變動情形;另外FGT的模糊法則可以透過離線狀況下建立各種網路延遲的系統模型,再交由基因演算法(Genetic Algorithm, GA)應用於Fuzzy Takagi-Sugeno-Kang (TSK) Model學習,以得到在不同延遲條件下最佳的控制系統效能。最後,本文以自動導航車做為受控平台進行路徑追隨與尋標避障等實驗,說明本模糊增益調節器在實際系統中的可行性。
英文摘要 Aim at the control system that communication by network system, this thesis proposes a “Fuzzy Gain Tuner, FGT” that can deal with the random delay of the network to cause an unstable and even not controllable result. The FGT considering the network delay status by the round-trip time (RTT) of network transmits a round-trip. Utilize RTT to analyze the congestion and the variation of the network delay. In addition, the fuzzy rules of FGT can learning automatically by genetic algorithm (GA) and the Takagi-Sugeno-Kang model (TSK) that considering many network delay models to get the better performance under difference delay conditions. Finally, experiment of path following and obstacle avoidance by the automatic guided vehicle (AGV) will prove the FGT feasibility in the practice control system.
論文目次 摘要…………………………………………………………………………………..i
ABSTRACT…………………………………………………………………………ii
誌謝…………………………………………………………………………………iii
目次…………………………………………………………………………………iv
表目錄………………………………………………………………………..………vii
圖目錄…………………………………………………………………………..…..viii
第一章 緒論………………………………………………………………………1
1.1 前言………………………………………………………………………1
1.2 文獻回顧…………………………………………………………………1
1.2.1 時延控制系統……………………….………………………………2
1.2.2 網路控制系統………………………………………………………2
1.2.3 自動導航車…………………………………………………………4
1.3 研究動機與目的…………………………………………………………5
1.4 章節說明………………………………………………………………7
第二章 網路控制系統…………………………………………………………9
2.1 網路控制系統簡介……………………………………………………9
2.1.1 網路控制架構……………………………………………………9
2.1.2 TCP/IP通訊協定…………………………………………………10
2.1.3 主從式網路架構…………………………………………………13
2.2 網路傳輸延遲分析……………………………………………………13
2.3 控制系統取樣頻率分析………………………………………………16
2.4 網路控制問題與策略…………………………………………………18
2.4.1 網路控制問題……………………………………………………18
2.4.2 網路控制策略……………………………………………………19
2.5 事件觸發式結合命令暫存器策略……………………………………21
2.5.1 系統說明…………………………….……………………………22
2.5.2 傳輸協定及封包格式………………………………………………23
第三章 模糊增益調節器……………..…………………………………………26
3.1 網路控制系統分析……………………………………………………26
3.2 增益與時延系統分析……………………………………………………28
3.3 模糊增益調節器………………….……………………………………30
3.3.1 模糊增益調節器架構……….………………………………………30
3.3.2 結合基因演算法設計模糊增益調節器………………………………32
3.3.2.1 基因演算法與模糊法則…….………………….……………32
3.3.2.2 模糊增益調節器輸入變數…….……………………….………34
3.3.2.3 網路延遲之模擬…….………………………………….………35
3.3.2.4 基因法則之學習…….………………………………….………39
3.4 實驗結果與討論…………………………………………………………41
第四章 自動導航車網路控制系統………………………………………………44
4.1 自動導航車系統架構…………………………………………………44
4.1.1 系統說明…………………….…………………………………44
4.1.2 車體結構…………………….……………………………………45
4.1.2.1 自走車型式類別……………………………………………45
4.1.2.2 自走車外觀…………………………………………………46
4.1.3 電腦與自走車通訊方式……………………………………………48
4.1.3.1 自動導航車連線方式………………………………………49
4.1.3.2 車上電腦之介紹……………………………………………50
4.1.4 電力與驅動系統……………………………………………………50
4.1.5 聲納感測系統………………………………………………………51
4.2 運動方程式……………………………………………………………53
4.3 動態模型………………………….……………………………………56
4.4 路徑追隨演算法………………………………………………………58
4.4.1 直線路徑法…………………………………………………………58
4.4.2 二次曲線法…………………………………………………………59
4.5 網路控制環境……………….…………………………………………61
第五章 路徑追隨網路控制器……………………………………………………63
5.1 延遲位置估測器………………………………………………………63
5.2 直線路徑控制…………………………………………………………65
5.2.1 模糊控制器設計……………………………………………………65
5.2.2 模糊增益調節器設計………………………………………………69
5.2.3 模擬網路延遲控制實驗……………………………………………72
5.2.4 實際網路延遲控制實驗……………………………………………76
5.2.5 實驗結果……………………………………………..……..…...81
5.3 二次曲線路徑控制……………………………………………………85
5.3.1 模糊控制器設計……………………….…………………………85
5.3.2 模糊增益調節器設計………………………………………………86
5.3.3 模擬網路延遲控制實驗……………………………………………92
5.3.4 實際網路延遲控制實驗……………………………………………97
5.3.5 實驗結果…………………………………………………………...104
第六章 尋標避障網路控制器…………………………………………………110
6.1 聲納感測器之使用……………………………………………………110
6.2 避障控制器……………………………………………………………110
6.2.1 斥力避障概念……………………………………………………110
6.2.2 窄巷模式…………………………………………………………116
6.3 模糊增益調節器………………….……………………………………117
6.4 模擬網路延遲避障實驗………………………………………………118
第七章 結論與未來展望………………………………………………………125
7.1 結論……………………………………………………………………125
7.2 未來展望…………………………………….…………………………126
參考文獻…………………………………………………………...………………127
參考文獻 [1] Mo-Yuen Chow, “Network-based control systems: a tutorial,” in Proc. IEEE Annual Conf. Industrial Electronics, vol. 3, pp. 1593 – 1602, Dec. 2001.
[2] Mo-Yuen Chow, “Gain adaptation of networked DC motor controllers based on QoS variations,” IEEE Trans. on Industrial Electronics, vol. 50, no. 5, pp. 936-943, Oct. 2003.
[3] O. H. Smith, “Closed control of loops with dead times,” Chem. Eng. Prog., vol. 53, no. 6, pp. 217–219, 1957.
[4] R. Matausek and A. D. Micic, “On the modified Smith predictor for controlling a process with an integrator and long dead-time,” IEEE Trans. Automat. Contr., vol. 44, no. 8, pp. 1603-1606, 1999.
[5] I. Kaya, “Obtaining controller parameters for a new PI-PD Smith predictor using auto tuning,” Journal of Process Control, vol. 13, no. 5, pp.465-472, 2003.
[6] S. Majhi and D. P. Atherton, “Modified Smith predictor and controller for processes with time delay,” IEE Proc.-Control Theory Appl., vol. 146, no. 5, Sep. 1999.
[7] W. F. Xie and A. B. Rad, “Fuzzy adaptive internal model control,” IEEE Trans. Ind. Electron., vol. 47, no. 1, pp. 193–202, 2000.
[8] K. R. Lee, J. H. Kim, E. T. Jeung, H. O Yun and H. B. Park, “Observer-based fuzzy H∞ control for uncertain nonlinear systems with time delays,” in Proc. American Contr. Conf., vol. 2, no. 2, pp. 1269-1273, 1999.
[9] H. F. Ho, Y. K. Wong and A. B. Rad, “Adaptive neuro-fuzzy control of system with time delay,” in Proc. IFSA World Congress and 20th NAFIPS Int. Conf., vol. 2, pp. 1044-1049, 2001.
[10] J. Q. Huang and F. L. Lewis, “Neural-network predictive control for nonlinear dynamic systems with time-delay,” IEEE Trans. Neural Networks, vol. 14, no. 2, pp. 377-389, 2003.
[11] I. R. Petersen and D. C. McFarlane, “Optimal guaranteed cost control and filtering for uncertain linear systems,” IEEE Trans. Automat. Contr., vol. 39, pp. 1971-1977, 1994.
[12] J. S. Luo, P. P. J., S. Weiland and A. Goldenberge, “Design of performance robustness for uncertain linear systems with state and control delays,” IEEE Trans. Automat. Contr., vol. 43, no. 11, pp. 1593-1596, 1998.
[13] N. Luo and M. D. L. Sen, “State feedback sliding mode control of a class of uncertain time delay systems,” IEEE Proceedings-D, vol. 140, no. 4, 1993.
[14] S. Oucheriah, “Dynamic compensation of uncertain time-delay system using variable structure approach,” IEEE Trans. Circuits and Syst., vol. 42, no.8, 1995.
[15] Y. Y. Cao, Y. X. Sun and J. Lam, “Delay-dependent robust H∞ control for uncertain systems with time-varying delays,” IEE Proc.-Control Theory Appl., vol. 145, no. 3, pp. 338-344, 1998.
[16] G. W. Ng and P. A. Cook, “Neural networks in control of systems with unknown and varying time-delays,” in Proc. Control’96, UKACC Int. Conf., vol. 1, pp. 188-193, 2-5 Sep. 1996.
[17] S. B. Chen, L. Wu and Q. L. Wang, “Self-learning fuzzy neural networks for control of uncertain systems with time delays,” IEEE Trans. Syst., Man, Cybern., vol. 27, no. 1, pp. 142-148, 1997.
[18] K. C. Lee, S. Lee and M. H. Lee, “Remote fuzzy logic control of networked control system via Profibus-DP,” IEEE Trans. Ind. Electr., vol. 50, no. 4, pp. 784-792, 2003.
[19] Haydn A. Thompson, “Wireless and Internet communications technologies for monitoring and control,” Control Engineering Practice, vol 12, pp. 781–791, 2004.
[20] Y. Tipsuwan and M. Y. Chow, “Control methodologies in networked control system,” Control Engineering Practice, vol. 11, pp. 1099-1111, 2003.
[21] K. H. Han, S. Kim, Y. J. Kim, S. E. Lee and J. H. Kim, “Implementation of internet-based personal robot with internet control architecture,” in Proc. IEEE Int. Conf. Robotics and Automat., vol. 1, pp. 217-222, 2001.
[22] A. Benporad, “Predictive control of teleoperated constrained systems with unbounded communication delays,” in Proc. IEEE Int. Conf. Decision Contr., vol. 2, pp. 16-18, 1998..
[23] J. W. Overstreet and A. Tzes, “An Internet-based real-time control engineering laboratory,” IEEE Contr. Syst. Magazine, vol. 19, no. 5, pp. 19–34, 1999.
[24] N. B. Almutairi, M. Y. Chow and Y. Tipsuwan, “ Network-based controlled DC motor with fuzzy compensation,” The 27th Annual Conference of the IEEE industrial Electronics society, vol. 3, pp. 1844 – 1849, 2001.
[25] R. Luck and A. Ray, “An observer-based compensator for distributed delays,” Automatica, vol. 26, no. 5, pp, 903-908, 1990.
[26] R. Luck and A. Ray, “Experimental verification of a delay compensation algorithm for integrated communication and control systems,” International Journal of Control, vol. 59, no. 6, pp. 1357-1372, 1994.
[27] H. Chan and U. Ozguner, “Closed-loop control of systems over a communications network with queues,” International Journal of Control, vol. 62, no. 3, pp. 493-510, 1995.
[28] T. F. Abdelzaher, E. M. Atkins and K. G , Shin, “QoS negotiation in real-time systems and its application to automated flight control,” IEEE Trans. Computers, vol. 49, no. 11, pp. 1170-1183, 2000.
[29] B. Li and K. Nahrstedt, “A control-based middleware framework for quality-of-service adaptations,” IEEE Journal on Selected Areas in Communications, vol. 17, no. 9, pp. 1632-1650, 1999.
[30] I. Elhajj, N. Xi, W. K. Fung, Y. H. Liu and W. J. Li, “Haptic information in internet-based teleoperation,” IEEE/ASME Trans. Mechatronics, vol. 6, no. 3, 2001.
[31] Junxia Mu, G. P. Liu and David Rees, "Design of robust networked predictive control systems," in Proc. American Contr. Conf., vol. 1, pp. 638 - 643, June 2005.
[32] Johan Nilsson, ”Stochastic Analysis and control of real-time systems with random time delays,” in Automatica, vol. 34, pp. 57-64, June 1997.
[33] Yodyium Tipsuwan and M. Y. Chow, “On the gain scheduling for networked PI controller over IP network,” IEEE/ASME Trans. Mechatronics, vol. 9, no. 3, pp. 491-498, Sep. 2004.
[34] Seung-Gu Na, “TCP-like flow control algorithm for real-time applications,” in Proc. IEEE Int. Conf. Networks, pp. 99-104, Sep. 2000.
[35] Rajani K. Mudi, “A robust self-tuning scheme for PI- and PD-type fuzzy controllers,” IEEE Trans. Fuzzy Systems, vol. 7, no. 1, pp. 2-16, Feb. 1999.
[36] Jin-Hee Choi, “One-way delay estimation and its application,” Elsevier Science, Computer Communications, vol. 28, no. 7, pp. 819–828, May 2005.
[37] D. Srinivasagupta, H. Schättler, Babu Joseph, “Time-stamped model predictive control: an algorithm for control of processes with random delays,” Computers and Chemical Engineering, vol. 28, pp. 1337-1346, 2004.
[38] R. C. Luo, and T. M. Chen, “Development of a multibehavior-based mobile robot for remote supervisory control through the Internet," IEEE/ASME Trans. on mechatronics, Vol. 5, No. 4, pp. 376-385, Dec. 2000.
[39] R. C. Luo, and T. M. Chen, “Remote supervisory control of a sensor based mobile robot via Internet,"in Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems, Grenoble, France, Vol. 2, pp.1163-1168, 1997
[40] R. C. Luo, “Networked intelligent robots through the Internet: Issues and Opportunities,” Proc. of the IEEE, USA, vol. 91, no. 3, pp. 371 - 382, Mar. 2003.
[41] A. Fujimori, and S. Tani, “A navigation of mobile robots with collision avoidance for moving obstacles," IEEE ICIT '02 Int. Conf. Bangkok, Thailand, Vol. 1, pp. 1-6, Dec. 2002.
[42] X. Wang and S. X. Yang, “A neuro-fuzzy approach to obstacle avoidance of a nonholonomic Mobile Robot,"in Proc. IEEE/ASME Conf. on Advanced intelligent Mechatronics, pp. 29-34, July 2003.
[43] N. H. C. Yung, and C. Ye, “An intelligent mobile vehicle navigator based on fuzzy logic and reinforcement learning,"IEEE Trans. Syst., Man, Cybern., Part B: Cybernetics, Vol. 29, No. 2, pp.314-321, Apr. 1999.
[44] C. Ye, N. H. C. Yung and D. Wang, “A fuzzy controller with supervised learning assisted reinforcement leaning algorithm for obstacle avoidance,"IEEE Trans. Syst., Man, Cybern., Part B: Cybernetics, Vol. 33, No. 1, pp.17-27, Feb. 2003.
[45] Y. C. Kim, S. B. Cho, and S. R. Oh, “Map-building of a real mobile robot with GA-Fuzzy controller," International Journal of Fuzzy Systems, vol. 4, no. 2, pp. 696-703, June 2002.
[46] S. Thongchai, and K. Kawamura, “Application of fuzzy control to sonar-based
obstacle avoidance mobile robot,” in Proc. IEEE Int. Conf. on Control Applications, Anchorage, Alaska, USA, pp. 425-430, Sep. 2000.
[47] K. Konolige, “A Gradient Method for Realtime Robot Control,” SRI International, 1999.
[48] J. I. Kyun, H. K. Bum, H. S. Kyo, and H. S. Chan,” Path planning of mobile robot using neural network,” in Proc. IEEE ISIE, Bled, Slovenia, pp. 979-983, 1999.
[49] A. Saffiotti, E. H. Ruspini, and K. Konolige,” Blending reactivity and goal-directedness in a fuzzy controller,” IEEE Neural Nets and Fuzzy Control, San Francisco, 1993.
[50] YUTING's, Page, http://lips.lis.ntu.edu.tw/ytchiang/, Sep. 2004.
[51] F. L. Lian,” Analysis, design, modeling and control of networked control systems,” PhD thesis, University of Michigan, USA, 2001.
[52] 黃能富,區域網路與高速網路,台北:維科出版社,1996。
[53] R. Oboe and P. Fiorini, “A design and control environment for internet-based telerobotics,” The International Journal of Robotics Research, vol.17, no.4, pp. 433-439, 1998
[54] Chin-Chin Lin, “A gain-adjusted fuzzy PI/PD adaptive controller based on the accumulated genetic algorithm,” in Proc. IEEE Int. Conf. Fuzzy Systems, pp. 513-518, May 2005.
[55] Patrick Siarry, “A genetic algorithm for optimizing Takagi-Sugeno fuzzy rule bases,” Elsevier Science, Fuzzy Sets and Systems, vol. 99, no. 1, pp. 37-47, Oct. 1998.
[56] Yodyium Tipsuwan, “Gain scheduler middleware: A methodology to enable existing controllers for networked control and teleoperation—Part II: Teleoperation,” IEEE Trans. on Industrial Electronics, vol. 51, no. 6, Dec. 2004.
[57] Koichi Yoshizawa, “Path tracking control of mobile robots using a quadratic curve,” in Proc. IEEE Intelligent Vehicles Symposium, pp 58-63, Sep. 1996.
[58] 連柏菁,基於模糊地圖重置之自動導航車避障策略,碩士論文,國立台北科技大學,2004。
[59] 羅雅齡,網路控制系統的穩定性分析,碩士論文,國立交通大學,2004。
[60] B. C. Kuo, Automatic control systems, 5 ed. englewood cliffs, NJ: Prentice-Hall, 1987.
[61] 張碩,自動控制系統,台北:鼎茂圖書,2001。
[62] 統計網路學習館, http://estat.ncku.edu.tw, Aug. 2000.
[63] 劉丁強,適用於時延系統之模糊控制器設計,碩士論文,國立台北科技大學,2004。

