Modelización de los procesos de conformado en caliente de los aceros microaleados de medio carbono mediante la aplicación de redes neuronales artificiales
In this thesis a study was performed to obtain a model of artificial neural network that is able to predict the flow behavior of steel under hot deformation conditions. The hot compression tests are performed on two types of steels: medium carbon micro alloyed steels, with different conditions auste...
| Autor: | |
|---|---|
| Tipo de recurso: | tesis doctoral |
| Fecha de publicación: | 2015 |
| País: | España |
| Institución: | Universitat Politècnica de Catalunya (UPC) |
| Repositorio: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | español |
| OAI Identifier: | oai:upcommons.upc.edu:2117/95798 |
| Acceso en línea: | https://hdl.handle.net/2117/95798 https://dx.doi.org/10.5821/dissertation-2117-95798 |
| Access Level: | acceso abierto |
| Palabra clave: | Aceros microaleados de medio carbono Acero dúplex moldeado Modelo dinámico de materiales Modelización Perceptron multicapa Redes neuronales artificiales Mapas de procesado Backpropagation Àrees temàtiques de la UPC::Enginyeria mecànica |
| Sumario: | In this thesis a study was performed to obtain a model of artificial neural network that is able to predict the flow behavior of steel under hot deformation conditions. The hot compression tests are performed on two types of steels: medium carbon micro alloyed steels, with different conditions austenitizing and molded duplex steel. or the neural network model the Multilayer Perceptron (MLP) with backpropagation learning algorithm was used. The inputs to the network are temperature, strain and strain rate. The output is te yield stress. We used four statistical methods to generalize the results. Once the neural network is trained obtain stress-strain curves. Then we determine processing maps using criteria based on the dynamic model of materials (DMM) and the phenomenological approach. The stress train curves and processing maps obtained by the neural network are very similar to the experimental. For dynamic stability criteria areas of maps of the neural network correspon to areas of experimental stability. Phenom enological criteria gives us little information on the stability of the shaped areas for steels studied. In conclusion we can consider that the proposed neural network model can be used as an alternative method in hot forming of different steels. |
|---|