Estimation of Date Syrup Viscosity using Machine Vision and Artificial Neural Network

Document Type : Research Article

Authors

• A. A. Jafari
• E. Tatar

Department of Biosystems Engineering, Shiraz University, Shiraz, Iran

https://doi.org/10.22067/jam.v8i2.61681

Abstract

Introduction
Science of rheology has numerous applications in various fields of the food industry such as process assessment, acceptance of products and sales. Fluid behavior changes during processing due to an adverse change in the consistency and due to the combined operations such as mixing, heating, cooling, etc. In this regard, viscosity is an important factor for quality assessment in most of the materials. To measure the viscosity, Viscometer devices are used which are directly in contact with the material. Working with these devices is time consuming, costly, under the influence of human factors and in some cases periodic calibration is required.

Materials and Methods
Date syrup was used as a viscous material in this study because it industrially is produced. An apparatus including a reservoir with an outlet orifice at the bottom was made to provide free flow of the liquid. Two sets of circular and rectangular orifices with different dimensions were used to investigate the effect of the orifice characteristics on the shape of the flow. Firstly, date syrup viscosity was measured by a conventional viscometer at 5 temperature levels and 6 concentration levels and behavior of the syrup were studied. Free flow of date syrup was photographed in the aforementioned temperatures and concentrations. On the other hand extracted features from the images were used as inputs to the neural network to give outputs as a fluid flow behavior index and consistency index. Measurement data were divided to three sets including training, validation and test sets whereas 70% of the data were used for training the neural networks, 15% as the validation set and 15% for testing the networks.

Results and Discussion
Results showed that similar to most of the liquids, viscosity of date syrup decreases when temperature increases. The experiments also revealed that the date syrup behavior is expressible with power law and can be determined using power equation. Date syrup has different behavior at different concentration levels. It changes from a pseudoplastic liquid to a Newtonian and then a dilatant liquid when concentration increases. Flow behavior index and consistency index corresponding to all three behavior of the fluid were determined. Results showed that the neural networks were able to accurately estimate the behavior and consistency indices with coefficient of correlations up to 0.99. Networks with three hidden layers were completely suitable for the estimation of the indices. These results revealed that in spite of different behavior of the liquid ranged from pseudoplastic to dilatant, the method was still able to determine the apparent viscosity of the fluid. Although the circular orifices were more efficient in determination of the indices than the rectangular orifices, there was not a significant difference between the uses of circular or rectangular orifices as well as no significant different between the orifices with different dimensions. The correlation between the actual and estimated values for fluid flow behavior index and consistency index was 0.98 whereas the mean square error of the validation sets was about 0.0138 which showed the accuracy of the method.
Conclusion
In this study a new method of viscosity determination was proposed. Machine vision was employed to estimate the viscosity based on the visual characteristics of the fluid free flow. Date syrup as a liquid with different rheological behaviors was used to assess the performance of the method. The strong correlation between the extracted features and fluid flow behavior index as well as a consistency index proved the reliability and accuracy of the method for viscosity estimation.

Keywords

• Digital image processing
• Pattern Recognition
• Real time
• Viscosity

20.1001.1.22286829.1397.8.2.6.0

References

1. Cubillos, F., and A. Reyes. 2003. Design of a model based on a modular neural network approach. Drying Thechnology 21 (7): 1185-1195.

2. Jung, W., C. Hurth, A. E. Becker, and F. Zenhausern. 2015. Real-time monitoring of viscosity changes triggered by chemical reactions using a high-speed imaging method. Sensing and Bio-Sensing Research 5: 8-12.

3. Kim, S., K. C. Kim, and E. Yeom. 2017. Microfluidic method for measuring viscosity using images from smartphone. Optics and Lasers in Engineering 95: 1-7.

4. Kheloufi, N., and M. Lounis. 2015. Viscosity measurement using optical tracking of free fall in Newtonian fluid. Acta Physica Polonica 128: 123-127.

5. Kono, Y., C. Kenney-Benson, Y. Shibazaki, C. Park, G. Shen, and Y. Wang. 2015. High-pressure viscosity of liquid Fe and FeS revisited by falling sphere viscometry using ultrafast X-ray imaging. Physics of the Earth and Planetary Interiors 241: 57-64.

6. Kvaal, K., J. P. Wold, U. J. Indahl, P. Baardseth, and T. Naes. 1998. Multivariate feature extraction from textural images of bread. Chemometrics and Intelligent Laboratory Systems 42: 141-158.

7. Nassiri, S. M., A. Bakhshipour, M. M. Heydari, and M. Barzegar. 2013. Estimation of apparent viscosity of non- Newtonian fluids using machine vision. The 8th National Congress on Agricultural Engineering (Biosystem) and Mechanization. Mashhad, Iran. (In Farsi).

8. Noel, M. H., B. Semin, J. P. Hulin, and H. Auradou. 2011. Viscometer using drag force measurements. Review of Scientific Instruments 82 (2): 023909.

9. Park, N. A., F. Thomas, and Jr. Irvine. 1997. Liquid density measurements using the falling needle viscometer. International Communications in Heat and Mass Transfer 24 (3): 303-312.

10. Razavi, M. A. 2006. Biophysical Properties of Agricultural Products and Food Materials. Ferdowsi University of Mashhad Publication, Mashhad. (In Farsi).

11. Razavi, S. M. A., M. B. Habibi Najafi, and Z. Alaee. 2007. The time independent rheological properties of low fat sesame paste/date syrup blends as a function of fat substitutes and temperature. Food Hydrocolloils 21: 198-202.

12. Sabati Gavgani, M. 2008. Investigation of the recycling status of valuable materials from agricultural wastes. Monthly Magazine of Agriculture and Food, 74. (In Farsi).

13. Shin, S., S. W. Lee, and D. Y. Keum. 2001. A new mass-detecting capillary viscometer. Review of Scientific Instruments 72 (7): 3127-3128.

14. Shahiri Tabarestani, H., Y. Maghsoodlou, A. Motamedzadegan, and A. Sadeghi Mahoonak. 2008. Prediction of viscosity variation of skin gelatin of rainbow trout (Onchorhynchus mykiss) at different preprocessing time by using artificial neural network. 18th National Congress on Food Science and Technology, Mashhad, Iran. (In Farsi).

15. Wang, X., F. Song, and X. Peng. 2016. A versatile fluorescent probe for imaging viscosity and hypochlorite in living cells. Dyes and Pigments 125: 89-94.

16. Wilhelm, L. R., D. A. Suter, and G. H. Brusewitz. 2004. Physical Properties of Food Materials. Chapter 2 in Food & Process Engineering Technology, 23-52. St. Joseph, Michigan: ASAE. American Society of Agricultural Engineers.