------------------------------------------------------------------------ 第 3 筆 ---------------------------------------------------------------------
系統識別號 U0006-0807200514304400
論文名稱(中文) 應用類神經網路與小波理論分析地震前地下水位波動
論文名稱(英文) Applications of Artificial Neural Network and Wavelet Theory to Analyze the Fluctuation of Groundwater Level Before An Earthquake Appears
校院名稱 國立台北科技大學
系所名稱(中) 土木與防災研究所
系所名稱(英) Graduate Institute of Civil and Disaster Prevention Engineering
學年度 93
學期 2
出版年 94
研究生(中文) 廖啟佑
學號 92428041
學位類別 碩士
語文別 中文
口試日期 2005-06-17
論文頁數 89頁
口試委員 指導教授-陳彥璋
委員-張國強
委員-林鎮洋
委員-楊翰宗
關鍵字(中) 地震
類神經網路
小波理論
關鍵字(英) Earthquake
Artificial Neural Network
Wavelet theory
學科別分類 學科別應用科學土木工程及建築
中文摘要 台灣地區由於地質複雜之特殊性,位處「歐亞大陸板塊」與「菲律賓海洋板塊」持續板塊擠壓,以致台灣每年地震活動頻繁,地震乃是大地能量釋放的自然演變過程,並非人力所能控制,經證實地震與地下水位異常變化有一定程度之相關係,加上台灣地區擁有健全地下水位觀測井網;於地震地下水研究上佔有先機,為尋求降低地震災害損失程度,極需深入探討地震地下水之相關機制。
本研究以嘉南強震觀測網中之六甲、那菝地震地下水觀測站井為研究對象,為能探討地震事件是否對地下水位產生異常行為,利用觀測的地下水位時序來進行解析,探討地震發生前後時間點之水位的變化量,而為避免地震事件受地潮、降雨等事件影響,致使小波分析之高頻異常診斷無法獲得準確之結果,故利用類神經網路將降雨、地潮及不規則訊號等影響因子之趨勢進行濾除。
將經類神經網路濾除受地潮、海潮及降雨等影響因子之地下水位序列資料,應用小波(Wavelet)分析理論,探索地下水位測站之長時程地下水水位之多分辦層結構及應用小波轉換計算地下水位時間序列之小波係數,經小波係數值之計算可評估地下水位各種交織在一起之混合訊號,分解成不同分辨層或不同頻率區塊訊號,再與Donoho和Johnstone對估測訊號所發展出來之小波收縮(Wavelet Shrinkage)方法,選取一合適的臨界值,將所得的高頻小波係數做修剪(clipping)收縮處理,再將門檻值以外之各高頻小波係數與地震發生時間做一分析整理,藉此可明顯指出地下水水位出現頻率異常之時間點,因而將有助於減災,延長避難反應時間。
英文摘要 Located on the Eurasia plate and the Philippine marine plate to push with the lasting, where earthquakes happen frequently, Taiwan, due to particularity with complicated geography character, was attack by earthquakes. Earthquake is a natural proceeding in which the earth releases energy. It is not the manpower that can be controlled, through verifying that relation with a certain level of education in groundwater level change and the earthquake appears. Besides, there are well network observing groundwater changes in Taiwan. For observing groundwater, we get certain advantage. Searching how to decrease the damage caused by earthquakes, we must study the correlation between groundwater and earthquakes.
Observe the monitoring station of Nabal and Liujar as the research object, at the Jarnan strong shock earthquake groundwater network in this research. In order to probe the earthquake incident, whether produce the unusual behavior to the groundwater level, make using observed of groundwater level time sequence to analyze the change amount of the groundwater level clicked, in time before and after an earthquake attack. In order to prevent the earthquake incident from being influenced by incidents, such as ground tide , rainfall ,etc. Causing the wavelet analyse obtain the accurate result, the unusually high frequency be unable diagnose. The Artificial Neural Network(ANN) is so utilizing to detrend of rainfall, ground tide, and irregular signal, etc.
Detrend of morning and evening tides, rainfall time series through kinds of ANN. Using the Wavelet theory to explore the long-time groundwater level examines the amount layer of structure separately, and uses the Wavelet transform and calculate the Wavelet coefficient, can assess various mixing interweaving kinds of the groundwater level signal by calculation of Wavelet coefficient value, resolve into and distinguish layer or different frequency block signals at differently level, and then, using Wavelet shrinkage method by Donoho and Johnstone, to estimating and examining the Wavelet coming out in development of the signal. Choose a suitable critical value, to clipping the high-frequency Wavelet coefficient. And then, using threshold to shrink wavelet coefficient, and clipping out the approximation function and the detail function of underground water level attack by just earthquake. Taking that obviously of this point out groundwater level appear frequency unusual time, therefore will contribute to reducing natural disasters, will lengthen and take refuge and reflect time.
論文目次 目錄

