Title: Data preprocessing and modelling of electronically-controlled automotive engine power performance using kernel principal components analysis and least squares support vector machines

Authors: Pak-Kin Wong, Chi-Man Vong, Lap-Mou Tam, Ke Li

Addresses: Faculty of Science and Technology, Department of Electromechanical Engineering, University of Macau, Macao, China. ' Faculty of Science and Technology, Department of Computer and Information Science, University of Macau, Macao, China. ' Faculty of Science and Technology, Department of Electromechanical Engineering, University of Macau, Macao, China. ' Faculty of Science and Technology, Department of Electromechanical Engineering, University of Macau, Macao, China

Abstract: Modern automotive engines are controlled by the Electronic Control Unit (ECU). The engine ECU calibration is done empirically through tests on the dynamometer because no exact mathematical engine model is yet available. With Least Squares Support Vector Machines (LS-SVM), the approximate engine power performance model can be determined by training the sample data acquired from the dynamometer. Besides, Kernel Principal Components Analysis (KPCA) is proposed to transform unimportant adjustable variables into a compact subset for shortening model construction time and improving model accuracy. Experimental results show that KPCA+LS-SVM can really improve the training time and accuracy of an engine model.

Keywords: LS-SVM; least squares support vector machines; SVM; KPCA; kernel principal components analysis; PCA; automotive engine power; engine performance modelling; vehicle engines; training time; accuracy.

DOI: 10.1504/IJVSMT.2008.025406

International Journal of Vehicle Systems Modelling and Testing, 2008 Vol.3 No.4, pp.312 - 330

Published online: 21 May 2009 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article