Authors: Tao-tao Jin, Ping-kang Li
Addresses: School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, 3 Shangyuancun, Xizhimenwai, Beijing 100044 P.R. China. ' School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, 3 Shangyuancun, Xizhimenwai, Beijing 100044 P.R. China
Abstract: In the automatic transmission systems, the availability of pressure information of a hydraulic actuator makes it possible to improve the fuel economy, reduce emission and enhance driving performance. It is still hard to get an accurate model that reflects the non-linear character of the hydraulic actuators through the routine methods. Although neural networks are quite useful in modelling of the routine non-linear systems, the returning parameters of the networks, i.e., the weights and bias, have no actual sense but some numeric values. This paper presents a radial basis function (RBF) neural network-based algorithm to estimate the parameters of the hydraulic actuator in a vehicle power transmission control system. The trained results of the networks are the parameters of the transfer function of the actuator. By means of experiments, it is shown that the proposed model can describe the main phenomena characterising of the hydraulic actuator dynamics well.
Keywords: transmission hydraulic actuators; modelling; radial basis function; RBF; neural networks; transfer function; parameters identification; shift quality control; hydraulic pressure; power transmission control; vehicle transmission; actuator dynamics.
International Journal of Modelling, Identification and Control, 2009 Vol.8 No.2, pp.148 - 157
Available online: 27 Oct 2009 *Full-text access for editors Access for subscribers Purchase this article Comment on this article