摘 要 i
ABSTRACT ii
誌 謝 iv
目錄 v
表目錄 v
圖目錄 vi
第一章 緒論 1
1.1 研究背景與動機 1
1.2 文獻回顧 1
1.2.1 國內地區地震前後地下水位變化相關研究 2
1.2.2 國外地區地震前後地下水位變化相關研究 5
1.3 研究目標與流程 7
第二章 研究資料背景說明 8
2.1 台灣之地震地體環境構造簡介 8
2.2 研究區域 9
2.3 台南那菝及六甲觀測井資料概述 14
第三章 倒傳遞類神經網路 25
3.1 類神經網路簡介 25
3.2 倒傳遞神經網路 25
3.2.1 倒傳遞網路架構 25
3.2.2 倒傳遞網路原理 26
3.2.3 倒傳遞網路演算法 27
3.2.4 倒傳遞網路參數設定 31
3.2.5 倒傳遞網路演算流程 32
第四章 小波理論 35
4.1 小波理論簡介 35
4.2 傳統訊號分析方法 35
4.2.1 傅利葉分析 35
4.2.2 短時間傅利葉轉換 38
4.3 小波轉換 41
4.3.1 連續小波轉換 41
4.3.2 離散小波轉換 42
4.4 小波轉換多重解析度分析 43
4.4.1 多重解析度分析 43
4.4.2 尺度函數與小波函數 45
4.4.3 Daubechies 的尺度函數與小波函數 48
4.5 小波收縮 50
第五章 地震前地下水位波動變化分析 51
5.1 地下水位之類神經網路模式與應用結果 51
5.1.1 地下水位神經網路模式架構 51
5.1.2 模式應用結果 52
5.2 地下水位之小波多重解析度分析與應用結果 59
第六章 結論與建議 81
6.1 結論 81
6.2 建議 82
參考文獻 83

