在煉油製程裡，其現場蒸餾塔設定點操作，常依靠現場員工的經驗，而無一定準則。而油品進料種類卻不固定，因此常造成油品生產過程中，一些不必要的損失。
而本研究即針對原油分餾工廠問題，進行探討和分析。而我們樣本取自於中油大林廠第十一蒸餾塔，此蒸餾塔的目的為從原油分餾出液化石油氣、輕油、煤油、柴油等。希望可以建立數學模型，能夠從有限的數據資料中，準確地預估出料油品的性質，藉此增加石油煉油廠的產率。
利用ASPEN化工模擬軟體，建立工廠模型。直接輸入現場數據，而得到模擬數據。以模擬數據與現場數據做比較，對於已建立模型做出修正，以期能達到準確預估油品性質的目標。
另外，結合類神經網路演算法(ANN)與Lasso演算法，實現非線性系統的描述與變數的選擇，對油品性質評估。因石油分餾屬於高度非線性的模型，而類神經網路則具有對複雜系統的學習與辨識能力。Lasso則是引入一個限制條件，進行變數選取。本論文就已上述方法，分別對於該系統估算參數設定值，藉此提供操作主蒸餾塔設定點的準則。

[1] R. Tibshirani, “Regression shrinkage and selection via the lasso”, Journal of the Royal Statistical Society, Series B (Methodological), 58(1), 267–288, 1996
[2] W. S. McCulloch and W. Pitts, “A Logical Calculus of the Ideas Immanent in Nervous Activity”, Bulletin of Mathematical Biophysics, 9, 127-147, 1943
[3] D. O. Hebb, “The Organization of Behavior”, Wiley, New York, 1949
[4] F. Rosenblatt, “The Perception: A Probabilistic model for Information Storage and Organization in the Brain”, Psychological Review, 65, 386-408, 1958
[5] D. E. Rumelhart, G. E. Hinton and R. J. Williams, “Learning Internal Representations by Error Progation”, Cambridge MA: MIT Press, 1, Chapter 8, 318-362, 1986
[6] J. C. Hoskins and D. M. Himmelblau, “Artificial Neural Network Models of Knowledge Representation in Chemical Engineering”, Comput. chem. Engng, 12(9/10), 881-890, 1988
[7] J. M. Horng, J. W. Ko, Y. P. I and W. T. Wu, “Determination of Operating Conditions for a Crude Tower Uring Neural Nectworks”, Process Control and Quality., 7, 21-26, 1995
[8] J. W. Ko, Y. P. I and, W. T. Wu, “Determination of an Optimal Operating Condition for a Crude Tower via a Neural Network Model”, Process Control and Quality, 10,291-298, 1997
[9] C. K. Liau, C. K. Yang and M. T. Tsai, “Expert System of a Crude Oil Fistillation Unit for Process Optimization using Neural Networks”, Expert Systems with Applications, 26, 247-255, 2004
[10] F. Jalali, S. Motlaghi and M. N. Ahmadabadi, “An Expert System Design for A Crude Oil Distillation Column with The Neural Networks Model and The Process Optimization using Genetic Algorithm Framework”, Expert Systems with Applications, 35, 1540–1545, 2008
[11] W. L. Luyben , “ Distillation Design and Control Using Aspen Simulation”, John Wiley & Sons, New York, 2006
[12] J. Haydary and T. Pavlík, “Steady-State and Dynamic Simulation of Crude Oil Distillation Using ASPEN PLUS and ASPEN DYNAMICS”, Petroleum & Coal , 51(2), 100-109, 2009