Apparent viscosity prediction of alumina–paraffin suspensions using artificial neural networks
- 作者：Drago Torkar ; Saš ; a Novak ; Franc Novak
- 关键词：Low-pressure injection moulding ; Ceramics ; Viscosity prediction ; Artificial neural networks
- 刊名：Journal of Materials Processing Technology
- 出版年：2008
- 期刊代码：102_09240136
- 类别：et
- 出版时间：18 July 2008
- 卷：203
- 期：1-3
- 页码：208-215
- 文件大小：761 K
摘要
A neural network model has been developed for the prediction of apparent viscosity of alumina–paraffin suspensions used in low-pressure injection moulding (LPIM) process. The model is based on a three-layer neural network with a backpropagation-learning algorithm. The training data were collected by the rotational viscometry followed by a nonlinear regression. The network is trained to predict the values of power-law model parameters suitable to describe non-Newtonian fluids. A comparison between experimental values and those predicted by the neural network shows a good coincidence. The approach helps to reduce the amount of experiments required to determine these constants in practice.