參考文獻 參考文獻

[1] 文成林、周東華,多尺度估計理論及其應用,清華大學出版社,2002第21-57頁。
[2] 王安濱、黃振義,「水位異常型態及其與地震關係的初步分析」,地震預報與地震工程研究論文集,地震出版社,1992,第16-21頁。
[3] 王瀚德,小波理論與類神經網路應用於潮汐之預測與補遺,碩士論文,國立中山大學海洋環境及工程研究所,2001。
[4] 王政偉,結合小波轉換與類神經網路辨別電力開關之切換,碩士論文,私立中原大學電機工程研究所,2003。
[5] 中央氣象局網站(http://www.cwb.gov.tw/V4/index.htm)。
[6] 中研院地科所網站(http://www.earth.sinica.edu.tw)。
[7] 水文水資源資料管理供應系統(http://gweb.wra.gov.tw/wrweb)。
[8] 臼井支朗,信號分析,科學出版社,1998,第110-130頁。
[9] 余貴坤,「降雨量與深井水位變動的關係研究」,台灣地區地球物理研討會,1986,第165-174頁。
[10] 余貴坤、陳建文,「深井水位變動預地震的關係研究」,中國地質學會年會,台北,1986,第26頁。
[11] 汪成民,地下水位動態異常與地震短臨預報,地震出版社,1993,第173-192頁。
[12] 李民,集集地震前後與其同震水文變化研究,博士論文,國立台灣大學地質科學研究所,2002。
[13] 林進國,降雨和地下水位變化之關聯性分析,碩士論文,國立成功大學水利及海洋工程研究所,2003。
[14] 林穎駿,應用小波轉換與類神經網路於電力品質事故之監測與辨識,碩士論文,私立中原大學電機工程研究所,2003。
[15] 林淑真,「地下水位動態分析及其異常行為之識別」,台北:行政院國家科學委員會專題研究計畫成果報告(計畫編號:NSC90-2211-E-426-003),2002。
[16] 岩村公太,安富觀測井における短周期水位變動と地殼歪みの相關,碩士論文,東京工業技術大學,2002。
[17] 邱靜怡,受動力作用下地層有效應力與地下水位變化之研究,碩士論文,國立成功大學資源工程學系,2004。
[18] 徐維聰,應用小波轉換與類神經網路進行電力系統故障種類之判別,碩士論文,私立中原大學電機工程研究所,2003。
[19] 施清芳、李錦地,「濁水溪臨近海岸地下水水位之頻譜分析」,核研季刊,第三十七期,2000,第79-93頁。
[20] 施清芳,「濁水溪臨近海岸地下水水位之頻譜分析」,核研季刊,第三十六期,2000。
[21] 單維彰,凌波初步,全華科技圖書股份有限公司,1999,第239-278、328-353頁。
[22] 國家地震局科技監測司,地下水分冊-地震監測與預測方法清理匯編,北京:地震出版社,1988。
[23] 國立成功大學防災研究中心,地震發生前後地下水位異常變化之研究(3/5),經濟部水利署委託研究計劃,台北,2003。
[24] 國立成功大學防災研究中心,地震發生前後地下水位異常變化之研究(4/5),經濟部水利署委託研究計劃,台北,2004。
[25] 魚金子、車用太、朱清鐘、谷國珠、劉春國,「北京太平庄井水的超遠強震異常(遠兆)研究」,地震研究,第二十一卷,第一期,1998,第42-49頁。
[26] 張大維、車用太、魚金子,「降雨對湯坑群井水位動態影響的剖析」,地震研究,第十七卷,第三期,1994,第273-280頁。
[27] 張仕印、李于民、陳學庭、楊剛宇,「台灣南投7.6級地震地下流體場異常及其前兆意義」,地震研究,第二十四卷,第三期,2001,第208-211頁。
[28] 陳暐家,地震引致地下水位動態異常之行為解析,碩士論文,立德管理學院資源與環境管理研究所,2003。
[29] 陳冠宇,臺灣西南宅港與三寮灣地層孔隙水地球化學研究,碩士論文,國立台灣大學地質科學研究所,1995。
[30] 陳佳杏,集集地震前後濁水溪沖積扇地下水水位變化之探討,碩士論文,國立台灣大學地質科學研究所,2002。
[31] 董志秋,由同震水文反應估算含水層特性與地質材料性質之研究,碩士論文,國立成功大學資源工程學系,2003。
[32] 黃世偉、林淑真、陳暐家、李宗仰、簡錦樹,「地震之地下水位異常分類及其物理隱意」,中國地質學會九十一年年會暨學術研討會,2002,第200-203頁。
[33] 黃宇璋,含雜訊系統之參數鑑別:離散小波轉換之應用,碩士論文,國立成功大學化學工程研究所,2001。
[34] 經濟部中央地質調查所,「九二一地震地質調查報告」,1999。
[35] 經濟部水利處(今經濟部水利署),「台灣地區地下水通訊」,中華民國八十八年九月號,1999,第38頁。
[36] 經濟部水利署地下水觀測網(http://pc183.hy.ntu.edu.tw)。
[37] 經濟部中央地質調查所全球資訊網站(http://www.moeacgs.gov.tw/main.jsp)。
[38] 賈儀平,「集集地震發生前後地下水位變化」,自然科學簡訊,第十一卷,第四期,1999,第136-138頁。
[39] 賈儀平、王原賢、陳佳杏、吳雪蘋,「集集大地主前後濁水溪沖積扇之地下水位變化」,第四屆地下水資源與水質保護研討會論文集,2001。
[40] 蔡清標、李宗霖,「類神經網路在潮汐預報之應用」,第二十屆海洋工程研討會論文集,1998,第17-22頁。
[41] 楊翰宗,類神經網路應用於光纖雷射與聲波杜卜勒測速儀渠流速度剖面量測之研究,博士論文國立台灣大學生物環境系統工程學研究所,2005。
[42] 劉興華、張嘉仁,時-頻分析在引擎振動診斷上的應用,碩士論文,國立臺北科技大學車輛工程學系,2002。
[43] 謝正倫、林慶偉、顏沛華、詹錢登,「地震發生前後地下水水位異常變化研究整體推動計畫之研訂」,財團法人成大水利海洋研究發展文教基金會,經濟部水資源局MOEA/WRB/ST-900017報告,2001。
[44] 秦前清、楊宗凱,實用小波分析,西安電子科技大學出版社,1994,第55-73、92-95頁。
[45] 虞和濟、陳長征、張省、周建男,基於神經網絡的智能診斷,冶金工業出版社,2000。
[46] 曹鍵滎,小波收縮應用於非安定訊號雜訊濾除之改進,碩士論文,國立台灣海洋大學電機工程研究所,2000。
[47] 應启珩、馮一苡、竇維蓓,離散時間信號分析和處理,清華大學出版社,2001,第1-11、390-414頁。
[48] 羅拎翼、程桂芬,隨機信號與控制基礎,化學工業出版社,2002,第138-189頁。
[49] 鄭欽韓,九二一地震前後地下水水位及含水層應力變化分析,碩士論文,國立成功大學水利及海洋工程研究所,2002。
[50] 饒瑞鈞,「臺灣的地震地體構造」,台灣之活動斷層與地震災害研討會,2002, 第30-48頁。
[51] Brani Vidakovic, Statistical Modeling by Wavelets, New York:John Wiley & Sons, 1999, pp.194-206.
[52] Bodvarsson, G., “Confined Fluids as Strain Meters”, J. Geophys. Res., Vol.75, 1970, pp. 2711-2718.
[53] Blanchard, F.B., and P. Byerly, “A study of a well gauge as a seismograph”, Bulletin of the Seismological Society of America, 25, 1935,pp.313-321.
[54] Caro, R. and Eaglesno, P. S., “Estimating aquifer recharge due to rainfall” , J. Hydrol., 53, 1981, pp.185-211.
[55] C. Sidney Burrus, Ramesh A. Gopinath, and Haitao Guo, Introduction to Wavelets and Wavelet Transforms, New Jersey:Burrus.Gopinath.Guo, 1998, pp.50-72.
[56] Chia, Y. P., Wang, Y. S., Chiu, J. J., and Liu, C. W., “Changes of groundwater level due to the 1999 Chi-Chi Earthquake in the Choshui River alluvial fan in Taiwan” Bull. Seis. Soc.Am., Vol. 91, 2001, pp.1062-1068.
[57] Chen,Bang-Fuh、Chu,Chih-Chun、Wu,Chaoyu,”Neural Network in Hydrological Forecasting and Supplement of Kao-Pin-Chi”, The Fourth International Conference Hydroinformatics ,2000,pp.268.
[58] Cooper, H. H., J. D. Bredehoeft, I. S. Papadopulos and R. R. Bennett, “The Response of Well-Aquifer Systems to Seismic Waves”, Journal of Geophysical Research, Vol. 70, No. 16,1965, pp. 3915-3926.
[59] Grecksch, G., F. Roth, and H. J. Kumpel,”Coseismic well-level changes due to the 1992 Roermond earthquake compared to static deformation of half-space solutions”, Geophys. J. Int. 138, 1999, pp.470-478.
[60] Ishiguro,M., T.Sato, Y.Tamura, and M.Ooe, “Tidal data analysis – An introduction to BAYTAP-G(in Japanese with English abstract)”,Proc.Inst.Math.,32,1984.
[61] Igrashi, G., and Wakita, H., “Tidal responses and earthquake- related changes in the water level of deep wells”, Journal of Geophysical Research, 96, 1991, pp.4269-4278.
[62] Jacob, C. E., “On the flow of water in an elastic artesian aquifer”, Eos Trans.AGU, 21(2), 1940,pp. 574-586.
[63] Joyce Van de vegte 著,侯正信、王國安 等譯,Fundamentals of Digital Signal Processing,電子工業出版社,2003,第525-563頁。
[64] John G. Ackenhusen著,李玉柏、楊采、李征、彭启琮、審校等譯,Real-time Signal Processing Systems,電子工業出版社,2002,第183-201頁。
[65] Kumpel, H. J., “About the potential of wells to reflect stress variations within inhomogeneous crust”, Tectonophysics,211, 1992, pp.317-336.
[66] Koizumi, N., E. Tsukuda, O. Kamigaichi, N. Matsumoto, M. Takahashi,and T. “Sato Preseismic Changes in Groundwater Level and Volumetric Strain Associated with Earthquake Swarms off the East Coast of the Izu Peninsula”, Japan, Geophys. Res. Lett., 26, 1999, pp.3509-3512.
[67] Leonardi, V., F. Arthaud, A. Tovmassian and A. S. Karakhanian ,“Relationships between Seismic Activity and Piezometric Level Changes in the Arax Basin” (SW Armenia) : Attempt at a Typology of Seismically Induced Piezometric Anomalies, Tectonophysics, 273, 1997, pp.293-316.
[68] Matsumoto, N., “Regression analysis for anomalous changes of ground water level due to earthquake”, Geophysical Research Letters, Vol. 19, 1992, pp.1193-1196.
[69] Matsumoto, N., Kitagawa, G., and Roeloffs, E. A., “Hydrological response to earthquake in the Haibara well, central Japan- I. Groundwater level changes revealed using state space decomposition of atmospheric pressure,rainfall and tidal responses”, Geophys. J. Int., 155, 2003, pp.885-898.
[70] Montgomery, D. R., and M. Manga, “Streamflow and water well responses to earthquakes”, Science, 300(27), 2003, pp.2047-2049.
[71] Ohno, M., H. Wakita, and K. Kanjo,”A water well sensitive to seismic wave”, Geophysical Research Letters, Vol. 24, 1997, pp.691-694.
[72] Parker, D.B., 1985. “Learning-logic:Casting the cortex of the human brain in silicon.” Technical Report TR-47, Center for Computational Research in Economics and Management Science, MassachusettsInstitute of Technology, Cambridge, MA.
[73] Roeloffs, E. A., “Hydrologic precursors to earthquake”, A review, Pure Appl. Ceophys., 126,1988,pp.177-209.
[74] Roeloffs, E. A., “Poroelastic techniques in the study of earthquake-related hydrologic phenomena”, in Advances in Geophysics, edited by R. Dmowska, Academic, San Diego, Calif, Vol. 137, 1996, pp.135-195.
[75] Roeloffs, E., and E. Quilty, “Water level and strain changes preceding and following the August 4, 1985 Kettleman Hills, California”, Earthquake, Pure and Applied Geophysics, Vlo. 149, 1997, pp.21-60.
[76] Roeloffs, E. A., “Persistent water level changes in a well near Parkfield, California. Due to local and distant earthquakes”, Journal of Geophysical Research, 103(B1), 1998, pp.869-889.
[77] Rumelhart, D.E., Hinton, G.E., Williams, R.J., 1986. “Learning Internal Representations by Error Propagation. in PARALLEL DISTRIBUTED PROCESSING:Explorations in the Microstructure of Cognition “,Volume 1:Foundations.” MIT Press, Cambridge, MA.
[78] Rojstaczer, S., “Intermediate period response of water levels in wells to crustal strain:Sensitivity and Noise level”, JGR, Vol. 93, No. B11, 1988, pp.13619-13634.
[79] Rojstaczer and Agnew, “The influence of formation material properties on the response of water level in wells to earth tides and atmospheric loading”, JGR, Vol. 94, NO. B9, 1989, pp.12403-12411.
[80] Shih, David C.-F., C.-D. Lee,Chiou, and S.-M., Tsai, “Spectral analysis of tidal fluctuations in ground water level”, Journal of American Water Resources Association, 36(5), 2000, pp.1087-1100.
[81] The Math Works-Wavelet Toolbox(http://www.mathworks.com)。
[82] Venetis, C., “Estimating infiltration and/or the parameters of unconfined aquifers from groundwater level observations”, J. Hydrol., 12, 1971, pp. 161-169.
[83] Viswanathan, M. N., “Recharge characteristics of an unconfined aquifer from the rainfall-water table relationship” ,J. Hydrol., 70, 1984, pp.223-250.
[84] Wakita, H., “Water Wells as Possible Indicators of Tectonic Strain”, Science, Vol.189, 1975,pp. 553-555.
[85] Week, E. P., “Field determination of vertical permeability to air in the unsatured zone”, U. S. Geol. Surv. Prof. Pap., 1051, 1978,pp. 41.
[86] Wright, M., P. Dillon, P. Pavelic, P. Peter, and A. Nefiodovas, “Measurement of 3-D hydraulic conductivity in aquifer cores at in situ effective stresses”, Ground water , 40(5), 2002, pp.509-517.

