ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM (ANFIS) APPROACH TO EVALUATE THE DEBUTANIZER TOP PRODUCT

This paper proposed an ANFIS estimator to evaluate the top product from secondary measurements. Real debutanizer column in one of the Iranian refineries has been purchased and the adaptive neuro-fuzzy inference system is trained and validated with real data. According to results, ANFIS can be used with acceptable approximation in replace of costly measurement instruments as gas chromatographs.

[1]  Hari Om Gupta,et al.  ANN based estimator for distillation—inferential control , 2005 .

[2]  Kauko Leiviskä.  Industrial Applications of Soft Computing , 2001 .

[3]  Richard Weber,et al.  The use of secondary measurements to improve control , 1972 .

[4]  F. Palis,et al.  Modeling and control of non-linear systems using soft computing techniques , 2007, Appl. Soft Comput..

[5]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[6]  Tetsuo Fuchino,et al.  Prediction of vapor–liquid equilibrium data for ternary systems using artificial neural networks , 2007 .

[7]  Qian Han-cheng,et al.  Fuzzy neural network modeling of material properties , 2002 .

[8]  M. A. Rahman,et al.  The application of a neural-fuzzy logic controller to process control , 1994, NAFIPS/IFIS/NASA '94. Proceedings of the First International Joint Conference of The North American Fuzzy Information Processing Society Biannual Conference. The Industrial Fuzzy Control and Intellige.