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

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