臺灣博碩士論文加值系統

目前常見的導航系統有航位推算（DR）系統、慣性導航系統（INS）、全球定位系統（GPS）、羅蘭C系統等幾種；而不論哪一種導航系統都同時存在優點與缺點，若要單獨使用於特定的導航任務，必定要在技術上及成本上付出相當的代價；而整合式導航系統即為結合不同之導航系統，取長補短，使得整體系統性能加以提升，超越單一導航系統之性能；最常用之結合技術為採用卡爾曼濾波器，將各單獨之導航系統加以整合。當然，導航系統最要求的性能仍為準確性，因此如何將準確性加以提升即為一重要之課題。
適應性網路模糊推論系統（ANFIS）結合了模糊推論系統與類神經網路兩種智慧型演算法的特性，因此其不但可充分應用於具有不確定性之系統，更同時具有自我學習及組織的能力；而本論文即藉由ANFIS之特性以輔助採用（1）鬆弛耦聯前饋式（2）鬆弛耦聯反饋式（3）緊密耦聯前饋式（4）緊密耦聯反饋式，等四種不同整合方式之DR/GPS整合式導航系統中的系統整合卡爾曼濾波器，提供定位誤差補償以提升整個系統的定位準確性。

In the present common navigation systems, such as Dead-Reckoning（DR）system, Inertial Navigation System（INS）, Global Positioning System（GPS）, Loran-C system ,etc. ; No matter what, there are advantage and shortcoming at the same time in any navigation systems .If should use it in the specific navigation task alone, must pay the suitable cost technically and on the cost ; And the Integrated Navigation Systems learn from other's strong points to offset one's weaknesses in order to combine different navigation systems , make whole systematic performance improve , surmount the performance of the single navigation system ; The most frequently used combination technology is to adopt Kalman filter. Then, the each single navigation system will be combined by it. Certainly, the performance that the navigation system requires most is still accuracy, So, How to improve accuracy is an important subject to all of us.
Adaptive Network-Based Fuzzy Inference System (ANFIS ) has combined fuzzy inference system and neural network two kinds of intelligent algorithm, so it can be apply to uncertainly system fully. Even more, it have self- study and ability of the organization at the same time; This thesis is base on the characteristic of ANFIS in order to assist with Kalman filter in the DR/GPS integrated navigation system, offer the error compensation to raise the accuracy of the whole system.That system uses the following four different merger ways ：(1) Loosely-coupled with feedforward type (2) Loosely-coupled with feedback type (3) Tightly-coupled with feedforward type (4) Tightly-coupled with feedback type.

中文摘要..................................................II
英文摘要.................................................III
目錄.......................................................V
圖目錄....................................................IX
表目錄...................................................XVI

第一章 緒論
1-1前言..................................................001
1-2研究動機與方法........................................002
1-3文獻回顧..............................................003
1-4論文架構..............................................004

第二章 整合式導航系統
2-1整合式導航系統概述....................................005
2-1.1鬆弛耦聯式整合導航系統..............................006
2-1.2緊密耦聯式整合導航系統..............................008
2-2 定位原理.............................................010
2-2.1 DR系統定位原理...................................011
2-2.2 GPS系統定位原理....................................012
2-2.3 GPS定位演算法......................................013
2-3最佳估測理論..........................................016
2-3.1最小平方法（Least-Square Method）...................016
2-3.2卡爾曼濾波器（Kalman Filter,KF）....................017
2-3.2.1離散型卡爾曼濾波器................................018
2-3.2.2非線性卡爾曼濾波器................................021

第三章 模糊化類神經網路
3-1類神經網路特性與類神經元模型..........................028
3-2類神經網路學習策略與架構..............................031
3-3模糊集合..............................................034
3-3.1模糊集合..........................................034
3-3.2歸屬函數..........................................035
3-3.3廣義模糊運算子......................................038
3-4 模糊關係與推論.......................................039
3-4.1 模糊關係.........................................040
3-4.2 合成運算...........................................040
3-4.3 模糊規則.........................................041
3-4.4 模糊推論...........................................043
3-5 模糊系統之架構.......................................046
3-5.1 模糊化機構.........................................047
3-5.2 模糊規則庫.........................................048
3-5.3 模糊推論引擎.......................................050
3-5.4 去模糊化機構.......................................051
3-6 模糊化類神經網路.....................................054
3-6.1 適應性網路模糊推論系統（ANFIS）....................054

