Online time-sequence incremental and decremental least squares support vector machines for engine air-ratio prediction

Abstract

Fuel efficiency and pollution reduction relate closely to air-ratio (i.e. lambda) control among all the engine control variables. Lambda indicates the amount that the actual available air-fuel ratio mixture differs from the stoichiometric air-fuel ratio of the fuel being used. Accurate lambda prediction is essential for effective lambda control. This paper employs an emerging online time-sequence incremental algorithm and proposes one novel online time-sequence decremental algorithm based on least squares support vector machines (LS-SVMs) to continually update the built LS-SVM lambda function whenever a sample is added to, or removed from, the training dataset. Moreover, the online time-sequence algorithm can also significantly shorten the function updating time as compared with function retraining from scratch. In order to evaluate the effectiveness of this pair of online time-sequence algorithms, three lambda time series obtained from experiments under different operating conditions are employed. The prediction results of the online time-sequence algorithms over unseen cases are compared with those under classical LS-SVMs, typical decremental LS-SVMs, and neural networks. Experimental results show that the online time-sequence incremental and decremental LS-SVMs are superior to the other three typical methods.

Keywords

online least squares support vector machines time sequence air ratio lambda prediction

Get full access to this article

View all access options for this article.

References

Manzie

Palaniswami

Watson

Gaussian networks for fuel injection control. Proc. IMechE, Part D: J. Automobile Engineering, 2001, 215(D10), 1053–1068. DOI: 10.1243/095440701152861710.1243/0954407011528617.

Manzie

Palaniswami

Ralph

Watson

Model predictive control of a fuel injection system with a radial basis function network observer. J. Dyn. Sys. Measure. Contr., Trans. ASME, 2002, 124(4), 648–658.

G. Y.

Application on intelligent control and MATLAB to electronically controlled engines, 2007 (Publishing House of Electronics Industry, Beijing, China). In Chinese.

Rototest Research Institute. Performance measurements on chassis dynamometers, 2005, available from www.rototest.com.

Deo

M. C.

Forecasting wind with neural networks. Mar. Struct., 2003, 16, 35–49.

Han

Wang

Analysis and modeling of multivariate chaotic time series based on neural network. Expert Sys. Appl., 2009, 36, 1280–1290.

Celik

Arcaklioglu

Performance maps of a diesel engine. App. Energy, 2005, 81, 247–259.

Hashemi

Clark

N. N.

Artificial neural network as a predictive tool for emissions from heavy-duty diesel vehicles in Southern California. Int. J. Engine Res., 2007, 8(4), 321–336.

Wang

Zhang

Cai

Wang

Prediction of chaotic time series using LS-SVM with automatic parameter selection. In Proceedings of 6th IEEE International Conference on Parallel and Distributed Computing, Applications and Technologies, Dalian, China, 5–8 September 2005 (IEEE Computer Society Press, Los Alamitos, California), pp. 962–965.

10.

Haykin

Neural networks: a comprehensive foundation, edition 2, 1999 (Prentice Hall).

11.

Valyon

Horvath

A sparse least squares support vector machine classifier. In Proceedings of IEEE International Joint Conference on Neural Networks, Budapest, Hungary, 25–29 July 2004 (IEEE, Piscataway, New Jersey), vol. 1, pp. 543–548.

12.

Suykens

De Brabanter

Lukas

Vandewalle

Least squares support vector machines, edition 1, 2002 (World Scientific Press).

13.

Shi

Han

Support vector echo-state machine for chaotic time-series prediction. IEEE Trans. Neural Networks, 2007, 18(2), 359–372.

14.

Vong

C. M.

Wong

P. K.

Zhang

Incremental modelling of automotive engine performance using LS-SVM. In Proceedings of 2009 IEEE International Conference on Information and Automation, Zhuhai/Macau, China, 22–25 June 2009 (IEEE, Piscataway, New Jersey), pp. 1537–1540.

15.

Golub

Van Loan

Matrix computations, 1989 (Johns Hopkins University Press, Baltimore, MD).

16.

Suykens

Van Gestel

De Brabanter

De Moor

Vandewalle

Weight least squares support vector machines: robustness and sparse approximation. Neurocomputing, 2002, 48(1–4), 85–105.

17.

Cauwenberghs

Poggio

Incremental and decremental support vector machine learning. In Advances in neural information processing systems (Eds Leen

T. K.

Dietterich

T. G.

Tresp

), 2001, vol. 13, pp. 409–415 (MIT Press, Cambridge, MA).

18.

Cao

Zhu

Modeling and control of PEMFC based on least squares support vector machines. Energy Conv. Manage., 2006, 47, 1032–1050.