Prediction of Fuel Consumption per 100km for Automobile Engine Based on Gaussian Processes Machine Learning

Abstract:

Article Preview

Gaussian processes (GP) is a machine learning method which has become a power tool for solving highly nonlinear problems. Aiming to the fact that it is still difficult to reasonably determine the fuel consumption per 100km for automobile engine,the model based on GP machine learning was proposed for prediction the fuel consumption per 100km for automobile engine. According to few training samples,the nonlinear mapping relationship between the fuel consumption per 100km and its influencing factors was established by GP machine learning model. The model was applied to a real engineering. The results of study showed that GP machine learning model is feasible, effective and simple to implement for prediction the fuel consumption. It has the merits of self - adaptive parameters determination and excellent capacity for solving nonlinear small samples problems.

Info:

Periodical:

Edited by:

Shengyi Li, Yingchun Liu, Rongbo Zhu, Hongguang Li, Wensi Ding

Pages:

1951-1955

Citation:

X. Xu and Y. Zhao, "Prediction of Fuel Consumption per 100km for Automobile Engine Based on Gaussian Processes Machine Learning", Applied Mechanics and Materials, Vols. 34-35, pp. 1951-1955, 2010

Online since:

October 2010

Authors:

Export:

Price:

$41.00

[1] S. K. Wang, F. Z. Men, X. Q. Xu and H. Lan, Fatigue Reliability Test Study of Automobile Engine Roller Chain, China Mechanical Engineering, vol. 20, no. 21, pp.2642-2645, (2009).

[2] M. Girolami, S. Rogers, Variational Bayesian multinomial probit regression with Gaussian process priors, Neural Computation, vol. 18, no. 8, pp.1790-1817, (2006).

DOI: https://doi.org/10.1162/neco.2006.18.8.1790

[3] R. B. Gramacy, An R package for Bayesian nonstationary, semiparametric nonlinear regression and design by treed Gaussian process models, Journal of Statistical Software, vol. 19, no. 19, pp.1-46, (2007).

DOI: https://doi.org/10.18637/jss.v019.i09

[4] C. E. Rasmussen and C. K. I. Williams, Gaussian Processes for Machine Learning, 1st ed., Cambridge, MIT Press, (2006).

[5] H. S. Oh, J. J. Woo, Reproducing Polynomial (singularity) Particle Methods And Adaptive Meshless Methods For Two-dimensional Elliptic Boundary Value Problems, Computer Methods in Applied Mechanics and Engineer , vol. 198, pp.933-946, (2009).

DOI: https://doi.org/10.1016/j.cma.2008.11.005