Neurocomputing
Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Fundamentals of neural networks: architectures, algorithms, and applications
Fundamentals of neural networks: architectures, algorithms, and applications
Neural network design
| Hi-index | 0.00 |
The objective of this paper is to estimate realistic principal extrusion process parameters by means of artificial neural network. Conventionally, finite element analysis is used to derive extrusion process parameters. However, the finite element analysis of the extrusion model does not consider the manufacturing process constraints in its modeling. Therefore, the process parameters obtained through such an analysis remains highly theoretical. Alternatively, process development in industrial extrusion is to a great extent based on trial and error and often involves full-size experiments, which are both expensive and time-consuming. The artificial neural network-based estimation of the extrusion process parameters prior to plant execution helps to make the actual extrusion operation more efficient because more realistic parameters may be obtained. And so, it bridges the gap between simulation results and the parameters required by a real manufacturing execution system. In this work, the feasibility of making use of neural networks to predict realistic principal extrusion process parameters is studied. In the course, a suitable neural network is designed which is trained using an appropriate learning algorithm. The network so trained is used to predict the extrusion process parameters.