------------------------------------------------------------------------ 第 4 筆 ---------------------------------------------------------------------
系統識別號 U0006-1007200610125600
論文名稱(中文) 滑鼠觸控板光學瑕疵檢測系統之開發
論文名稱(英文) Development of an Optical Flaw Defection System for Touch Pad
校院名稱 國立台北科技大學
系所名稱(中) 機電整合研究所
系所名稱(英) Graduate Institute of Mechatronic Engineering
學年度 94
學期 2
出版年 95
研究生(中文) 練建良
學號 93408007
學位類別 碩士
語文別 中文
口試日期 2006-07-04
論文頁數 128頁
口試委員 指導教授-吳明川
委員-駱榮欽
委員-蔡明忠
關鍵字(中) 滑鼠觸控板
實數型基因演算法
倒傳遞類神經網路
關鍵字(英) Touch Pad
Real-Valued Genetic Algorithm
Back-Propagation Neural Network
學科別分類 學科別應用科學電機及電子
學科別應用科學機械工程
中文摘要 本研究針對筆記型電腦上的滑鼠觸控板(Touch Pad)的表面瑕疵,利用機器視覺的技術建立一套自動化的檢測系統。在滑鼠觸控板的製造過程中,常常因為機器的油墨塗佈不均、或是在運輸的過程中產生瑕疵。而主要的瑕疵種類包括:尺寸不良、刮痕、油墨汙點與油墨汙漬這四類。而在黑色的滑鼠觸控板中,瑕疵具有低對比性與非均勻性的特質,所以現階段還是以人工方式來作瑕疵判斷,而這樣的方式不僅使得檢測的成本提高,且因為人工檢測的因素,無法達到固定的品質標準。在本文研究中,係針對這些問題,發展一套檢測技術來取代人工檢測,以期達到減少人力資源,提高生產品質、生產效率及降低生產成本。
在研究中所使用的機器視覺技術,主要有影像對比增強,將瑕疵的對比性提高,搭配實數型基因演算法(Real-Valued Genetic Algorithm, GA)找出最佳的對比閥值,利用空間域濾波方式消除雜訊,經由邊界特性的局部臨界法與形態學濾波方式將瑕疵從樣本中清晰的分割出來,再經由倒傳遞類神經網路(Back-Propagation Neural Network)分類出瑕疵種類,本研究使用的影像處理方式,可以將瑕疵部份快速且精確的檢測出來,而最後的總檢測平均時間約為0.19~0.35秒,比用人工檢測需花上3~4秒要快上許多。
英文摘要 This paper develops an automatic inspection system for touch pad of notebook using machine vision. The surface of the touch pad is often unsmooth during painting process and some defects are easily produced in the course of transportation. There are four kinds of main defects including inaccurate size, scratch, spots and stain. As to black touch pad, the features of defects are low contrast of image and not homogeneous. So the inspect factory heavily depend on human vision. Using human vision does not only raise the cost of inspection, but also does not reach the quality standard. In this study, we develop an automatic inspection system to replace human vision and increase the inspection efficiently, the quality of products and the quantity of output.
In this research, image processing such as image contrast enhancement, spatial filter, edge detection, morphology and image classification are used to inspect the defects. In this paper we use Real-Valued Genetic Algorithm (RVGA) to find out the best threshold value of contrast. In the image segmentation, we use edge detection to separate the defects from pad, and uses Back-Propagation Neural Network to recognize kinds of the defects. It is hope for the proposed inspection system can detect the defects quickly and accurately. It is shown that the system only takes 0.19~0.35 seconds for image process in standard of 3~4 seconds by human vision. So the proposed automatic inspection system is better than human vision.
論文目次 目 錄

