A Hybrid Neural Network Approach精品.pdfVIP

A Hybrid Neural Network M. Cao Approach for the Development of K. W. Wang Friction Component Dynamic Department of Mechanical and Nuclear Engineering Model The Pennsylvania State University University Park, PA 16802 In this research, a new hybrid neural network is developed to model engagement behav- iors of automotive transmission wet friction component. Utilizing known first principles Y. Fujii 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 W. E. Tobler modules, all the physical parameters are represented by neurons with various activation functions derived from first principles. These new features contribute to the improved Research and Advanced Engineering performance and trainability over a conventional two-layer network model. Both the Ford Motor Company hybrid and conventional neural net models are trained and tested with experimental data Dearborn, MI 48121 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 compo