Monitoring of a Sugar Crystallization Process with Fuzzy Logic and Digital Image Processing

The sugar crystallization process is a solid–liquid separation where molecules are transferred from a solute dissolved in a liquid phase to a solid phase. The aim of this research is to present a monitoring computational framework to model sugar crystallization process based on expert knowledge using fuzzy logic and digital image techniques from direct samples of crystallization slurries, which determine the size of sugar crystals. The framework acquires images that feed a diffuse network automatically. Therefore, it is determined when displaying an image to various times in the process of crystallization. This allows us to know the growth behavior and to determine the optimum crystallization of the sugar crystals. The results show that using fuzzy logic techniques with digital images can be incorporated as a complementary tool for monitoring a sugar crystallization process. Practical Application In the sugar industry, it is very important to have a monitoring system for the crystallization process of sugar. This kind of system for the monitoring process can generate products of the highest quality and can facilitate energy savings in the industry. Moreover, the image processing-based systems can also be used as a visual monitoring tool for the sugar crystallization process, allowing to improve the final quality of the products and to optimize the manufacturing process.

[1]  Da-Wen Sun,et al.  Recent developments and applications of image features for food quality evaluation and inspection – a review , 2006 .

[2]  Nicolas Vandenbroucke,et al.  Color image segmentation by pixel classification in an adapted hybrid color space. Application to soccer image analysis , 2003, Comput. Vis. Image Underst..

[3]  Automated classification of crystallization experiments using wavelets and statistical texture characterization techniques , 2008 .

[4]  M. Louhi-Kultanen,et al.  In-line image analysis on the effects of additives in batch cooling crystallization , 2006 .

[5]  Marco Loog,et al.  Scale selection for supervised image segmentation , 2012, Image Vis. Comput..

[6]  Julian Morris,et al.  On-line monitoring of a sugar crystallization process , 2005, Comput. Chem. Eng..

[7]  Ebrahim H. Mamdani,et al.  An Experiment in Linguistic Synthesis with a Fuzzy Logic Controller , 1999, Int. J. Hum. Comput. Stud..

[8]  A. Ferreira,et al.  Sucrose crystal growth in the presence of dextran of different molecular weights , 2012 .

[9]  A. Marangoni,et al.  3D fractal dimension of fat crystal networks , 2006 .

[10]  J. Ulrich,et al.  Ultrasonic crystallization monitoring technique for simultaneous in-line measurement of liquid and solid phase , 2013 .

[11]  Jose Alvarez-Ramirez,et al.  Characterization of cane sugar crystallization using image fractal analysis , 2010 .

[12]  Menghan Hu,et al.  The Potential of Double K‐Means Clustering for Banana Image Segmentation , 2014 .

[13]  E. H. Mamdani,et al.  Application of Fuzzy Logic to Approximate Reasoning Using Linguistic Synthesis , 1976, IEEE Transactions on Computers.

[14]  M. Nagao,et al.  Effects of tilting mirrors on the solid-liquid interface during floating zone growth using tilting-mirror-type infrared-heating image furnace , 2010 .

[15]  V. Solomatov Batch crystallization under continuous cooling: analytical solution for diffusion limited crystal growth , 1995 .

[16]  Daniel Cremers,et al.  Image segmentation with one shape prior - A template-based formulation , 2012, Image Vis. Comput..

[17]  Mohammad Hassan Asemani,et al.  A robust H∞ observer-based controller design for uncertain T-S fuzzy systems with unknown premise variables via LMI , 2013, Fuzzy Sets Syst..

[18]  Ghenadii Korotcenkov,et al.  The role of grain size on the thermal instability of nanostructured metal oxides used in gas sensor applications and approaches for grain-size stabilization , 2012 .

[19]  Q. Smejkal,et al.  Influence of dextran concentrations and molecular fractions on the rate of sucrose crystallization in pure sucrose solutions , 2008 .

[20]  Siyi Pan,et al.  Improvement of Sugar Production From Potato Pulp with Microwave Radiation and Ultrasonic Wave Pretreatments , 2014 .

[21]  Souad Abderafi,et al.  Estimation of sucrose crystallization kinetics from batch crystallizer data , 2008 .

[22]  N. Kubota,et al.  Effect of Impurities on the Growth Kinetics of Crystals , 2001 .

[23]  P. Panigrahi,et al.  Optical imaging and three dimensional reconstruction of the concentration field around a crystal growing from an aqueous solution: A review , 2012 .

[24]  Kevin J. Roberts,et al.  Real-Time Measurement of the Growth Rates of Individual Crystal Facets Using Imaging and Image Analysis: A Feasibility Study on Needle-shaped Crystals of L-Glutamic Acid , 2007 .

[25]  J. Álvarez-Ramírez,et al.  Effect Analysis from Dynamic Regulation of Vacuum Pressure in an Adiabatic Batch Crystallizer Using Data and Image Acquisition , 2008 .

[26]  Zhi Liu,et al.  A probabilistic fuzzy logic system for modeling and control , 2005, IEEE Transactions on Fuzzy Systems.

[27]  Richard W. Hartel,et al.  Computer modeling of sugar crystallization during drying of thin sugar films , 1999 .

[28]  Determination of metastable zone width for combined anti-solvent/cooling crystallization , 2009 .

[29]  A framework for optimization of crystal growth processes applied to VGF growth of fluorides , 2005 .

[30]  T. Someya,et al.  Formation of uniform 10-nm-scale InGaN quantum dots by selective MOCVD growth and their micro-photoluminescence intensity images , 2000 .

[31]  Jose Alvarez-Ramirez,et al.  Fractal analysis of crystallization slurry images , 2010 .

[32]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[33]  J. Boilot,et al.  3D morphology of II VI semiconductor nanocrystals grown in inverted micelles , 1999 .

[34]  Kevin J. Roberts,et al.  Multi-scale segmentation image analysis for the in-process monitoring of particle shape with batch crystallisers , 2005 .