A prediction method for the wax deposition rate based on a radial basis function neural network

Abstract

The radial basis function neural network is a popular supervised learning tool based on machinery learning technology. Its high precision having been proven, the radial basis function neural network has been applied in many areas. The accumulation of deposited materials in the pipeline may lead to the need for increased pumping power, a decreased flow rate or even to the total blockage of the line, with losses of production and capital investment, so research on predicting the wax deposition rate is significant for the safe and economical operation of an oil pipeline. This paper adopts the radial basis function neural network to predict the wax deposition rate by considering four main influencing factors, the pipe wall temperature gradient, pipe wall wax crystal solubility coefficient, pipe wall shear stress and crude oil viscosity, by the gray correlational analysis method. MATLAB software is employed to establish the RBF neural network. Compared with the previous literature, favorable consistency exists between the predicted outcomes and the experimental results, with a relative error of 1.5%. It can be concluded that the prediction method of wax deposition rate based on the RBF neural network is feasible.

Keywords

Crude oil / Prediction model / Radial basis function neural network / Wax deposition rate

References

[1] A. Kamari, A.H. Mohammadi, A. Bahadori, S. Zendehboudi, A reliable model for estimating the wax deposition rate during crude oil production and processing, Petrol. Sci. Technol. 32 (2014) 2837-2844.

[2] W.K. Su, Q.L. Cheng, W. Sun, Progress in research wax deposition model of oil pipelines, Chem. Eng. Mach. (2016) 20-23.

[3] E. Burger, T. Perkins, J. Striegler, Studies of wax deposition in the trans Alaska pipeline, J. Petrol. Technol. 33 (1981) 1075-1086.

[4] J. Hsu, M. Santamaria, J. Brubaker, Wax Deposition of Waxy Live Crudes Under Turbulent Flow Conditions, Society of Petroleum Engineers, 1994.

[5] Q.Y. Huang, Y.X. Li, J.J. Zhang, Unified wax deposition model, Acta Petrol. Sin. 29 (2008) 459-462.

[6] S.D. Zhou, M. Wu, J. Wang, Wax deposition rate model for crude oil pipeline based on neural network, J. Xi’an Shiyou Univ. Nat. Sci. Ed. 19 (2004) 38-40.

[7] T.J. Behbahani, A.A.M. Beigi, Z. Taheri, B. Ghanbari, Investigation of wax precipitation in crude oil: experimental and modeling, Petroleum 1 (2015) 223-230.

[8] X. Hu, R. Li, J. Meng, H. Xiong, J. Xia, Z. Li, Evaluation of the occurrence possibility of SNP in Brassica napus with sliding window features by using RBF networks, Wuhan Univ. J. Nat. Sci. 16 (2011) 73-78.

[9] E.P. Maillard, D. Gueriot, RBF Neural Network, Basis Functions and Genetic Algorithm, IEEE, 1997, pp. 2187-2192.

[10] Q.Y. Huang, J.J. Zhang, D.F. Yan, A new wax deposition model, Oil Gas Storage Transp. 22 (2003) 22-25.

[11] Q.Y. Huang, J.J. Zhang, X.F. Gao, Study on wax deposition of daqing crude oil, Acta Petrol. Sin. 4 (2006).

[12] J. Zhu, Urban Atmospheric Environmental Quality Evaluation Based on Grey Correlation Analysis: A Case Study on Municipalities Directly under the Central Government and Provincial Capitals, IEEE, 2010, pp. 68-71.

[13] S. Cong, Neural Network Theory and Application with MATLAB Toolboxes, third ed., USTCP, Anhui, 2009.

[14] X.L. Wang, The Wax Deposition Phenomena Prediction of Huachi Oil Pipelines, Xi’an Shiyou University, Xi’an, 2010.

[15] S.D. Zhou, M. Wu, Investigation on the model of oil pipeline wax deposition velocity, J. Liaon-ing Univ. Petrol. Chem. Technol. 24 (2004) 73-77.

[16] Z.B. Zhang, Wax Deposition Study of Crude Oil in Pipeline, China Petroleum University, Dongyin, 2009.