每年出版 4 期
ISSN 打印: 2152-2057
ISSN 在线: 2152-2073
Indexed in
PREDICTION OF EROSION WEAR OF GRANITE-FILLED JUTE−EPOXY COMPOSITES USING AN ARTIFICIAL NEURAL NETWORK
摘要
The erosion wear process is considered as a complex nonlinear problem due to its operating variables. The wear process depends on various parameters such as impact velocity, impingement angle, material, erodent size, etc. In order to obtain a minimum erosion rate, experiments have to be conducted on a material with a combination of these parameters. Therefore, it becomes expensive and time consuming for finding out the minimum erosion rate of a material. In this regard, an artificial neural network (ANN) is a robust tool for predicting the erosion rate of a material. ANN is capable of representing nonlinear systems and can be applied to a wide variety of fields. In the present work, waste granite powder is used as a filler in a jute fiber-reinforced−epoxy composite. Four different weight proportions of granite (0, 5, 10, and 15 wt.%) are used to fabricate four different composites. It is observed that the predicted values of erosion rate have shown good agreement with experimental values.