Application of neural networks for determina11on of friction coefficient in sheet metal forming

F. Stachowicz, T. Trzepieciński

Politechnika Rzeszowska.

DOI:

https://doi.org/10.7494/cmms.2004.3.0057

Abstract:

Friction between the sheet and tools is one of the important factors affecting the quality of drawpiece, so that the clarification of the friction is essential for modeling and analysis of sheet metal forming processes. Friction is a complex variable that results from the interactions between the sheet metal surfaces, the surface of forming tools and the lubricant used. Since analytical expression of the friction coefficient between tool and formed material is difficult to achieve, the Multi-layer Perceptron (MLP) was trained using measured process data of friction test. The MLP had surface roughness parameters and test condition (lubricant, load) as input, and friction coefficient as output. It was confirmed that this system is a valid alternative for the quick responsible method of friction coefficient determination.

Cite as:

Stachowicz, F., Trzepieciński, T. (2004). Application of neural networks for determina11on of friction coefficient in sheet metal forming. Computer Methods in Materials Science, 4(3), 87 – 97. https://doi.org/10.7494/cmms.2004.3.0057

Article (PDF):

Keywords:

References: