In this research, a new hybrid neural network is developed to model engagement behaviors of automotive transmission wet friction component. Utilizing known first principles on the physics of engagement, special modules are created to estimate viscous torque and asperity contact torque as preprocessors to a two-layer neural network. Inside these modules, all the physical parameters are represented by neurons with various activation functions derived from first principles. These new features contribute to the improved performance and trainability over a conventional two-layer network model. Both the hybrid and conventional neural net models are trained and tested with experimental data collected from an SAE#2 test stand. The results show that the performance of the hybrid model is much superior to that of the conventional model. It successfully captures detailed characteristics of the friction component engagement torque as a function of time over a wide operating range.
Skip Nav Destination
Article navigation
March 2004
Technical Papers
A Hybrid Neural Network Approach for the Development of Friction Component Dynamic Model
M. Cao,
M. Cao
Department of Mechanical and Nuclear Engineering,The Pennsylvania State University, University Park, PA 16802
Search for other works by this author on:
K. W. Wang,
K. W. Wang
Department of Mechanical and Nuclear Engineering,The Pennsylvania State University, University Park, PA 16802
Search for other works by this author on:
Y. Fujii,
Y. Fujii
Research and Advanced Engineering, Ford Motor Company, Dearborn, MI 48121
Search for other works by this author on:
W. E. Tobler
W. E. Tobler
Research and Advanced Engineering, Ford Motor Company, Dearborn, MI 48121
Search for other works by this author on:
M. Cao
Department of Mechanical and Nuclear Engineering,The Pennsylvania State University, University Park, PA 16802
K. W. Wang
Department of Mechanical and Nuclear Engineering,The Pennsylvania State University, University Park, PA 16802
Y. Fujii
Research and Advanced Engineering, Ford Motor Company, Dearborn, MI 48121
W. E. Tobler
Research and Advanced Engineering, Ford Motor Company, Dearborn, MI 48121
Contributed by the Dynamic Systems, Measurement, and Control Division of THE AMERICAN SOCIETY OF MECHANICAL ENGINEERS for publication in the ASME JOURNAL OF DYNAMIC SYSTEMS, MEASUREMENT, AND CONTROL. Manuscript received by the ASME Dynamic Systems and Control Division May 14, 2002; final revision, August 25, 2003; Associate Editor: R. Langari.
J. Dyn. Sys., Meas., Control. Mar 2004, 126(1): 144-153 (10 pages)
Published Online: April 12, 2004
Article history
Received:
May 14, 2002
Revised:
August 25, 2003
Online:
April 12, 2004
Citation
Cao , M., Wang, K. W., Fujii , Y., and Tobler, W. E. (April 12, 2004). "A Hybrid Neural Network Approach for the Development of Friction Component Dynamic Model ." ASME. J. Dyn. Sys., Meas., Control. March 2004; 126(1): 144–153. https://doi.org/10.1115/1.1649980
Download citation file:
Get Email Alerts
Global-Position Tracking Control for Multi-Domain Bipedal Walking with Underactuation
J. Dyn. Sys., Meas., Control
Surge-Elimination Strategy for Aero-Engine Transient Control
J. Dyn. Sys., Meas., Control (July 2024)
Safe Reinforcement Learning-Based Balance Control for Multi-Cylinder Hydraulic Press
J. Dyn. Sys., Meas., Control (July 2024)
Integral Sliding Mode Disturbance Observer Based Preview Repetitive Control
J. Dyn. Sys., Meas., Control
Related Articles
Development of a Friction Component Model for Automotive Powertrain System Analysis and Shift Controller Design based on Parallel-Modulated Neural Networks
J. Dyn. Sys., Meas., Control (September,2005)
Consistent and Minimal Springback Using a Stepped Binder Force Trajectory and Neural Network Control
J. Eng. Mater. Technol (January,2000)
Related Proceedings Papers
Related Chapters
Materials
Design and Application of the Worm Gear
Applications of Artificial Neural Network in Pressure Distribution Analysis of Hydrodynamic Journal Bearings
International Conference on Computer Technology and Development, 3rd (ICCTD 2011)
A Review on Prediction over Pressured Zone in Hydrocarbon Well Using Seismic Travel Time through Artificial Intelligence Technique for Pre-Drilling Planing
International Conference on Software Technology and Engineering, 3rd (ICSTE 2011)