Application of Artificial Neural Network (ANN) in prediction of crystallization induction period

DOI

10.2991/icmii-15.2015.46How to use a DOI?

Keywords

Industrial crystallization; Artificial neural network; Induction period

Abstract

The induction period (INT) is a measure of the ability of a supersaturated solution to remain the metastable state, and it is a very important parameter to design and optimize the crystallization process. Due to the highly nonlinear dependence of INT on the process parameters such as supersaturation and concentration, the conventional models are difficult to give prediction with high accuracy. More-accurate approaches for predicting INT are greatly needed in the design and operation of industrial crystallization process. Artificial neural network (ANN), as a non-model based prediction method, does not require any assumed special mathematic function to fit the experimental data. ANN was utilized to estimate the experimentally determined INT. The simulation results showed that the ANN could give good prediction of the INT data.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Min Yuan
AU  - Yujie Gao
PY  - 2015/10
DA  - 2015/10
TI  - Application of Artificial Neural Network (ANN) in prediction of crystallization induction period
BT  - Proceedings of the 3rd International Conference on Mechatronics and Industrial Informatics
PB  - Atlantis Press
SP  - 245
EP  - 250
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmii-15.2015.46
DO  - 10.2991/icmii-15.2015.46
ID  - Yuan2015/10
ER  -