On various multi-layer perceptron and radial basis function based artificial neural networks in the process of a hot flow curve description

Journal of Materials Research and Technology

卷:14

Ivo Schindler¹  Petr Opěla²  Petr Kawulok³  Stanislav Rusz³  Rostislav Kawulok³  Horymír Navrátil³ 

[1] Faculty of Materials Science and Technology, VSB–Technical University of Ostrava, 17. Listopadu 2172/15, 70800 Ostrava–Poruba, Czech Republic;

[2] Corresponding author.;

关键词: Hot deformation behavior;    Hot flow curve description;    Multi-layer feed-forward network;    Multi-layer cascade-forward network;    Radial basis network;    Generalized regression network;   

DOI  :  

来源: DOAJ

【 摘 要 】

In recent years, the study of the hot deformation behavior of various materials is significantly marked by an increasing utilization of artificial neural networks, which are frequently employed for a hot flow curve description. This specific kind of description is commonly solved via a Feed-Forward Multi-Layer Perceptron architecture and rarely via a Radial Basis architecture. Both network architectures are compared to assess their suitability in the process of a hot flow curve description under a wide range of thermomechanical conditions. The performed survey is also aimed on the eventual utilization of corresponding modifications of both studied networks, namely on a Cascade-Forward Multi-Layer Perceptron and Generalized Regression network. The main results have shown that the Feed-Forward Multi-Layer Perceptron architecture represents a good choice if very high accuracy is a crucial goal. However, in the case of this architecture, finding the proper parameters can be time-consuming and the hardware burdensome. On the contrary, for the flow curve description the almost unused Radial Basis network offers a very easy training procedure and significantly shorter computing time under acceptable accuracy. The results of the submitted research should then serve as a background for the selection and following application of a suitable network architecture in the process of solving future flow curve description tasks.

【 授权许可】

Unknown