擁有良好類化能力的可微分小腦模型控制器(Differentiable Cerebellar Model
Articulation Controller, DCMAC)是一個很有用的學習系統，而模糊滑動模式控制器(
Fuzzy Sliding Mode Controller, FSMC)進行控制時並不需要事先知道受控體的數學模式
，因此可被用來解決信息不充分的控制系統。
受控體有從單純的物件到複雜的機構物件，這些物件於控制當中可能受到各式各樣的干擾
，而且不同的控制物件具有不同的控制特性，因此唯有給予受控體正確的控制方法，才能
使它獲得良好的控制品質。
基於上述考量，本研究所設計的控制器除了利用誤差、誤差值的變化外還必須考慮那些控
制器擁有類似積分器的功能，可以被用來做浮球位置控制，而可微分小腦模型控制器及模
糊滑動模式控制器因能滿足上述之條件，所以為本研究所選用。
本研究所設計的浮球位置控制系統，係以浮球的位置輸出值和其期望值做比較，對其所產
生的誤差及誤差值的變化量，經由可微分小腦模型控制器及模糊滑動模式控制器分別運算
後，再同時對浮球位置控制系統輸出控制信號，使浮球能儘快地、穩定地到達預期目標，
以使控制系統的響應速度及響應能力獲得改善。

Differentiable Cerebellar Model Articulation Controller owning the good
ability of generalization is a very useful study system. and Fuzzy Sliding
Mode Controller when it is used doesn't need to know the mathematics mode of
the plant in advance, therefore it can be used to solve control system, which
information is not complete.
The plant has from pure thing to complex organization thing, these things
which is controlled may be come across every kind of disturbance, and the
different control thing have different control characteristics, therefore the
plant has to be give the correct control method, then it will obtain the good
control quality.
Base on above-cited, the controller which be designed in this paper must use
the error、delta of error and consider the controller which owning ability of
integral, can be used to float ball position control, and Differentiable
Cerebellar Model Articulation Controller and Fuzzy Sliding Mode Controller can
to satisfy on the conditions above, so that they be chose.
The control system which is designed in this paper, firstly the output
position of the float ball compares with the expected position of the float
ball, then obtaining its error and variety quantity, after being calculated by
Differentiable Cerebellar Model Articulation Controller and Fuzzy Sliding Mode
Controller respectively, and transmitting control value to the control system
of the float ball simultaneously, then the float ball can reach the expected
position as soon as possible and stability, so that the response speed and the
response ability of the controller system can be improved.

[1] Miller, T. W., Glanz, F. H. Kraft & L. G. (1987). Application of a General Learning Algorithm to the Control of Robotic Manipulators. The International Journal of Robotic Research, 6, 2, 84-98.
[2] Miller, W.T. & Aldrich (1990). Rapid Learning Using CMAC Neural Networks: Real Time Control of an Unstable System. Proceedings of the 5th IEEE International Symposium on Intelligent Control 1990, Philadelphia, PA., (pp.465-470).Richard P. Lippmann (1989). Pattern Classification Using Neural Netwroks. IEEE Communications Magazine, 47-64.
[3] Shelton R. O. & Peterson & J. K. (1992). Controlling a Truck with an Adaptive Critic CMAC Design. Simulation, 58, 5, 319-326.
[4] Chiang C.T., Lin. C.S. (1996). CMAC with General Basis Functions. Neural Networks, 9, 7, 1199-1211,1996.
[5] Chih-Ming Chen, Hahn-Ming Lee & Yu-Rong Hsieh (1999). A New Learning Model of Hierarchical CMAC Neural Networks. Proceedings of Fourth National Conference on Artificial Intelligence and Applications, pp.17-22,1999.
[6] Jar-Shone Ker, Yau-Hwang Kuo, Rong-Chang Wen & Bin-Da Liu Hardware Implementation of CMAC Neural Network with Reduced Storage Requirement. IEEE Transaction on Neural Networks, 8, 6, 1545-1556,1997.
[7] 洪欽銘、陳志銘、羅維恆、黃昭諺。採用無失真壓縮技術精簡小腦模型控制器聯想記憶體之研究。第五屆人工智慧與應用研討會，pp.277-282，2000
[8] Albus, J.S. A New Approach to Manipulator Control: The Cerebellar Model Articulation Controller (CMAC). Journal of Dynamic Systems,
73
Measurement, and Control, Transactions of ASME, 220-227,1975.
[9] Albus, J.S. Data Storage in the Cerebellar Model Articulation Controller (CMAC). Journal of Dynamic Systems, Measurement, and Controller, Transactions of ASME, 228-233,1975.
[10] S. H. Lane, D. A. Handelman, J. J. Gelfand, “Theory and Development of Higher-Order CMAC Neural Networks,” IEEE Contr. Syst., vol. 12, 1992, pp. 23-30.
[11] C. T. Chiang and C. S. Lin, “Integration of CMAC and Radial Basis Function Techniques,” IEEE International Conference on Intelligent Systems for the 21st, Vol. 4, 1995, pp.3263-3268.
[12] C. T. Chiang and C. S. Lin, “CMAC with General Basis Functions,” Neural Network, vol.9, no.7, 1996, pp.1199-1211.
[13] U.Itkis, “Control Systems of Variable Structure,” New York:Wilek,1976.
[14] V. I. Utkin, “Sliding modes and their application in variable structure system,” Moscow: Mir,1978(English translation).
[15] S. V. Emel'yanov, “Use of Nonlinear Correcting Devices of Switch Type to Improve the Quality of Second-Order Automatic Control Systems,” Automat. I Telemekh., Vol. 20, No. 7, 1959.
[16] K. Furuta, “Sliding Mode Control of A Discrete System,” Systems & Control Letters, vol. 14, 1990, pp.145-152.
[17] D. Milosavljevic, “General conditions for the existence of a quasi-sliding mode on the switching hyperplane in discrete variable structure systems,” Automat. Remote Contr., vol. 46, 1985, pp.307-314.
[18] Y. Dote and R. G. Hoft, “Microprocessor based Sliding Mode Controller for DC Motor Drivers,” Ind. Application Soc. Annu. Metting Cincinnati, OH,
74
1980.
[19] S. Z. Sarpturk, Y. Istefanopulos, and O. Kaynak, “On the Stability of Discrete-Time Sliding Mode Control Systems,” IEEE Trans. Automat. Contr., vol. 32, no, 10, 1987, pp.930-932.
[20] W. B. Gao, “The Foundation of Variable Structure Theory”, Beijing: CST, 1988, pp.243.
[21] G. Golo, Č. Milosavljević, “Robust Discrete-Time Chattering Free Sliding Mode Control,” Sys. & Contr. Letters, Vol. 41, 2000, pp.19-28.
[22] L. A. Zadeh, "Fuzzy sets," Information and Control,” vol. 8, no. 3,pp.338-353,1965.
[23] E. H. Mamdani, "Application of fuzzy algorithms for control of a simple dynamic plant," Proc. IEE, vol. 121, no. 12, ppl585-1588, 1974.
[24] C. C. Lee, "Fuzzy Logic in Control System : Fuzzy Logic Controller-Part I," IEEE Trans. System, Man , and Cybernetics, Vol. 20, No. 2, pp.404-418, 1990.
[25] C. C. Lee, "Fuzzy Logic in Control System: Fuzzy Logic Controller-Part II," IEEE Trans. System, Man, and Cybernetics, Vol. 20, No. 2, pp.419-435, 1990.
[26] 楊凱鈞(民90)：浮球定位控制實驗單元。台北，智控科技。
75