The estimation of kinematic viscosity of petroleum crude oils and fractions with a neural net |
| |
| Affiliation: | 1. Department of Chemical Engineering, University of Technology, Baghdad, Iraq;2. Environmental Research Center, University of Technology, Baghdad, Iraq;1. Department of Chemical Engineering and Biotechnology, University of Cambridge, Cambridge CB2 3RA, United Kingdom;2. Department of Chemical and Biological Engineering, The University of Sheffield, Sir Robert Hadfield Building, Portobello Street, Sheffield S1 3JD, United Kingdom;1. Center for Applied Energy Research, University of Kentucky, 2540 Research Park Drive, Lexington, KY 40511, USA;2. NSLS, Brookhaven National Laboratories, Brookhaven Ave., Upton, NY 11973, USA;1. Department of Pediatrics, Division of Neonatology, Children''s Hospital of Eastern Ontario (CHEO), University of Ottawa, Ottawa, Canada;2. Division of Neonatology, Department of Pediatrics, Meir Medical Center, Kfar Saba, Israel;3. Sackler Faculty of Medicine, University of Tel Aviv, Tel Aviv, Israel;4. Clinical Research Unit, Children’s Hospital of Eastern Ontario, Ottawa, Ontario, Canada;5. Neurophysiology Lab, Division of Neurology, Children''s Hospital of Eastern Ontario (CHEO), University of Ottawa, Ottawa, Canada;6. Department of Pediatrics, Division of Neurology, British Columbia Children''s Hospital, University of British Columbia, Vancouver, Canada;7. Department of Pediatrics, Division of Neurology, Children''s Hospital of Eastern Ontario (CHEO), University of Ottawa, Ottawa, Canada |
| |
| Abstract: | This paper illustrates how a neural net, a three-layered perceptron, can be trained to estimate viscosities for undefined crude oils and fractions. Three Saudi-Arabian crude oils were employed to illustrate the use of the neural net to approximate the relation in a very simple manner with no need for a priori knowledge of the system. This empirical correlation was accurate to 98.74% if tested on experimental data not used during training, which is a fivefold improvement on average results obtained by two recently-proposed equations to estimate the viscosity of hydrocarbons. Although the neural net equation seems to be less transparent than former correlations, a method called backward analysis is proposed to analyze the weight matrix of the neural net in order to gain valuable insight into the viscosity system. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
