臺灣博碩士論文加值系統

存貨管理在製造業上是個很重要的議題，如何訂購最佳的訂購量並減少成本以得到最大獲利，一直都是此議題必須努力改善實現的目標。因此，本研究假設製造業上的需求屬於碎形布朗運動並驗證之，並根據碎形布朗運動的特性結合存貨模型，將赫斯特幂數應用於前置期間需求量，進行(Q, r)存貨模型的修正。最後利用碎形布朗運動產生不同赫斯特幂數的需求數列，發展存貨政策，與假設獨立的存貨模型作數值比較，發現本存貨模型改善後的效能更優於獨立模型，可獲得較小的總成本，因此可提供管理者進行生產決策或預測規劃。

Inventory management is an important issue in the manufacture. The target of developing these inventory models is to determine optimal order quantity and gain the maximum profit. Hence, in this thesis, we assume the demand in the manufacture is under fractional Brownian motion. We also use fractional Brownian motion by Hurst exponent in the fixed lead-time demand to modify (Q, r) inventory model. Finally, we simulated fBm process by different H values for the lead time demand to develop inventory policy. We compare result with independent model. We could find out our model is better than assumed independent model. We hope that could provide managers to make a correct decision.

中文摘要 II
ABSTRACT III
ACKNOWLEDGEMENTS IV
CONTENT V
FIGURE LIST VI
TABLE LIST VII
1. INTRODUCTION 1
1.1. Background and motivation 1
1.2. Objective 2
1.3. Organization of Thesis 2
2. LITERATURE REVIEW 3
2.1. The Hurst Phenomenon and Hurst law 3
2.2. The Brownian motion and The Fractional Brownian motion 6
2.2.1. The Brownian motion 7
2.2.2. The fractional Brownian motion 9
2.3. The fractional Gaussian noise 14
2.4. The dimension of the graph 16
2.5. The Quantile-Quantile Plot 17
2.6. The Chi-Square Goodness-of-Fit Test 19
3. VERIFICATION 21
3.1. Data research 21
3.2. Analysis result 36
4. INVENTORY MODEL 37
4.1. Introduction 37
4.2. Notations and assumptions 38
4.3. Continuous-review System 41
4.4. Numberical example 47
4.4.1. Parameters and assumption 47
5. SENSITIVITY ANALYSIS AND EFFECTS OF THE PARAMETERS 49
6. CONCLUSION 52
REFERENCE 55

[1]Apley, D.W. and Tsung, F. (2002). The autoregressive T2 chart for monitoring univariate autocorrelated processes. Journal of Quality Technology, 34, 80-96.
[2]Bagchi, U., Hayya, J.C., and Ord, J.K (1982). The distribution of demand during lead time: A synthesis of the state of the use art. working paper, Pennsylvania State University.
[3]B.B. Mandelbrot, Wallis, J.R. (1969a). Computer experiments with fractional Gaussian noises, Parts 1,2,3. Water Resource. 5, 228-267.
[4]B.B. Mandelbrot, Wallis, J.R. (1969). Some long-run properties of geophysical records. Water Resource. 5(2), 321-340.
[5]B.B. Mandelbrot and J.W. van Ness (1968). Fractional Brownian motions, fractional noises and applications. SIAM Review, 10, 422—437.
[6]Chambers, John, William Cleveland, Beat Kleiner, and Paul Tukey (1983). Graphical Methods for Data Analysis. Wadsworth.
[7]Crownover, R. M. (1995). Introduction to Fractals and Chaos. Jones and Bartlett Publishers, Boston.
[8]Dueck, S. (2003). Synthesis of fractional Brownian motion: an evaluation of the simulation techniques of Mandelbrot-van Ness and Cholesky. Physica S 1,.1-29
[9]Falconer, K. (1990). Fractal geometry. John Wiley & Sons, New York.
[10]Feder, J. (1988). Fractals. Plenum Press, New York.
[11]G.. Gallego, D.D. Yao and I. Moon (1993). The distribution free newsboy problem. The Journal of Operational Research Society, 44(8), 825-834.
[12]H.E. Hurst (1956). Long-term storage capacity of reservoirs. American Society of Civil Engineers, 116, 770—808.
[13]Heinz-Otto Peitgen and Dietmar Saupe (1998). The Science of FRACTAL IMAGES. Springer-Verlag, New York Inc.
[14]Hogg, R.V. and Tanis, E.A. (2006). Probability and Statistical Inference, 7th edition. Pearson Prentice Hall: Upper Saddle River, NJ.
[15]Hsieh, C.C., Hu, T.W. and Chang, H.K. (1997). Discussing the meaning of Hurst exponent. Construction and Building Activities and Water Conservancy. 7-18.
[16]Kottas, J.F., and Lau, H.S. (1979). A realistic approach for modelling stochastic lead time distributions. AIlE Transactions, 11, 54-60.
[17]Kottas, J.F., and Lau, H.S. (1980). The use of versatile Distribution families in some stochastic inventory calculations. Journal of the Operational Research Society, 31, 393-403.
[18]Lau, H.S., and Wang, M.C. (1987). Estimating the lead time demand distribution when the daily demand is non-normal and autocorrelated. European Journal of Operational Research, 29, 60-69.
[19]Magre, O. and Guglielmi, M. (1997). Modelling and analysis of fractional Brownian motions. Chaos, Solitons & Fractals, 8, 377-388.
[20]Ouyang L.Y. & Yen N.C. & Wu K.S. (1996). Mixture inventory model with backordersand lost sales for variable lead time, Journal of the Operational Research Society, 47, 829-832.
[21]Ravindran, A., Phillips, D. T., and Solberg, J. J. (1987). Operations Research: Principles and Practices ,New York: Wiley.
[22]Ray, W.D. (1980). The significance of correlated demands and variable lead time for stock control policies. Journal of the Operational Research Society, 31, 187-190.
[23]Ray, W.D. (1981). Computation of reorder level when the demands are correlated and the lead time random. Journal of the Operational Research Society, 32, 27-34.
[24]Snedecor, George W. and Cochran, William G. (1989). Statistical Methods, Eighth Edition, Iowa State University Press.
[25]Stergios Fotopoulos, Wang, Min-Chiang and S. Subba Rao (1988). Safety stock determination with correlated demands and arbitrary lead times. European Journal of Operational Research, 35(2), 172-181.
[26]Stoev, S., Taqqu, M., Park, C., and Marron, J. S. (2005). On the Wavelet Spectrum Diagnostic for Hurst Parameter Estimation in the Analysis of Internet Traffic. Computer Networks, 48, 423-445.
[27]Van Ness, P.D., and Stevenson, N.J. (1983). Reorder-point models with discrete probability distributions. Decision Sciences, 14, 363-369.
[28]Wallis, J. R. and Matalas, N. C. (1970). Small Sample Properties of H and K-Estimators of the Hurst Coefficient h. Water Resources Research, 6(6): 1583-1594.