This study is aimed to deals with artificial neural network (ANN) approach for prediction grain size (GS) of 17 - 4 pH stainless steel powders. Experimental data which were obtained from experimental studies in a laboratory environment have been used for this modeling. Using some of the experimental data for training and testing an ANN for GS was developed. In these systems, output parameters GS has been determined using input parameters including environment, time, speed, ball diameter, ball ratio, and material. When experimental data and results obtained from ANN were compared by regression analysis in Matlab, it was determined that both groups of data are consistent. The correlation coefficient between estimated GS values and experimental data obtained are 0.99 for traing and 0.98 for testing respectively. The correlation coefficient is closely to 1. This coefficient shows that there is a strong relationship between these data. Also, the accuracy rate was 98.97% for GS. As a result, it has been shown that designed ANN can be used reliably in powder metallurgic industry and engineering.
Keywords: Artificial neural network, mechanical milling, garin size.
Copyright © 2022 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0