ArticlesNo Access

COMPARATIVE ANALYSIS ON NONLINEAR MODELS FOR RON GASOLINE BLENDING USING NEURAL NETWORKS

R. CARREÑO AGUILERA

Instituto Politecnico Nacional, Zacatenco. Av. IPN S/N. Colonia Lindavista, 07738. Ciudad de México, Mexico

E-mail Address: ricardo.carreno@hotmail.com

Corresponding author.

Search for more papers by this author

WEN YU

Cinvestav, Zacatenco. Av. IPN 2508. Colonia San Pedro Zacatenco, 07360. Ciudad de México, Mexico

Search for more papers by this author

J. C. TOVAR RODRÍGUEZ

Instituto Politecnico Nacional, Zacatenco. Av. IPN S/N. Colonia Lindavista, 07738. Ciudad de México, Mexico

Search for more papers by this author

M. ELENA ACEVEDO MOSQUEDA

Instituto Politecnico Nacional, Zacatenco. Av. IPN S/N. Colonia Lindavista, 07738. Ciudad de México, Mexico

Search for more papers by this author

M. PATIÑO ORTIZ

Instituto Politecnico Nacional, Zacatenco. Av. IPN S/N. Colonia Lindavista, 07738. Ciudad de México, Mexico

Search for more papers by this author

J. J. MEDEL JUAREZ

Instituto Politecnico Nacional, Zacatenco. Av. IPN S/N. Colonia Lindavista, 07738. Ciudad de México, Mexico

Search for more papers by this author

, and

D. PACHECO BAUTISTA

Universidad del Istmo Campus Tehuantepec Av. Universidad S/N, Santa Cruz de Tagolaba Tehuantepec, OAX, Mexico

Search for more papers by this author

https://doi.org/10.1142/S0218348X17500645Cited by:2 (Source: Crossref)

Abstract

The blending process always being a nonlinear process is difficult to modeling, since it may change significantly depending on the components and the process variables of each refinery. Different components can be blended depending on the existing stock, and the chemical characteristics of each component are changing dynamically, they all are blended until getting the expected specification in different properties required by the customer. One of the most relevant properties is the Octane, which is difficult to control in line (without the component storage). Since each refinery process is quite different, a generic gasoline blending model is not useful when a blending in line wants to be done in a specific process. A mathematical gasoline blending model is presented in this paper for a given process described in state space as a basic gasoline blending process description. The objective is to adjust the parameters allowing the blending gasoline model to describe a signal in its trajectory, representing in neural networks extreme learning machine method and also for nonlinear autoregressive-moving average (NARMA) in neural networks method, such that a comparative work be developed.

Keywords:

References

1. N. Pasadakis et al., Octane number prediction for gasoline blends, Fuel Process. Technol. 2006 (2006) 505–509. Crossref, Web of Science, Google Scholar
2. W. Yu, Modeling of gasoline blending via discrete-time neural networks, Neural Netw. Proc. 2004 (2004) 6. Google Scholar
3. W. Yu, Gasoline blending system modeling via static and dynamic neural networks, Int. J. Model. Simul. 24(3) (2004) 151–160. Crossref, Google Scholar
4. W. Yu et al., Neural networks for the optimization of crude oil blending, Int. J. Neural Syst. 15(05) (2005) 377–389. Link, Web of Science, Google Scholar
5. D. Marcek, Forecasting high frequency data: An arma-soft RBF network model for time series, Decis. Mak. Soft Comput. 9 (2014) 113–118. Link, Google Scholar
6. J. Chen et al., Link prediction and route selection based on channel state detection in UASNs, Int. J. Distrib. Sens. Netw. 2011 (2011) 939864. Crossref, Web of Science, Google Scholar
7. J. Patiño et al., Seismic activity seen through evolution of the Hurst exponent model in 3D, Fractals 24(4) (2016) 10. Web of Science, Google Scholar
8. M. Choda, Around Shannon’s interpretation for entropy preserving stochastic averages, Int. J. Math. 25(10) (2014) 14. Link, Web of Science, Google Scholar
9. R. Palma, J. J. Medel and Y. G. Garrido, A m–dimensional stochastic estimator, RMFl 58(1) (2012) 69–71. Google Scholar
10. V. S. Pugachev, Theory and Mathematical Statistics for Probability Engineers (Pergamon Press, Oxford, 1984). Google Scholar
11. F. Kwasniok, Estimation of noise parameters in dynamical system identification with Kalman filters, Phys. Rev. E 86(036214) (2012) 1–8. Google Scholar
12. W. Yu and X. Li, Automated nonlinear system modeling with multiple fuzzy neural networks and kernel smoothing, Int. J. Neural Syst. 20(05) (2010) 429–435. Link, Web of Science, Google Scholar
13. W. Yu and A. Cruz, Some new stability properties of dynamic neural networks with different time scales, Int. J. Neural Syst. 16(03) (2006) 191–199. Link, Web of Science, Google Scholar
14. S. Lu et al., Nonlinear autoregressive and nonlinear autoregressive moving average model parameter estimation by minimizing hypersurface distance, IEEE Trans. Signal Process. 51(12) (2003) 3020–3026. Crossref, Web of Science, Google Scholar
15. L. Sheng and J. Hwan, A new algorithm for linear and nonlinear ARMA model parameter estimation using affine geometry, IEEE Trans. Biomed. Eng. 48(10) (2001) 1116–1124. Crossref, Web of Science, Google Scholar
16. J. J. Carrasco, ELM regularized method for classification problems, Int. J. Artif. Intell. Tools 25(01) (2016) 1550026. Link, Web of Science, Google Scholar
17. B. Sang et al., The research of signal power quality disturbance identification and classification based on the GA-ELM, Manage. Inform. Optoelectron. Eng. 2017 (2017) 233–238. Link, Google Scholar
18. G.-B. Huang, What are extreme learning machines? Filling the gap between Frank Rosenblatt’s dream and John von Neumann’s puzzle, Cogn. Comput. 7(3) (2015) 263–278. Crossref, Web of Science, Google Scholar
19. F. Kwasniok, Analysis and modeling of glacial climate transitions using simple dynamical systems, Philos. Trans. R. Soc. A, Math. Phys. Eng. Sci. 371 (20110472) (2013) 1–11. Google Scholar
20. J. Li and L. Yang, Finite-time terminal sliding mode tracking control for Piezoelectric actuators, Abstract Appl. Anal. 2014 (2014) 760937. Google Scholar
21. R. Carreño et al., A nonlinear acoustic transducer model with variable structure control, Fractals 25(02) (2017) 1750018. Link, Web of Science, Google Scholar
22. X. Liu and Q. Gao, Parameter estimation and control for a neural mass model based on the unscented Kalman filter, Phys. Rev. E 88(042905) (2013) 1–8. Google Scholar