本論文旨在利用MATLAB中的xPC Target System，建立一套可進行即時信號處理的系統，並將此系統應用於即時辨識衝頭在衝擊過程中所撞擊的試片材質。我們以裝設在衝頭內部的加速規為感應器，在衝擊過程中即時擷取加速度信號的變化，並透過適當的即時信號運算和辦別邏輯進行即時的識別工作。
我們首先將加速度信號進行特徵值抽取，再依照衝擊過程中衝頭所處的狀態將其進行分類，如靜止、自由落體等。以「可塑性網路」為識別系統的架構。此系統由許多子網路組成，各個子網路使用BPN或是ANFIS為分類器，負責辨識一種狀態。子網路的輸入為各特徵值，輸出則為0或1，表示輸入屬於或不屬於該狀態，在系統訓練完畢後，將各個訓練完畢後的子網路輸出做統合運算，可得到該時間點時衝頭所處的狀態。最後將此識別系統建立於xPC Target System上進行即時識別。

This thesis is concerned with the construction of real-time signal processing system by utilizing “xPC target system” in MATLAB and we would apply this system in the identification of material type during the impact processing. The accelerometer would be used as sensor and mounted in the penetrator. It could measure the real-time variation of acceleration signals and they are useful for building the identification system. By suitable signal processing and logic estimation we could know what material the penetrator hit.
First we get feature extractions of signals and classify the situation of penetrator, such as rest or free body dropping etc, during the impact processing. Then we choose the “Plastic network” to be our configuration of system. It consist of many subnets and each use BPN or ANFIS as the classification to determine one situation. Inputs of subnets are feature extractions and outputs are zero or one. It represent whether the input is this situation the subnet classified or not. After finishing training the system, we get outputs of all subnets to generate an integrated result. Finally we implement this system in xPC Target System.

1. Jonas A. Zukas, “Impact Dynamics”, John Wiley & Sons, Inc, 1982.
2. Yates et al., “United States Patent, Patent Number 4375192”,
Date of Patent Apr. 3, 1981.
3. Abt, “United States Patent, Patent Number 4480550”,
Date of Patent Jul. 26, 1982.
4. Parsons et al. , “United States Patent, Patent Number 5698814”,
Date of Patent Jan. 11, 1996.
5. Schmacker, “United States Patent, Patent Number 6276277”,
Date of Patent Apr. 22, 1999.
6. Min et al., “United States Patent, Patent Number 5,255,608”,
Date of Patent Oct. 26, 1993.
7. 李易儒, “多層介質即時辨識系統之研究-應用類神經網路”,
國立台灣科技大學高分子工程研究所碩士論文, 2003.
8. 彭啟忠, “以數位訊號處理器為基礎的多層介質穿透即時辨識系統之研究”,
國立台灣科技大學高分子工程研究所碩士論文, 2004.
9. 陳秋恭, “應用模糊類神經網路於穿刺結構之動態訊號分析”,
國立成功大學航太研究所碩士論文, 2004.
10. Li-Xin Wang, “A course in fuzzy systems and control”,
Prentice Hall International, Inc, 1997.
11. 李允中,王小璠,蘇木春, “模糊理論及其應用”, 全華科技, 2003.
12. L. A. Zadeh, “Fuzzy sets”, Inform. Conter, vol.8, p.338~353, 1965.
13. 蒙以正, “MATLAB 5 專業設計技巧”, 碁峯科技, 1999.
14. E. H. Mamdani and S. Assilian, “An experiment in linguistic synthesis
with a fuzzy logic controller”, International Journal of Man-Machine
Studies, 7(1):1-13, 1975.
15. T. Takagi and M. Sugeno, “Fuzzy identification of systems and its
applications to modeling and control ”, IEEE Transactions on Systems, Man,
and Cybernetics, 15:116-132, 1985.
16. M. Sugeno and G.T. Kang., “Structure identification of fuzzy model”,
Fuzzy Sets and Systems, 28:15-33, 1988.
17. K. M Hornik, M. Stinchcimbe and H. White, ”Multilayer feedforward networks
are universal approximators”, Neural Networks, vol.2, no.5,
pp.359-366, 1989.
18. 葉怡成, “類神經網路模式應用與實作”, 儒林圖書, 2003.
19. Hagan, Demuth, Beale, “類神經網路設計: Neural network Design”,
湯姆生亞洲出版, 2004.
20. 羅華強, “類神經網路: MATLAB的應用”, 清蔚科技, 2001.
21. J.S.R. Jang, C.T. Sun and E. Mizutani, “Neural-Fuzzy And Soft Computing”,
Prentice Hall International, Inc, 1997.
22. Chin-Teng Lin, C.S. George Lee., “Neural fuzzy systems:
a neuro-fuzzy synergism to intelligent systems”,
Prentice Hall International, Inc, 1996.
23. J.S.R. Jang, “ANFIS: Adaptive-Network-Based Fuzzy Inference System”,
IEEE Transactions on System, Man and Cybernetics, vol. 23, no.3,
pp.665-685, 1993.
24. Simon Haykin, Barry Van Veen, “Signals and Systems”, John Wiley & Sons,
Inc., 1999.
25. 王凱達, “平編及雙強結構玻纖複材層板承受低速落綞衝擊之研究”,
國立成功大學航太研究所碩士論文, 2000.
26. 沈廣漢, “應用MEMS為感測器於多層穿靶訊號之偵測”,
國立成功大學航太研究所碩士論文, 2005.
27. 周義昌, “類神經網路新架構: 可塑性認知網路 A New Architecture of Neural
network: Plastic Perceptron”, 電信研究季刊, 第22卷第3期, 民國81年6月.
28. J.S.R. Jang, “Input Selection for ANFIS Learning”, Proceedings of the
Fifth IEEE International Conference on, Volume: 2, 1996.