This paper describes a robust support vector regression (SVR) methodology that offers superior performance for important process engineering problems. The method incorporates hybrid support vector regression and differential evolution technique (SVR-DE) for efficient tuning of SVR meta parameters. The algorithm has been applied for prediction of pressure drop of solid liquid slurry flow. A comparison with selected correlations in the literature showed that the developed SVR correlation noticeably improved prediction of pressure drop over a wide range of operating
conditions, physical properties, and pipe diameters.
Mattera D, Haykin S, Support vector machines for dynamic reconstruction of a chaotic system, Advances in Kernel Methods, Support Vector Machine, MIT Press, 1999
Roco MC, Shook CA, Powder Technology, 39, 159, 1984
Roco MC, Shook CA, J. Fluids Eng., 107, 224, 1985
Sastry KKN, Behra L, Nagrath IJ, Differential evolution based fuzzy logic controller for nonlinear process control, Fundamenta Informaticae, Special Issue on Soft Comput., 1998
Scholkopf B, Burges J, Smola A, Advances in kernel methods: Support vector machine, MIT Press, 1999
Smola A, Murata N, Scholkopf B, Muller K, Asymptotically optimal choice of epsilon-loss for support vector machines, Proc. ICANN, 1998
Turian RM, Yuan TF, AIChE J., 23, 232, 1977
Vapnik V, Golowich S, Smola A, Adv. in Neural Inform. Proces. Syst., 9, 281, 1996
Vapnik V, The nature of statistical learning theory, Springer Verlag, New York, 1995
Vapnik V, Statistical learning theory, John Wiley, New York, 1998
Wasp EJ, Aude TC, Kenny JP, Seiter RH, Jacques RB, Deposition velocities transition velocities and spatial distribution of solids in slurry pipelines, Proc. Hydro transport 1, BHRA Fluid Engineering, Coventry, UK, paper H42 53-76, 1970
Wilson KC, A unified physically-based analysis of solid-liquid pipeline flow, Proceedings of the 4th International Conference on Hydraulic Transport of Solids, BHRA Fluid Engineering, Cranfield UK Paper A2, 1-16, 1976
Wilson KC, Pugh FJ, Can. J. Chem. Eng, 66, 721, 1988
Zandi I, Govatos G, Proc. ACSE, J. Hydraul. Div., 93, 145, 1967