臺灣博碩士論文加值系統

本研究主要目的是探討使用球型端銑刀高速加工自由曲面時，影響表面粗度變異的切削參數。且利用誘導式類神經網路系統建立球型端銑刀之表面粗度模式，並依據此模式探討在不同加工條件下，各切削參數對表面粗度變異的影響。實驗驗證結果顯示，本數學模式具有良好的適用性。
本文採用實驗規劃法規劃實驗。選擇主軸轉速、進給率、軸向切深、徑向切深及工件傾角為實驗因子，並利用實驗規劃法中之表面反應設計為基礎配置實驗。實驗數據由誘導式類神經網路系統進行回歸分析，建立表面粗度之數學模式。並利用最佳化演算法PSO，在本研究探討之切削範圍內，進行切削條件的配置，以提供加工者選擇切削條件之參考。

In this investigation the main goal is discussing the cutting parameters affecting the surface roughness variable when using the ball-end mill to machining the free curves at a high speed. The Abductive Networks is used to establish the model of the roughness and based on this model to discuss the effects of every cutting parameter on the surface roughness variable under the different machining conditions. The experimental results show that this mathematical model is very suitable for the investigation.

The experimental scheme is selected to plan the experiment in this paper. The spindle speed, feed rate, axial depth of cut, radial depth of cut, and rake angle of the workpiece are chosen as the experimental factors. Additionally, the response curve design in the experimental scheme is used to be the basic disposed experiment. The Abductive Networks is used to regress and analysis the experimental data and then the mathematical model of the roughness will be established. In the cutting range discussed in this investigation, the optimal algorithm PSO is used to dispose the cutting conditions for providing the operators a reference to select the cutting parameters.

Abstract…….……………......….…………………………….…………….i
誌謝……..………..………………..……………...…….…………………ii
Contents….……………......………..……………………..…...………….iii
Chapter 1 Introduction…….…….……...…………………..……...…….1
1.1 Introduction……...………..……………………………….…1
1.2 Literature review….....………….…………………………....3
1.3 Research goal....…….....…………….……………………….6
1.4 Paper overhead construction…………..…………………......8
Chapter 2 Theory………..……..…………..……………….……….…...9
2.1 Synopsis…….……………………………………..………....9
2.2 Surface roughness………………..………………….……...11
2.3 Response surface method………….…………….….………16
2.3.1 Response surface method...………….…………….16
2.3.2 Central composite design……….…..…….……….21
2.4 Abductive networks system..…………………….…………22
2.4.1 Synopsis……………..…….…………………….…22
2.4.2 Abductive Networks Use flow…..…...……….……26
2.5 Particle Swarm Optimization…………………….………....29
2.5.1 Synopsis………………..…….…………………….29
2.5.2 Simulation of the social behavior………………….29
2.5.3 Basic conception of PSO……….………………….30
2.5.3 Procedure concept of PSO……...………………….34
Chapter 3 Plan and the result in experiment.……………...….....……..36
3.1 Experimental facilities…….…………...……….……..……36
3.2 The experiment disposing……………………………..……40
3.3 Experimental result……………….……………………..….46
3.4 Modling and proved……………………………..……….....46
Chapter 4 Optimization.....………..…………………......…..................49
Chapter 5 Result and discussing..…………………………...................55
Chapter 6 Conclusion……………………………………….…………66
References…............................…………………..….…………………….68

[1]K.V. Olsen, Surface roughness on turned steel components and the relevant mathematical analysis, The Production Engineer 59 (December) (1968) 593–606.
[2]K. Taraman, Multi machining output—multi independent variable turning research by response surface methodology, International Journal of Production Research 12 (1974) 233–245.
[3]P.G. Petropoulos, Statistical basis for surface roughness assessment in oblique finish turning of steel components, International Journal of Production Research 12 (1974) 345–360.
[4]G. Boothroyd, Fundamentals of Metal Machining and Machine Tools, McGraw Hill Publishers, 1975.
[5]M. Hasegawa, A. Seireg, R.A. Lindberg, Surface roughness model for turning, Tribology International December (1976) 285–289.
[6]R.M. Sundaram, B.K. Lambert, Mathematical models to predict surface finish in fine turning of steel, Part I, International Journal of Production Research 19 (1981) 547–556.
[7]R.M. Sundaram, B.K. Lambert, Mathematical models to predict surface finish in fine turning of steel, Part II, International Journal of Production Research 19 (1981) 557–564.
[8]U. Tetsutaro, M. Naotake, Prediction and detection of cutting tool failure by modified group method of data handling, International Journal of Machine Tools and Manufacture 26 (1986) 69–110.
[9]A. Mital, M. Mehta, Surface roughness prediction models for fine turning, International Journal of Production Research 26 (1988) 1861–1876.
[10]M.A. El Baradie, Surface roughness model for turning grey cast iron (154BHN), Proceeding of Institution of Mechanical Engg, Part B, Journal of Engineering Manufacture 207 (1993) 43–54.
[11]S. Das, R. Islam, A.B. Chattopadhyay, Simple approach for online tool wear monitoring using the analytical hierarchy process, Proceedings of Institution of Mechanical Engineers, Part B, Journal of Engineering Manufacture 211 (1997) 19–27.
[12]P.V.S. Suresh, P. Venkateswara Rao, S.G. Deshmukh, A genetic algorithmic approach for optimization of surface roughness prediction model, International Journal of Machine Tools & Manufacture 42 (2002) 675–680.
[13]百賜清“工業實驗設計法”中華民國品質管制學會發行，1994.
[14]R.C. Eberhart, J. Kennedy, A new optimizer using particle swarm
theory, in: Proceedings of the Sixth International Symposium on
Micro Machine and Human Science (1995) pp. 39–43.
[15]V. Tandon a, H. El-Mounayri a,*, H. Kishawy 1,b,NC end milling optimization using evolutionary computation, International Journal of Machine Tools & Manufacture 42 (2002) 595–605.
[16]Ayed Salman*, Imtiaz Ahmad, Sabah Al-Madani, Particle swarm optimization for task assignment problem, Microprocessors and Microsystems 26 (2002) 363–371.
[17]Reynolds, C. W. (1987). Flocks, herds and schools: a distributed behavioral model. Computer Graphics, 21(4):25-34.
[18]Heppner, F. and U. Grenander(1990). A stochastic nonlinear model for coordinated bird flocks. In S. Krasner, Ed., The Ubiquity of Chaos. AAAS Publications, Washington, DC.
[19]Wilson, E. O. (1975). Sociobiology: The new synthesis, Belknap Press, Cambridge, MA.