Advanced hybrid neural network automotive friction component model for powertrain system dynamic analysis. Part 1: Model development

Abstract An accurate and easy-to-implement dynamic friction component model is necessary for powertrain system design and performance studies. A neural network approach developed by Cao et al. [1] for friction component modelling has illustrated some very promising results. However, this model has complex architecture that may lead to reduced training efficiency; also, owing to the lack of time information, the network cannot adapt to time step variations. Therefore, it cannot be easily integrated with powertrain system models, which in general require variable time steps for superior numerical integration performance. In this paper, a new first-principle-based hybrid network friction component model, the advanced hybrid neural network (AHNN), is derived for dynamic engagement analysis with variable time steps. With improvement over the previous work by Cao et al. [1], the time pattern information is added to the inputs and a simpler architecture is developed through more explicit utilization of the physical laws. With these new features, the AHNN model can significantly out-perform the previous approach. The network is trained and tested using experimental data as well as analytical results. It is shown that this new model can compensate for time step variations and can predict the friction component torque accurately for a wide range of operating conditions. This is Part 1 of a two-part paper. In Part 2, the AHNN friction component model is integrated with a powertrain model and implemented for system simulations.

[1]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[2]  W. E. Tobler,et al.  Prediction of wet band brake dynamic engagement behaviour Part 1: Mathematical model development , 2001 .

[3]  Edward J. Berger,et al.  Analytical and Numerical Modeling of Engagement of Rough, Permeable, Grooved Wet Clutches , 1997 .

[4]  B. Irie,et al.  Capabilities of three-layered perceptrons , 1988, IEEE 1988 International Conference on Neural Networks.

[5]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[6]  W. E. Tobler,et al.  Prediction of wet band brake dynamic engagement behaviour Part 2: Experimental model validation , 2001 .

[7]  D. Joseph,et al.  Boundary conditions at a naturally permeable wall , 1967, Journal of Fluid Mechanics.

[8]  Shinichi Natsumeda,et al.  Numerical Simulation of Engagement of Paper Based Wet Clutch Facing , 1994 .

[9]  Kon-Well Wang,et al.  A Hybrid Neural Network Approach for the Development of Friction Component Dynamic Model , 2004 .

[10]  Moustafa El-Gindy,et al.  Possible application of artificial neural networks to vehicle dynamics and control: a literature review , 1993, International Journal of Vehicle Design.

[11]  L. Ting.  Engagement behavior of lubricated porous annular disks. Part I: Squeeze film phase — surface roughness and elastic deformation effects , 1975 .

[12]  Wu Hai,et al.  A review of porous squeeze films , 1978 .