中文摘要 i
英文摘要 ii
誌謝 iii
目錄 iv
表目錄 vii
圖目錄 viii
第一章 緒論 1
1.1 前言 1
1.2 研究動機與目的 2
1.3 文獻回顧 5
1.4 研究範疇 9
1.5 論文架構 10
第二章 數位影像處理技術 11
2.1影像對比增強處理 11
2.2空間濾波 15
2.2.1 中值濾波 17
2.2.2 均値濾波 18
2.2.3 高通濾波 19
2.3 邊緣檢測 20
2.4 形態學濾波 26
2.5 二値化處理 29
第三章 機器視覺檢測系統 31
3.1 機器視覺系統介紹 31
3.2 光源系統設備說明 34
3.2.1 前照式光源架設方式 35
3.2.2 背照式光源架設方式 38
3.3 滑鼠觸控板檢測的前置工作 42
3.3.1 自動聚焦法則 43
3.3.2 聚焦法則的評估 46
3.3.3 影像與工件尺寸實際對應的比例關係 53
第四章 基因演算法 57
4.1 基因演算法的起源 57
4.2 基因演算法的運作方式 58
4.2.1 染色體的編碼 59
4.2.2 初始族群數 59
4.2.3 適應性函數 59
4.2.4 複製 61
4.2.5 交配 62
4.2.6 突變 62
4.2.7 中止條件 62
4.2.8 實數型基因演算法 63
4.3 搜尋灰階動態範圍 64
4.4 實數型基因演算法搜尋結果 64
第五章 倒傳遞類神經網路 74
5.1 類神經網路介紹 74
5.2 類神經網路架構 75
5.3 倒傳遞類神經網路 77
5.4 倒傳遞類神經網路演算法 78
5.5 改進倒傳遞類神經網路學習 82
5.6 瑕疵特徵值 83
第六章 實驗及討論 86
6.1 檢測程式介面說明 86
6.2 滑鼠觸控面板檢測結果 88
6.3 倒傳遞類神經網路學習結果 95
6.4 檢測時間 101
第七章 結論與未來展望 110
7.1 結論 110
7.2 未來展望 111
參考文獻 112
附錄A:滑鼠觸控板檢測結果 117
參考文獻 [1] 徐章,「台灣AOI發展策略」,2006電子資訊產業年鑒,2006,第69-72頁。
[2] 梁俊傑, DVD與 VCD光碟表面瑕疵檢測系統之開發,碩士論文,國立屏東
科技大學機械工程系,屏東,2001。
[3] K. Nakashima, “Hybrid Inspection System for LCD Color Filter Panels,”
Instrumentation and Measurement Technology Conference, vol.2, 1994,
pp.689-692.
[4] W.S. Kim, D.M. Kwak, Y.C. Song, D.H. Choi, and K.H. Park, “Detection of
Spot-Type Defects on Liquid Crystal Display Modules,” Key Engineering
Materials, 2004, pp.270-273.
[5] 蔡篤銘、林品杰、曾彥馨,「應用獨立成份分析濾波器於背光板與 TFT-LCD
面板之瑕疵檢測」,2005全國 AOI 論壇與展覽研討會論文集,新竹,2005,
第60-71頁。
[6] 陳亮嘉、楊順霖、郭家成,「創新式背景重建演算法應用於 TFT-LCD Mura
瑕疵之自動化檢測技術」,2005全國 AOI 論壇與展覽研討會論文集,新竹,
2005,第156-166頁。
[7] 李淑惠, X-RAY即時影像強化與瑕疵偵測之研究,碩士論文,私立元智大學
工業工程與管理學系,桃園,2000。
[8] R. C. Gonzalez and R. E. Woods, Digital image processing, New
York:Wiley,1992.
[9] J. G. Leu, “Image Contrast Enhancement Based on the Intensities of Edge Pixels,”
Graphical Models and Image Processing, vol. 54, no. 6, 1992, pp. 497-506.
[10] J. Rogowska, K. Preston, and D. Sashin, “Evaluation of Digital Unsharp Masking
113
and Local Contrast Stretching as Applied to Chest Radiographs,” IEEE
Transactions on Biomedical Engineering, vol.35, no.10, 1988, pp.817-827.
[11] 連國珍,數位影像處理,台北:儒林圖書公司,2004,第4-12頁。
[12] 廖克東,應用機器視覺於低對比動態 X-Ray影像強化及瑕疵偵測之研究,碩
士論文,元智大學工業工程與管理學系,桃園,2001。
[13] 黃泰祥,具備人臉追蹤及辨識功能的一個數位型監視系統,碩士論文,中原
大學電子工程學系,桃園,2004。
[14] 鍾瑞賢,應用機器視覺與類神經網路於電機零組件品質之自動檢測-以S鐵心
為例,碩士論文,元智大學工業工程研究所,桃園,1999。
[15] 蔡典霖,應用機械視覺於印刷電路板表面元件之檢測,碩士論文,國立清華
大學動力機械工程研究所,新竹,2004。
[16] 鄭光宏,應用影像視覺於超薄型表面載式電感器之線上自動檢測,碩士論文,
大葉大學機電自動化研究所,彰化,2004。
[17] 林東賦,應用影像處理技術與類神經網路理論於非織物瑕疵辨識,碩士論文,
國立台灣科技大學纖維及高分子工程技術研究所,台北,2001。
[18] 李冠岳,乳房 X光影像中基於馬可夫隨機場係數對微鈣化組織的辨識,碩士
論文,國立中正大學電機工程研究所,嘉義,2004。
[19] M. Martorella, F. Berizzi and S. Bruscoli, “Use of Genetic Algorithms for ISAR
Image Autofocusing,” Radar Conference,2004. Proceedings of the IEEE, 2004,
pp.201-206.
[20] N. K. Chern, P. A. Neow, H. Marcelo and J. Ang , “Practical Issues in Pixel-Based
Autofocusing for Machine Vision,” Proceedings of the 2001 IEEE International
Conference on Robotics & Automation Seoul, Korea, 2001, pp. 21-26.
[21] 潘嘉偉,變焦測深技術的應用,碩士論文,國立中山大學機械工程學系研究
所,高雄,2000。
114
[22] 吳上立、林宏墩編譯, C語言數位影像處理,台北:全華科技,2005。
[23] 陳兵旗、孫明,Visual C++ 實用圖像處理,北京:清華大學出版社,2004。
[24] 繆紹綱譯,數位影像處理,台北:普林斯頓國際有限公司,2004。
[25] 余松煜、周源華、吳時光,數位影像處理,台北:格致圖書,1993。
[26] R. Jain, R. Kasturi and B.G. Schunck, Machine Vision, Mcgraw-Hill international
edition, 1995.
[27] I. E. Sobel, Camera Models and Machine Perception, Ph.D. Thesis, Stanford
University, California, 1970.
[28] N. Otsu, “A Threshold Selection Method from Gray-Level Histograms,” IEEE
Transaction on System, vol.9, no.1, 1979, pp.62-66.
[29] 位元文化,Visual C++(從C++、物件導向到視窗程式設計),台北:文魁,2003。
[30] 蔡孟凱、雷穎傑、黃昭維、陳錦輝、陳正凱,C++ Builder6 完全攻略,台北:
金禾資訊,2004。
[31] 黃文吉,C++ Builder與影像處理,台北:儒林圖書公司,2003。
[32] 泰洛科技股份有限公司,「增進視覺系統辨識之光源選擇與技巧」,機電整
合雜誌,2000,第99-104頁。
[33] 黃世良,循邊式影像量測之研究,碩士論文,國立台北科技大學機電整合科
技研究所,台北,2004。
[34] 陳時新,實戰機器視覺,台北:電子技術出版社,1997。
[35] J. E. Schlag, A. C. Sanderson, C. P. Neumann, and E. C. Wimberly,
“Implementation of Automatic Focusing Algorithms for a Computer Vision
System with Camera Control,” Technical Report CMU-RI-TR-83- 14, Carnegie
Mellon University, August, 1983.
[36] 陳亮嘉,自動化光學檢測,教學講義,國立台北科技大學自動化科技研究所,
台北,2004。
115
[37] K.S. Choi, J.S. Lee and S. L. Ko, “New Autofocusing Technique Using the
Frequency Selective Weighted Median Filter for Video Cameras,” Consumer
Electronics, IEEE Transactions on, vol.45, 1999, pp.820-827.
[38] M. Subbarao and J. Tyan, “Selecting the Optimal Focus Measure for Autofocusing
and Depth-From-Focus,“ Pattern Analysis and Machine Intelligence, IEEE
Transactions on, vol.20, 1998,pp.864-870.
[39] J. John, Genetic Algorithms for Machine Learing, Boston : Kluwer Academic
Publishers, 1994.
[40] K. F. Man, K. S. Tang, S. Kwong, Genetic Algorithms:Concepts and Designs, New
York : Springer , 1999.
[41] 蕭俊祥,智慧型控制,教學講義,國立台北科技大學機電整合研究所,台北,
2004。
[42] R. F. Fung, C. H. Yang, S. C. Hsien and J. L. Ha, “Identification of the
Piezoelectric Actuator with Hysteresis Based on Real-Coded Genetic Algorithm,”
2004 Automation Technology Conference, 2004, pp.210-216.
[43] J. W. Kim, S. W. Kim, P. G. Park, and T. J. Park, “On the Similarities between
Binary-Coded GA and Real-Coded GA in Wide Search Space,” IEEE Evolutionary
Computation. Proceedings of the 2002 Congress on, 2002, pp.681-686.
[44] S. Bing, A. Nabout and H. A. Eldin, “Measurement of Ring-Shaped and Toothed
Mechanical Parts through Image Processing,” IEEE. Proceedings. Integrating
Intelligent Instrumentation and Control, 1995, pp.396-401.
[45] R. J. Chen and J. L. Lai, “Novel Approach and System for Automatic PCB Visual
Inspection Using Hybrid Flaw Detection,” Journal of National Llen-Ho Institure of
Technology , vol.17, 2000, pp.175-183.
[46] C. H. Hsieh, Y. W. Huang and M. J. Wu, “Automatic Concentricity Measurement
116
by Image Processing,” IEEE. Instrumentation and Measuremetn Technology
Conference, 1994, pp.853-857.
[47] 王進德、蕭大全編著,類神經網路與模糊控制理論入門,台北:全華科技,
1994。
[48] Ning-Feng Zeng, Keiji Taniguchi and Hiroshi Yamamoto, “Evaluating the Quality
of Pellet Component by Using Image Processing Technique with Neural
Networks,” Proceedings. 2000 International Conference on, 2000, pp.340-343.
[49] 林昇甫、洪成安,神經網路入門與圖樣辨識,台北:全華科技圖書,1993。
[50] 張宏林,數字圖像模式識別技術及工程實踐,上海:人民郵電出版社,2003。
[51] A.S. Pandya and R.B. Macy, Pattern Recognition with Neural Networks in C++,
Florida: Florida Atlantic University, 1996.

------------------------------------------------------------------------ 第 5 筆 ---------------------------------------------------------------------
系統識別號 U0006-1708200617093600
論文名稱(中文) 無線區域網路環境下定位技術之效能分析
論文名稱(英文) Performance Comparison of WLAN-based Positioning Techniques
校院名稱 國立台北科技大學
系所名稱(中) 電機工程系所
系所名稱(英) Department of Electronic Engineering
學年度 94
學期 2
出版年 95
研究生(中文) 廖仁誠
學號 92318513
學位類別 碩士
語文別 中文
口試日期 2006-07-27
論文頁數 65頁
口試委員 委員-周俊賢
委員-黃紹華
委員-徐演政
指導教授-譚旦旭
關鍵字(中) 802.11b
802.11g
室內定位
無線區域網路
WLAN
關鍵字(英) 802.11b
802.11g
indoor positioning
wireless local area network (WLAN)
學科別分類 學科別應用科學電機及電子
中文摘要 本研究利用802.11g及802.11b規格之無線網卡,在室內環境比較多種定位技術之優劣,採用的定位方法包括NNSS, KNN, 重心法,Curve Fitting, Wiener Filtering等,我們探討了AP數目及連線速率對定位準確度之影響。
實驗結果顯示,3個AP的定位結果優於2個AP。另外,在大部分情況下,802.11b的定位表現優於802.11g。整體而言,以802.11b的連線速率加上KNN定位法可獲得最好的定位效果。
英文摘要 This study compares the accuracy of various positioning techniques including NNSS, KNN, center of gravity, curve fitting, and Wiener filtering via indoor measurement by applying 802.11b and 802.11g wireless cards. The effects of number of access point (AP) and link rates on positioning accuracy are also investigated. Experimental results indicate that the accuracy of 3 sets of AP is better than that of 2 sets of AP, and the accuracy of 802.11b is better than that of the 802.11g in most cases. Finally, it is found that the KNN approach with 802.11b is among the best choice for indoor positioning.
論文目次 目 錄

