Title :
Application of the Chaos-RBF Neural Network on Oil Film Parameters Identification to Gasoline Engines under Transient Conditions
Author :
Li Yuelin ; Ding Jingfeng ; Yang Wei ; Lu Dongxu
Author_Institution :
Sch. of Automotive & Mech. Eng., Changsha Univ. of Sci. & Technol., Changsha, China
Abstract :
As it was difficult to determine the transient operating conditions of oil film parameter accurately, this article put forward an oil film parameter distinguish method in the gasoline engine transient conditions based on Chaos-RBF. The recognition ability with least square method was compared and analyzed, the Chaos-RBF neural network verified model has better ability of nonlinear identification which could effectively improve the oil film dynamic parameter identification precision and oil film dynamic characteristics under different working conditions was obtained.
Keywords :
internal combustion engines; least squares approximations; mechanical engineering computing; parameter estimation; radial basis function networks; chaos-RBF neural network verified model; gasoline engines; least square method; nonlinear identification; oil film dynamic characteristics; oil film dynamic parameter identification precision; recognition ability; transient condition; Calibration; Chaos; Engines; Films; Fuels; Mathematical model; Neural networks; FPGA; Intel8080 interface; SDRAM; STM32; altlvds_tx;
Conference_Titel :
Intelligent Systems Design and Engineering Applications, 2013 Fourth International Conference on
Conference_Location :
Zhangjiajie
Print_ISBN :
978-1-4799-2791-3
DOI :
10.1109/ISDEA.2013.438
