An image-based multi-resolution sensor for online prediction of crystal size distribution (CSD) is proposed. The mean and standard deviation (std) of lognormal probability density function as the CSD can be predicted through the on-line sensor. Texture analysis, through wavelet-texture algorithm, as characteristic parameters to follow the crystal growth is utilized. Following nonlinear mappings consisting of artificial neural networks (ANNs) is incorporated using as inputs the texture information in conjunction with the available on-line process conditions. The output data for training the ANN models are measured manually at different sampling times as well as in a range of operating conditions. Validations against experimental data are presented for the NaCl-water-ethanol anti-solvent crystallization system.
Image-based multi-resolution-ANN approach for on-line particle size characterization
TRONCI, STEFANIA;BARATTI, ROBERTO
2013-01-01
Abstract
An image-based multi-resolution sensor for online prediction of crystal size distribution (CSD) is proposed. The mean and standard deviation (std) of lognormal probability density function as the CSD can be predicted through the on-line sensor. Texture analysis, through wavelet-texture algorithm, as characteristic parameters to follow the crystal growth is utilized. Following nonlinear mappings consisting of artificial neural networks (ANNs) is incorporated using as inputs the texture information in conjunction with the available on-line process conditions. The output data for training the ANN models are measured manually at different sampling times as well as in a range of operating conditions. Validations against experimental data are presented for the NaCl-water-ethanol anti-solvent crystallization system.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
