Title :
Automotive engine modelling based on online time-sequence incremental and decremental least-squares support vector machines
Author :
Zhuo Yang ; Shaojia Huang ; GongRui Sun ; Zhenyu Deng
Author_Institution :
Dept. of Mech. & Automotive Eng., Jilin Univ., Jilin, China
Abstract :
Air-ratio relates closely to engine emissions, power and fuel consumption among all of the engine parameters. The thesis proposed an online time-sequence incremental and decremental least-squares support vector machines (OLSSVM) for engine modelling to predict the air-ratio. Experimental results show that the proposed OLSSVM can effectively predict the air-ratio to the target values under varies operating conditions and is superior to the air-ratio models available in the recent literatures. Therefore, the proposed OLSSVM is a promising scheme for automotive engine modelling.
Keywords :
engines; least squares approximations; mechanical engineering computing; support vector machines; OLSSVM; air-ratio models; automotive engine modelling; decremental least-squares support vector machines; online time-sequence incremental SVM; operating conditions; Accuracy; Adaptation models; Atmospheric modeling; Computational modeling; Engines; Mathematical model; Predictive models; OLSSVM; air-ratio; air-ratio models;
Conference_Titel :
Advanced Research and Technology in Industry Applications (WARTIA), 2014 IEEE Workshop on
Conference_Location :
Ottawa, ON
DOI :
10.1109/WARTIA.2014.6976328
