Information Systems for Evaluation of Wheat Technological Advantages

In the practice of the food industry, high-precision and express methods for determining the technological qualities of wheat and predicting the consumer properties of its processed products are in demand. For these purposes it is promising to use a complex indicator of hardness, but today its definition is associated with low accuracy, high labor costs, the use of expensive tools. It is necessary to develop automated systems of the analysis of milled grain in the grinding lines in the milling industry. Such systems can be used to determine the purpose of the flour produced. The article describes the automated system for assessing the technological properties of grain processing products in the grinding process. The system is based on the methods of forming data of the shape and size of particles in the grain grinding streams. To do it the pictures of grinding grain particles taken by the digital camera Sony IMX219 were processed by Raspberry Pi 3 microcomputer with the software that was developed on the basis of library of computer vision algorithms OpenCV. To implement the operation of such a system in the grinding production lines, a laboratory unit was constructed. Since successful analysis of the particles by computer vision needs eliminating the effect of particle adhesion, the joint effect of electrostatic fields and vibration was used for this purpose. The optimal technical parameters were selected empirically - the electrical voltage of about 24 kV and the vibration frequency of the analyzed samples of flour grinding of about 45 Hz. To obtain high voltages the generator of short pulses based on high-frequency thyristors ТЧ63 was used. Changing the voltage supply of the generator the output voltage can smoothly be changed from 1 to 35 kV. One pin of the high-voltage power supply is grounded, the second pin is connected to the sensor-registrar of grinding particles. The algorithm of estimation of wheat hardness based on the data about shape and size of the particles in the flow of grinding grain is developed - the corresponding regression equation is formed. To assess the accuracy of the algorithm, the results of the hardness evaluation of grain samples were compared with the reference method - in terms of micro hardness - of the ability of grain to resist deformation (indentation). Micro hardness of grain was evaluated with the hardness test machine PMT-3 with a square pyramid. The established empirical dependences make it possible to estimate the hardness of grain with an accuracy of at least 3%. Due to this express assessment of the technological properties of grain processing products, it is possible to control the grinding process and adjust it to improve efficiency.

technological properties, wheat grain, products of grain processing, particle size analysis, computer vision, grain hardness, information system

1. Беркутова Н.С. Методы оценки и формирования качества зерна. М.: Росагропромиздат, 1991. 206 с.

2. Беркутова Н.С., Швецова И.А. Микроструктура пшеницы. М.: Колос, 1977. 122 с.

3. Казеннова Н.К., Шнейдер Д.В., Цыганова Т.Б. Формирование качества макаронных изделий. М.: ДеЛи принт, 2009. 100 с.

4. Калачев М.В. Малые предприятия для производства хлебобулочных и макаронных изделий. М.: ДеЛи принт, 2008. 288 с.

5. Суворов О.А., Лабутина Н.В., Карягина С.В., Погорелов А.Г. Аналитические измерения в хлебопекарном производстве // Пищевая промышленность. 2008. № 3. С. 24-25.

6. Лабутина Н.В. Технология производства хлебобулочных изделий из замороженных полуфабрикатов. Смоленск: Универсум, 2004. 236 с.

7. Медведев П.В., Федотов В.А. Информационно-измерительные системы управления потребительскими свойствами зерномучных товаров // Баранова Т.И. Современные тенденции в экономике и управлении: новый взгляд: монография. Оренбург: ООО «Агентство «Пресса», 2013. С. 35-51.

8. Мелешкина Е.П., Туляков Д.Г., Витол И.С. Реологические свойства разных видов муки и композиционных смесей // Вестник Алтайского государственного аграрного университета. 2017. № 4. С. 174-179.

9. Каллан Р. Основные концепции нейронных сетей. М.: Издательский дом «Вильямс», 2001. 287 с.

10. Buyukozturk O., Hearing B. Crack propagation in concrete composites influenced by interface fracture parameters // International Journal of Solids and Structures. 1998. No. 35. P. 4055-4066.

11. Chung O.K., Ohm J.B., Lookhart G.L., Bruns R.F. Quality characteristics of hard winter and spring wheats grown under an overwintering condition // Journal of Cereal Science. 2003. No. 37. P. 91-99.

12. Karim A.A., Norziah M.H., Seow C.C. Methods for the study of starch retrogradation // Food Chemistry. 2000. No. 71. P. 9-36.

13. Maghirang E.B., Lookhart G.L., Bean S.R., Pierce R.O., Xie F., Caley M.S., Wilson J.D., Seabourn B.W., Ram M.S., Park S.H., Chung O.K., Dowell F.E. Comparison of quality characteristics and breadmaking functionality of hard red winter and hard red spring wheat // Cereal Chemistry. 2006. No. 83. P. 520-528.

14. Parker J.R. Algorithms for Image Processing and Computer Vision. Indiana: Wiley Publishing Inc., 2010. 504 p.

15. Pomeranz Y. Composition and functionality of wheat flour components // Wheat chemistry and technology. 1988. Vol. 2. P. 219-370.

16. Rundgren K., Lyckfeldt O., Sjöstedt M. Improving Powders with Freeze Granulation // Ceramic Industry. 2003. No. 1. P. 40-44.

17. Souza E.J., Martin J.M., Guttieri M.J., O’Brien K., Habernicht D.K., Lanning S.P., Carlson G.R., Talbert L.E. Influence of genotype, environment, and nitrogen management on spring wheat quality // Crop Science. 2004. No. 44. P. 425-432.

18. Zhang H.T., Tian Y., Sun Z.Y. Research on the classification of wheat grain hardness based of the near infrared hyperspectral imaging analysis // Journal of Henan agricultural sciences. 2015. No. 44. P. 181-184.

19. Mo X.S., Huang W., Chen J.W. Test on the new national standard of wheat hardness index // Journal of flour. 2008. No. 6. P. 22-23.

20. Caporaso N., Whitworth M., Fisk I. Application of calibrations to hyperspectral images of food grains: example of wheat // Falling Number Journal of Spectral Imaging. 2016. No. 1. P. 46-52.

21. Varzakas T. Quality and safety aspects of cereals (wheat) and their products // Critical Reviews in Food Science and Nutrition. 2016. Vol. 56. No. 15. P. 2495-2510. doi:10.1080/10408398.2013.866070

22. Katyal M., Singh N., Chopra N., Kaur A. Hard, medium-hard and extraordinarily soft wheat varieties: Comparison and relationship between various starch properties // International Journal of Biological Macromolecules. 2019. No. 123. P. 1143-1149.

23. Huang M., Wang Q.G., Zhu Q.B., Qin J.W., Huang G. Review of seed quality and safety tests using optical sensing technologies // Seed Science and Technology. 2015. No. 43(3). P. 337-366. doi: 10.15258/sst.2015.43.3.16

24. Tanabata T., Shibaya T., Hori K., Ebana K., Yano M. Smart Grain: high-throughput phenotyping software for measuring seed shape through image analysis // Journal of Plant Physiology. 2012. No. 160(4). P. 1871-1880. doi:10.1104/pp.112.205120

25. Gonzalez-Dugo V., Hernandez P., Solis I., Zarco-Tejada P.J. Using high-resolution hyperspectral and thermal airborne imagery to assess physiological condition in the context of wheat phenotyping // Remote Sensing. 2015. No. 7(10). P. 13586-13605. doi:10.3390/rs71013586

26. Nuttall J.G., O’Leary G.J., Panozzo J.F., Walker C.K., Barlow K.M., Fitzgerald G.J. Models of grain quality in wheat // Field Crop Research. 2017. No. 202. P. 136-145. doi:10.1016/j.fcr.2015.12.011