中文摘要 i
英文摘要 ii
誌謝 iii
目錄 iv
表目錄 vii
圖目錄 viii
第一章 緒論 1
1.1 研究動機與目的 1
1.2 研究方法 2
1.3 各章節內容摘要 3
第二章 無線相關技術 4
2.1 802.11x 4
2.2 Bluetooth 11
2.3 RFID 12
2.3.1 RFID原理介紹 12
2.3.2 RFID的頻率使用範圍 15
第三章 定位方法介紹 16
3.1 網路端定位 16
3.1.1 抵達時間(Time of Arrival, TOA) 16
3.1.2 收訊時間差(Time Difference of Arrival, TDOA) 18
3.1.3 收訊角度(Angle of Arrival, AOA) 19
3.2 用戶端定位 19
3.2.1 全球定位系統(Global Positioning System, GPS) 20
3.2.2 訊號強度法(Received Signal Strength, RSS) 21
3.3 RADAR System(Radio Detection and Ranging, RADAR) 22
第四章 實驗架構與方法 25
4.1 實驗環境與軟硬體工具 25
4.1.1 實驗環境 25
4.1.2 硬體設備 26
4.1.3 實驗平台及量測程式 27
4.1.4 相關設定 27
4.2 資料收集 28
4.3 定位演算法 29
4.3.1 NNSS 29
4.3.2 KNN 30
4.3.3 重心法 31
4.3.4 曲線匹配(Curve Fitting) 31
4.3.5 維納濾波器(Wiener Filter) 33
4.4 AP數目對定位準確度之影響 35
第五章 定位實驗結果與效能比較 36
5.1 實驗一 NNSS定位法 36
5.2 實驗二 KNN定位法 37
5.3 實驗三 重心定位法 37
5.4 實驗四 Curve Fitting 38
5.5 實驗五 Wiener Filtering 42
5.6 實驗六 802.11b與802.11g定位效能比較 42
5.7 移動誤差 46
5.8 實驗比較 52
5.9 討論 54
第六章 結論與未來展望 56
參考文獻 57
附錄一 PCI BLW-54PM產品規格表 59
附錄二 3Com無線網卡規格表 62
附錄三 Cisco無線網卡規格表 63



















表目錄

表2.1 802.11a頻道使用表 7
表2.2 802.11a所採用之調變技術 7
表2.3 802.11x之比較 8
表2.4 802.11 b/g 頻道使用表 10
表2.5 主動式與被動式電子標籤之比較 13
表2.6 不同寫入程度電子標籤之比較 14
表4.1 硬體設備表 26
表4.2 AP設定值 28
表4.3 訊號強度資料庫格式 28
表5.1 定位準確度比較表 47













圖目錄

圖2.1 IEEE 802.11協定層 5
圖2.2 Ad-Hoc mode連線示意圖 6
圖2.3 Infrastructure mode 連線示意圖 6
圖2.4 基本的射頻識別之系統架構 13
圖2.5 RFID系統架構圖 15
圖3.1 TOA定位法 17
圖3.2 非直視線傳播時定位可能出現之區域 18
圖3.3 TDOA定位法 19
圖3.4 GPS定位示意圖 21
圖3.5 Multiple Nearest Neighbors示意圖 23
圖3.6 K值與定位誤差之關係 23
圖4.1 實驗現場 25
圖4.2 實驗現場平面圖 26
圖4.3 NetStumbler操作畫面 27
圖4.4 實驗畫面 29
圖4.5 程式執行畫面 30
圖4.6 AP1距離與訊號強度關係圖 32
圖4.7 Wiener Filter示意圖 33
圖5.1 NNSS定位法之誤差分佈 37
圖5.2 KNN定位法之誤差分佈 38
圖5.3 重心定位法之誤差分佈 39
圖5.4 AP1與無線網卡之間的距離和訊號強度關係圖 40
圖5.5 AP2與無線網卡之間的距離和訊號強度關係圖 ...40
圖5.6 AP3與無線網卡之間的距離和訊號強度關係圖 41
圖5.7 Curve Fitting定位法之誤差分佈 41
圖5.8 Wiener Filtering定位法之誤差分佈 42
圖5.9 802.11b/g訊號強度比較 43
圖5.10 802.11b/g於NNSS定位法之誤差分佈 44
圖5.11 802.11b/g於KNN定位法之誤差分佈 44
圖5.12 802.11b/g於重心法之誤差分佈 45
圖5.13 802.11b/g於Curve Fitting定位法之誤差分佈 45
圖5.14 以802.11b沿AP1直線移動之定位誤差 46
圖5.15 以802.11g沿AP1直線移動之定位誤差 47
圖5.16 以802.11b沿AP2直線移動之定位誤差 48
圖5.17 以802.11g沿AP2直線移動之定位誤差 49
圖5.18 以802.11b沿AP3直線移動之定位誤差 50
圖5.19 以802.11g沿AP3直線移動之定位誤差 51
圖5.20 使用2個AP定位之效能比較 52
圖5.21 使用3個AP定位之效能比較 53
圖5.22 AP1於每個測量點之RSSI標準差 54
圖5.23 AP2於每個測量點之RSSI標準差 55
圖5.24 AP3於每個測量點之RSSI標準差 55
參考文獻 參考文獻

[1] 周駿呈,Wi-Fi定位服務新應用,新竹:工研院產經中心,2006。
[2] P. Bahl and V. N. Padmanabhan, “RADAR: An RF-Based In-Building User Location and Tracking System,” in Proc. of IEEE Computer and Communications Societies, pp. 775-784, 2000.
[3] 陳革安,考量最佳化存取點配置方法的室內無線區域網路定位系統,碩士論文,2005。
[4] 柯文力,改善無線區域網路室內定位精度之研究,碩士論文,國立高雄第一科技大學電腦與通訊工程研究所,2005。
[5] http://www.netstumbler.com
[6] 陳榮銘,大都會無線寬頻整體服務規劃報告,桃園:中華電信研究所,2004。
[7] 顏春煌,802.11無線區域網路理論與實務,台北:旗標出版股份有限公司, 2004。
[8] 簡永懿,IEEE 802.11n 技術提案摘之研究-PHY Layer Frame Format,新竹:工研院電通所,2005。
[9] 禹凡,無線藍芽技術的深入探討,台北:文魁圖書公司,2001。
[10] 林傑斌、秦美惠、羅傑克,WLAN&行動通訊網路,台北:文魁圖書公司,2003。
[11] http://bluetooth.com
[12] 2004年第一屆博物館資訊管理學術暨實務研討會論文集。
[13] 電子設計資源網http://www.eedesign.com.tw/
[14] 鄭嘉元,無線區域網路室內定位系統,碩士論文,義守大學機械與自動化工程研究所,2005。
[15] 鄭力強,無線區域網路之室內定位機制研究,碩士論文,銘傳大學資訊工程研究所,2005。
[16] 蔡彥名,室內無線定位方法之開發與驗證,碩士論文,國立交通大學電信工程研究所,2004。
[17] http://www.ttsh.tp.edu.tw/~c024/gardeng3.htm
[18] http://www.geog.ntu.edu.tw/research/六大軸線/空間資訊/衛星定位及遙測 /index.htm
[19] 章俊彥,階層式室內定位系統與其服務,碩士論文,國立中央大學資訊工程研究所,2004。。
[20] C. L. Wang, Y. S. Chiou and S. C. Yeh, “An Indoor Location Scheme Based on Wireless Local Area Networks,” in Proc. of IEEE Consumer Communications and Networking, pp. 602-604, 2005.
[21] 游舒偉,無線區域網路室內定位之研究,碩士論文,國立台灣科技大學機械工程研究所,2003。

