在新世代的無線網路中，高精準度、高穩定性的頻率及時間將是不可或缺的關鍵要素。本論文採用調適性類神經模糊推論系統（ANFIS）為基礎，來建置時間及頻率備援系統。本系統有2種運作模式：一般模式(Normal Mode)及繼任模式(Holdover Mode)。在一般模式下，以高精準度銫原子鐘(Cesium Clock)之頻率為校準基礎，透過模糊推論控制器（Fuzzy Controller）來校正恆溫石英晶體震盪器（OCXO），並記錄毎秒的控制量。當銫原子鐘無法正常運作時，繼任模式將會使用ANFIS的預測來接管系統，使用ANFIS分析資料庫之數據來預測下一秒控制量，並經由數位類比轉換器提供電壓加以控制，以延長OCXO之精準度。實驗結果顯示，一般模式下的OCXO精準度由10-9改善到10-13；繼任模式中之效能則可維持到10-12。本研究之系統可適用於電信、量測、儀器、控制、航運、電力系統及各種各樣的應用。

Accuracy and stability are two essential issues of frequency and time in the new generation wireless networking. A backup system for time and frequency calibration based on adaptive neural-fuzzy inference system (ANFIS) is presented in this paper. The System has two kinds of operation way: normal mode and holdover mode. In normal mode, an oven-controlled crystal oscillator (OCXO) is steered by using fuzzy controller to synchronize with the primary cesium atomic clock, and recorded the control amount of per second. While the primary cesium atomic clock cannot operate correctly, a holdover mode operation which utilizes an ANFIS predictor will takes over the system. In particular, the ANFIS is applied to analyze datum of the database for predicting the controlling amount of the next second when the system enters holdover mode. Experimental results show that the frequency stability of the OCXO can be improved from a few parts in 10-9 to 10-13 for averaging times, as well as the performance could be maintained within a few parts in 10-12 in the holdover mode. The system of this research is applicable to telecommunication, measurement, instrumentation, control systems, navigations, power systems, and in numerous other applications.

[1] The 3rd generation partnership project. Available:http://www.3gpp.org/
[2] ITU-T Rec. G.810, Definition and Terminology for Synchronization Networks, Aug. 1996.
[3]國家時間與頻率標準實驗室，建立及維持國家時間與頻率標準，經濟部，2004。
[4] C.W.T. Nicholls, G.C. Carleton, Adaptive OCXO drift correction algorithm , IEEE Frequency Control Symposium and Exposition, pp. 509 – 517, 2004.
[5] C.W.T. Nicholls, P. Wu, Ultra low cost base station timing module, Frequency Control Symposium, 2007 Joint with the 21st European Frequency and Time Forum, IEEE International, Geneva, pp. 1318 – 1323, June 2007.
[6] K. Y. Tu, F. R. Chang, C. S. Liao, and L. S. Wang, Frequency Syntonization Using GPS Carrier Phase Measurements , IEEE Transactions on Instrumentation and Measurement, vol. 50, no. 3, June 2001.
[7] K. Y. Tu, C. S. Liao, F. R. Chang, and L. S. Wang, Time Transfer Using GPS Carrier Phase with Multi-channel Common-view, IEEE Conference on Precision Electromagnetic Measurement, Sydney, Australia, pp. 74-75, May 2000.
[8] K. Y. Tu, S. S. Chen, C. S. Liao, F. R. Chang, Synchronized clock using GPS carrier phase with self-calibration in holdover mode, Frequency Control Symposium and Exhibition, Proceedings of the 2000 IEEE/EIA International, Kansas City, MO, pp. 612 – 617, 7-9 June 2000.
[9] L. X. Wang，汪惠健，模糊理論與應用，全威圖書，2008。
[10] 張道弘，PID控制理論與實務，全華科技，1999。
[11] 王文俊，認識 Fuzzy ，三版，全華科技， 2005。
[12] 孫宗瀛，楊英魁， Fuzzy控制理論、實作與應用 ，全華科技，2005。
[13] D. Drianko, H. Hellendoorn, M. Reinfrank, An Introduction to Fuzzy Control, New York: Springer-Verlag, 1992.
[14] 張裵章，張秋麗，類神經網路，東華書局，2005。
[15] 張智星， MATLAB程式設計與應用 ，清蔚科技， 2000。
[16] 蒙以正， MATLAB入門與精進 ，儒林圖書，2007。
[17] J. S. Jang, ANFIS: Adaptive Network-based Fuzzy Inference System, IEEE Transactions on Systems, Man, and Cybernetics, vol. 23, no. 3, June 1993.
[18] 羅華強，類神經網路-MATLAB的應用，清蔚科技，2001。
[19] K. Y. Tu, C. S. Liao, Application of ANFIS for Frequency Syntonization Using GPS Carrier-Phase Measurements, Frequency Control Symposium, 2007 Joint with the 21st European Frequency and Time Forum, IEEE International, pp. 933 – 936, May 29 2007-June 1 2007.
[20] 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，2004。
[21] K. C. Lee, P. Gardner, Adaptive neuro-fuzzy inference system (ANFIS) digital predistorter for RF power amplifier linearization, IEEE Transactions on Vehicular Technology, Volume 55, Issue 1, pp. 43 – 51, Jan. 2006.
[22] D. W. Chen, J. P. Zhang, Time series prediction based on ensemble ANFIS, Proceedings of 2005 International Conference on Machine Learning and Cybernetics, Volume 6, Vol. 6, pp. 3552 – 3556, 18-21 Aug. 2005.
[23] C. A. Greenhall, D, A. Howe, D. B. Percival, Total variance, an estimator of long-term frequency stability, Ultrasonics, IEEE Transactions on Ferroelectrics and Frequency Control, Volume 46, Issue 5, pp. 1183 - 1191, Sept. 1999.
[24] 程家龍，單頻接收機GPS載波相位結合動態智慧型適應預測濾波器在頻率同步之應用，博士論文，2007。