第四章 ANFIS應用於整合式導航系統之誤差補償
4-1系統狀態與卡爾曼濾波器之狀態函數關係..................058
4-2 ANFIS輔助整合式導航系統之架構........................061
4-3 ANFIS輔助卡爾曼濾波器之參數設定....................065

第五章 模擬結果
5-1 模擬條件.............................................087
5-2 模擬結果與測試.......................................094
5-2.1 ANFIS輔助鬆弛偶聯前饋式DR/GPS整合式導航系統....094
5-2.2 ANFIS輔助鬆弛偶聯反饋式DR/GPS整合式導航系統........102
5-2.3 ANFIS輔助緊密偶聯前饋式DR/GPS整合式導航系統........109
5-2.4 ANFIS輔助緊密偶聯反饋式DR/GPS整合式導航系統........117

第六章 結論分析與展望....................................128

參考文獻.................................................131

【1】張斐章、張麗秋、黃浩倫，類神經網路理論與實務，東華書 局，2003。
【2】Edward J. Krakiwsky, Clyde B. Harris, and Richard V.C. Wong.
”A KALMAN FILTER FOR INTEGRATING DEAD RECKONING.MAP MATCHING AND GPS POSITIONING,”
CH2675-7/88/0000-00369 IEEE,pp39-46,1988.
【3】SAN-TONG ZHANG,XUE-YE WEI.”FUZZY ADAPTIVE
KALMAN FILTERING FOR DR/GPS,” 0-7803-7865-2 IEEE,pp2634-2637,2003.
【4】莊智清、黃國興，電子導航，全華科技圖書股份有限公司，2001。
【5】秦永元、张洪钺、汪淑华，卡尔曼滤波与组合导航原理，西北
工业大学出版社，2004
【6】楊中舜，”卡爾曼濾波器之應用：GPS定位精確度之改善”，國
立台灣海洋大學電機工學程系碩士論文，1997
【7】R.G. Brown and P. Y. C. Hwang,” Introduction to random signals
and applied Kalman filtering, ”3rd end, New York, 1997.
【8】付梦印、邓志红、张继传，kalman滤波理论及其在导航系统中
的应用，科学出版社，2003
【9】S. Haykin.”Neural networks: A Comprehensive Foundation,”
Prentice Hal Internaitonal.Inc. 1994.


【10】蘇木春、張孝德，機器學習：類神經網路、模糊系統以及基因演算法則，全華科技圖書股份有限公司，2001。
【11】K. Takaba, Y. Iiguni, and H. Tokumaru, “An Improved Tracking
Kalman Filter Using a Multilayered Neural Network,” Mathl. Comput. Modelling vol. 23, No.1/2, pp.119-128, 1996.
【12】J. L. Elmam, ”Distributed Representations, Simple Recurrent
Networks, and Grammatical Structure,”Machine Learning, vol.7,
【13】E. H. Mamdani and S. Assilian,“An experiment in linguistic sythesis with a fuzzy logic controller,”Int. Journal of Man-Machine Studies, Vol.7,No.1,pp. 1-13,1975.
【14】T. Takagi and M. Sugeno,“Fuzzy identification of systems and its applications to modeling and control,”IEEE Trans. On Systems, Man, and Cybernetics, Vol.15, No.1, pp. 116-132,1985.
【15】M. Sugeno and G. T. Kang,“Structure identification of fuzzy model,”Fuzzy Sets and Systems, Vol. 28,pp. 15-33, 1985.
【16】Y. Tsukamoto,“An approach to fuzzy reasoning,”in Madan M. Gupta,Rammohaw K. Ragade, and Ronald R. Yager, editors, Advances in fuzzy set theory and applications, pp. 137-149, North-Holland, Ameterdam, 1979.
【17】L. A. Zadeh, “Outline of new approach to the analysis of complex systems and decision processes,”IEEE Trans. On Systems, Man, and Cybernetics, SMC-1, pp. 28-44, 1973.

【18】A Kaufmann, Introduction to the Theory of Fuzzy Subsets, New York : Academic Press, 1975.
【19】M. Mizumoto,“Fuzzy sets and their operations,”Int. Control, Vol. 48, pp.30-48, 1981.

【20】J.-S. R. Jang., ”ANFIS : Adaptive Network-based Fuzzy Inference System.” IEEE Transactions on Systems, Man, and Cybernetics, vol. 23, No. 3, pp.665-685, 1993.
【21】R.K. Mehra, “ Approaches to adaptive filtering,” IEEE Trans. Automat. Contr.,vol.AC-17, pp.693-698, 1972.
pp.195-225, 1991.