Please use this identifier to cite or link to this item:
|Title:||Prediction of the amount of PCA for mechanical milling|
|Authors:||Zhang, Y.F. |
|Source:||Zhang, Y.F.,Lu, L.,Yap, S.M. (1999-05-19). Prediction of the amount of PCA for mechanical milling. Journal of Materials Processing Technology 89-90 : 260-265. ScholarBank@NUS Repository. https://doi.org/10.1016/S0924-0136(99)00042-4|
|Abstract:||Process control agent (PCA) can strongly influence the size of ball milled powder particles. Experimental results show that the mean particle size is affected by: (1) the types of the PCA, (2) the amount of PCA, and (3) the milling duration. Two kinds of materials, namely Al and Mg, were used in the experiment and analysis of the influence of process control agent. It was found that there is a critical amount of process control agent below which the size of the powder particles tends to increase and above which it tends to decrease. In order to predict the amount of PCA required for a particular mean particle size under a particular milling duration resulting from a particular mechanical alloying process, a back-propagation neural network is employed. For each combination of base material and PCA, a neural network is trained using experimental data to achieve the correlation between the amount of PCA and a given particle size under a particular milling duration, i.e., PCA amount=f(particle size, milling duration). The testing results show that the trained networks have a fairly good generalization capability.|
|Source Title:||Journal of Materials Processing Technology|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Dec 13, 2017
checked on Dec 15, 2017
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.