------------------------------------------------------------------------ 第 6 筆 ---------------------------------------------------------------------
系統識別號 U0006-2007200611552400
論文名稱(中文) 切換式磁阻馬達智慧型間接轉矩控制驅動系統之研製
論文名稱(英文) Study and Implementation of Intelligence Indirect Torque Control Drive System for Switched Reluctance Motor
校院名稱 國立台北科技大學
系所名稱(中) 電機工程系所
系所名稱(英) Department of Electronic Engineering
學年度 94
學期 2
出版年 95
研究生(中文) 簡劭全
學號 93318030
學位類別 碩士
語文別 中文
口試日期 2006-07-14
論文頁數 135頁
口試委員 指導教授-王順源
委員-洪欽銘
委員-曾傳蘆
關鍵字(中) 類神經網路
小腦模型控制器
灰色預測理論
切換式磁阻馬達
關鍵字(英) Artificial Neural Network
Cerebellar Model Articulation Controller
Grey Prediction Theory
Switched Reluctance Motor
學科別分類 學科別應用科學電機及電子
中文摘要 本論文利用智慧型控制理論設計控制器,並透過轉矩分配之策略,建立切換式磁阻馬達智慧型間接轉矩控制驅動系統,所提出的控制策略使系統響應具有高性能的表現。切換式磁阻馬達具有高轉矩、高效率、無轉子繞組以及成本低廉等優點,然而,其定、轉子雙凸極式的結構設計,導致輸出轉矩具有高度非線性特性,因此增加控制器設計之困難度。本研究利用類神經網路以及小腦模型控制器優異的非線性適應能力,並結合適應性控制理論之投影演算法(projection algorithm) ,與灰色預測理論來設計控制器。所設計之控制器架構皆具線上即時調適PI參數的能力,充分彌補傳統固定參數PI控制器的缺點,有效提升系統的動態特性。
為了驗證所設計控制器之性能及可行性,本研究利用dSPACE-DS1104訊號處理平台來實現所提出的控制策略。經由實驗結果證明,本研究所提出之控制策略確實有效提升系統之動態響應。
英文摘要 This thesis adopts intelligent control technique to design the controller and using the torque sharing strategy to implement the intelligent indirect torque control drive system for switched reluctance motors (SRMs). The proposed control scheme can improve system response. The merits of SRMs include high torque, high efficiency, no rotor windings, and low cost. However, the structure of salient poles on both the rotor and the stator brings about high nonlinearity of the output torque and makes SRM difficult to control. Since both the Neural Network (NN) technique and the Cerebellar Model Articulation Controller (CMAC) provide a good capability to deal with nonlinear characteristics, we propose a NN-based and a CMAC-based controller respectively with the grey prediction theory and the projection algorithm used in the adaptive control theory. The proposed controller structure can on-line adjust PI parameters to make the dynamic behavior of the proposed system superior to that of the system using the conventional fix-parameter PI controller.
To verify the feasibility and practicality of the controller, a dSPACE-DS1104 platform is used to implement the proposed control scheme. From the experimental results, it is seen that the dynamic performance of the SRM driver system is improved by the proposed scheme.
論文目次 中文摘要 i
英文摘要 ii
誌 謝 iv
目 錄 v
表目錄 ix
圖目錄 x
第一章 緒論 1
1.1 研究動機 1
1.2 切換式磁阻馬達研究近況 2
1.3 研究目的 3
1.4 大綱 4
第二章 切換式磁阻馬達 5
2.1 前言 5
2.2 切換式磁阻馬達結構與特性 5
2.3 切換式磁阻馬達數學模式 7
2.3.1 電壓方程式 8
2.3.2 轉矩方程式 10
2.4 切換式磁阻馬達運轉驅動原理 11
2.4.1 轉矩產生原理 11
2.4.2 驅動原理 12
2.4.3 轉換器電路分析 16
2.5 參數量測 19
2.6 結語 22
第三章 灰色系統理論 23
3.1 前言 23
3.2 灰色系統理論簡介 24
3.3 灰色預測模型 25
3.4 內涵型灰色預測模型 28
3.5 灰色決策導論 31
3.5.1 灰色決策定義 31
3.5.2 灰色多目標局勢決策實例 33
3.6 結語 36
第四章 類神經網路理論 37
4.1 前言 37
4.2 類神經網路技術 37
4.2.1 類神經網路處理單元 39
4.2.2 類神經網路系統架構 41
4.3 小腦模型控制器 44
4.3.1 小腦模型控制器之動作原理 45
4.3.2 小腦模型控制器之參數影響模擬 51
4.3.3 小腦模型控制器之加速法 59
4.4 結語 63
第五章 智慧型控制器設計與系統模擬 64
5.1 前言 64
5.2 植基於投影演算法之類神經控制器設計 64
5.2.1 投影演算法 65
5.2.2 投影演算法植入類神經網路控制器架構 66
5.3 植基於投影演算法之小腦模型控制器設計 68
5.3.1 投影演算法植入小腦模型控制器架構 69
5.4 內涵型灰決策預測模型設計 71
5.4.1 灰色決策動態步距設計 72
5.4.2 內涵型灰色決策預測模型 76
5.5 切換式磁阻馬達模擬系統 77
5.5.1 速度控制器設計 78
5.5.2 轉矩控制器設計 79
5.5.3 電壓脈波寬度調變與轉換器 83
5.6 模擬結果 84
5.7 結語 91
第六章 切換式磁阻馬達控制系統實驗 92
6.1 前言 92
6.2 功率級轉換器與驅動電路 93
6.3 電流量測與過電流保護電路 94
6.4 實驗結果與分析 95
6.5 結語 124
第七章 結論與建議 125
7.1 結論 125
7.2 建議 125
參考文獻 127
符號彙編 130
附錄A:馬達規格 132
附錄B:電感模型傅立葉級數係數 133
附錄C:實驗設備照片 134
作者簡介 135

參考文獻 [1] W. Cai and P. Pillay, "Resonant frequencies and mode shapes of switched reluctance motors," IEEE Transactions on Energy Conversion, vol. 16, no. 1, 2001, pp. 43-48.
[2] K. M. Rahman and S. E. Schulz, "Design of high-efficiency and high torque density switched reluctance motor for vehicle propulsion," IEEE Transactions on Industry Applications, vol. 38, no. 6, 2002, pp. 1500-1507.
[3] S. Brisset and P. Brochet, "Optimization of switched reluctance motors using deterministic methods with static and dynamic finite element simulations," IEEE Transactions on Magnetics, vol. 34, no. 5, 1998, pp. 2853-2856.
[4] M. Barnes and C. Pollock, "Power electronic converters for switched reluctance drives," IEEE Transactions on Power Electronics, vol. 13, no. 6, 1998, pp. 1100-1111.
[5] V. Vujicic and S. N. Vukosavic, "A simple nonlinear model of the switched reluctance motor," IEEE Transactions on Energy Conversions, vol. 15, no. 4, 2000, pp. 395-400.
[6] T. Lachman, T. R. Mohamad and C. H. Fong, "Nonlinear modelling of switched reluctance motors using artificial intelligence techniques," IEE Proceedings of the Electric Power Applications, vol. 151, no. 1, 2004, pp. 53-60.
[7] B. Fahimi, A. Emadi and Jr. B. Sepe, "Position sensorless control," IEEE Industry Applications Magazine, vol. 10, 2004, pp. 40-47.
[8] T. H. Liu and C. G. Chen, "Implementation of a sensorless switched reluctance drive with self-inductance estimating technique," IEEE 2002 28th Annual Conference of the Industrial Electronics Society, vol. 1, 5-8 Nov. 2002, pp. 508-513.
[9] T. Wakasa, H. J. Guo and O. Ichinokura, "A simple position sensorless driving system of SRM based on new digital PLL technique," IEEE 2002 28th Annual Conference of the Industrial Electronics Society, vol. 1, 5-8 Nov. 2002, pp. 502-507.
[10] C. G. Chen and T. H. Liu, "Nonlinear controller design for switched reluctance drive systems," IEEE Transactions on Aerospace and Electronic Systems, vol. 39, no. 4, 2003, pp. 1429-1440.
[11] Y. Yang and Y. Zhang, "Sliding mode-PI control of switched reluctance motor drives for EV," IEEE 8th International Conference on Electrical Machines and Systems, vol. 1, 27-29 Sept. 2005, pp. 603-607.
[12] C. Mademlis and I. Kioskeridis, "Performance optimization in switched reluctance motor drives with online commutation angle control," IEEE Transactions on Energy Conversion, vol. 18, no. 3, 2003, pp. 448-457.
[13] L. A. Zadeh, "Fuzzy set," Information and Control, vol. 8, 1965, pp. 338-353.
[14] C. M. Hong, C. T. Chiang and S. C. Lin, "Design of grey prediction controller based on fuzzy reasoning," The 2nd National Conference on Fuzzy Theory and Application (Fuzzy ’94), 1994, pp. 405-410.
[15] J. L. Deng, "Introduction to grey system theory," The Journal of Grey System, 1998, pp. 1-24.
[16] 吳漢雄、鄧聚龍、溫坤禮,灰色分析入門,台北:高立圖書股份有限公司,1996。
[17] 翁慶昌、陳嘉欉、賴宏仁,灰色系統基本方法及其應用,台北:高立圖書有限公司,2001。
[18] T. Hayakawa, W. M. Haddad, N. Hovakimyan and V. Chellaboina, "Neural network adaptive control for nonlinear nonnegative dynamical systems," IEEE Transactions on Neural Networks, vol. 16, no. 2, 2005, pp. 399-413.
[19] 張斐章、張麗秋、黃浩倫,類神經網路理論與實務,台北:東華書局,2003。
[20] C. M. Lin and Y. F. Peng, "Adaptive CMAC-based supervisory control for uncertain nonlinear systems," IEEE Transactions on System, Man, and Cybernetics-part B, vol. 34, no. 2, 2004, pp. 1248-1260.
[21] P. E. M. Almeida and M. G. Simões, "Parametric CMAC networks: Fundamentals and applications of a fast convergence neural structure," IEEE Transactions on Industry Applications, vol. 39, no. 5, 2003, pp. 1551-1557.
[22] Z. Q. Wang, J. L. Schiano and M. Ginsberg, "Hash-Coding in CMAC neural networks," IEEE International Conference on Neural Networks, vol. 3, 3-6 Jun. 1996, pp. 1698-1703.
[23] S. F. Su, T. Tao and T. H. Hung, "Credit Assigned CMAC and its application to online learning robust controllers," IEEE Transactions on System, Man, and Cybernetics-part B, vol. 33, no. 2, 2003, pp. 202-213.
[24] G. C. Goodwin and K. S. Sin, Adaptive Filtering Prediction and Control, Englewood Cliffs: Prentice-Hall, 1984.
[25] S. K. Sahoo, S. K. Panda and J. X. Xu, "Indirect torque control of switched reluctance motors using iterative learning control," IEEE Transactions on Power Electronics, vol. 20, no. 1, 2005, pp. 200-208.
[26] Y. S. Lai and J. C. Lin, “New hybrid fuzzy controller for direct torque control induction motor drives,” IEEE Transactions on Power Electronics, vol. 18, 2003, pp. 1211-1219.

 


客服專線 0800-000747 886-2-82215585  客服傳真 886-2-82215586
華藝數位股份有限公司 版權所有 ©2006 All Rights Reserved