Modeling of the microstructural properties of (x)ZnO(1 − x)Fe₂O₃ nanocrystallines by artificial neural network and response surface methodology

详细信息    查看全文

• 作者：M.A. Louly^a ; O.M. Lemine^b ; ^{leminej@yahoo.com} ; A. Gharbi^a
• 关键词：ANN ; Mechanical milling ; Optimization ; RSM ; Simulation
• 刊名：Measurement
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：95
• 期：Complete
• 页码：70-76
• 全文大小：1629 K
• 卷排序：95

文摘

In this work, artificial neural network and response surface methodology (RSM) models were developed for the analysis and prediction of the microstructural properties (x)ZnO(1 − x)Fe2O3 nanocrystallines produced by mechanical milling process. The input parameters are milling times and concentration. The lattice parameters (a,c) and crystallite size are the outputs of the models. The ability of ANN and RSM methods for the optimization of mechanical milling process is investigated. The results of two methods were compared based on their predictive capabilities in terms of the coefficient of determination (R2). It was found that ANN model is much more accurate in prediction as compared to RSM even the small numbers of experiments.