Particle Size Analysis of Nanopowders Using Neural Networks and Electron Microscopy

The purpose of the research is to develop an application capable of automatically determining the particle size distribution of nanopowder using neural network technology in order to simplify the process of preparing documentation during its manufacture.

Methods. To determine the physical properties of nanopowders during their fabrication, it is necessary to analyze the particle size distribution. A methodology for determining the size distribution of nanopowder particles based on light neural networks is proposed. Images obtained by electron microscopy are used for processing, which allows to speed up the preparation of manufactured powders for sale. The dataset collected for training contains real images of samples of different powders, augmented data and generated images. The Python language, LabVIEW graphical programming environment, YOLO convolutional neural network and various Python language libraries were used in the development.

Results. The study resulted in a model trained on the collected dataset that is capable of recognizing particles in images. A software interface was created to work with the model to analyze nanopowder samples.

Conclusion. The developed application allows to automatically determine the size of each powder particle on the basis of the obtained images, as well as to build graphs of their size distribution. This greatly simplifies the work of nanopowder producers and facilitates the preparation of the necessary documentation for the produced product.

1. Michalski J., Wejrzanowski T., Pielaszek R., Konopka K. Application of image analysis for characterization of powders. Materials Science – Poland, 2005, vol. 23, no. 1, pp. 79‒ 86.

2. Gadalov V. N., Gubanov O. M., Vornacheva I. V., Petrenko V. R., Makarova I. A. Obzor kompozicionnyh metallopolimerov, uprochnennyh nano- i ul'tradispersnymi chasticami [Overview of composite metal polymers reinforced with nano- and ultradisperse particles]. Uprochnyayushchie tekhnologii i pokrytiya = Hardening Technologies and Coatings, 2021, vol. 17, no. 9 (201), pp. 424‒432.

3. Gadalov V. N., Gubanov O. M., Petrenko V. R., Filonovich A. V. Fiziko-himicheskoe i matematicheskoe opisanie diffuzionnyh processov pri svarke poroshkovyh materialov [Physico-chemical and mathematical description of diffusion processes in welding of powder materials]. Spravochnik. Inzhenernyj zhurnal = Handbook. Engineering Magazine, 2023, vol. 4, no. 313, pp. 3‒9.

4. Kroetsch D., Wang C. Particle size distribution. Soil Sampling and Methods of Analysis, 2008, vol. 2, pp. 713‒725.

5. Gadalov V. N., Sal'nikov V. G., Ageev E. V., Romanenko D. N. Metallografiya metallov, poroshkovyh materialov i pokrytij, poluchennyh elektroiskrovymi sposobami [Metallography of metals, powder materials and coatings obtained by electric spark methods]. Upravlenie personalom i intellektual'nymi resursami v Rossii [Personnel management and intellectual resources in Russia]. Moscow, Infra Publ., 2011. 468 p.

6. Gadalov V. N., Gubanov O. M., Alymov D. S., Filonovich A. V., Vornacheva I. V. Razrabotka tekhnologii proizvodstva i termicheskaya obrabotka poroshkovogo titanovogo splava TI6,1AL5,4V1,8SN [Development of production technology and heat treatment of powder titanium alloy TI6,1AL5,4V1,8SN]. Zagotovitel'nye proizvodstva v mashinostroenii = Procurement Production in Mechanical Engineering, 2021, vol. 19, no. 6, pp. 276‒280.

7. Proizvoditel' poroshkov Slam Metal Powder ‒ Poroshok TiAl4822 [Manufacturer of Slam Metal Powder ‒ Powder TiAl4822]. Available at: https://www.slammetalpowder.com/ru/tovar/tial4822-powder/. (accessed 15.09.2023)

8. Google Colaboratory. Available at: https://colab.research.google.com/. (accessed 01.09.2023)

9. Repozitorij LabelImg [The Labeling repository]. Available at: https://github.com/tzutalin/labelImg. (accessed 02.09.2023)

10. Seaborn: statistical data visualization. Available at: https://seaborn.pydata.org/. (accessed 05.09.2023)

11. Tomakova R. A., Tomakov M. V., Durakov I. V., Zhilin V. V. Metod klassifikacii rentgenogramm na osnove ispol'zovaniya global'noj informacii ob ih strukture [Method of classification of radiographs based on the use of global information about their structure]. Biomedicinskaya radioelektronika = Biomedical Radioelectronics, 2016, no. 9, pp. 45‒51.

12. Tomakova R. A., Filist S. A., Naser A. A. Nechetkie nejrosetevye tekhnologii dlya vydeleniya segmentov s patologicheskimi obrazovaniyami i morfologicheskimi strukturami na medicinskih izobrazheniyah [Fuzzy neural network technologies for identifying segments with pathological formations and morphological structures in medical images]. Biomedicinskaya radioelektronika = Biomedical Radioelectronics, 2012, no. 4, pp. 43‒50.

13. Dyudin M. V., Povalyaev A. D., Podval'nyj E. S., Tomakova R. A. Metody i algoritmy konturnogo analiza dlya zadach klassifikacii slozhnostrukturiruemyh izobrazhenij [Contour analysis methods and algorithms for classification problems of complex structured images]. Vestnik Voronezhskogo gosudarstvennogo tekhnicheskogo universiteta = Bulletin of the Voronezh State Technical University, 2014, vol. 10, no. 3-1, pp. 54‒59.

14. Tomakova R. A., Filist S. A., Tomakov M. V. Gibridnye tekhnologii v intellektual'nyh sistemah identifikacii lekarstvennyh sredstv [Hybrid technologies in intelligent drug identification systems]. Nejrokomp'yutery: razrabotka, primenenie = Neurocomputers: Development, Application, 2014, no. 6, pp. 31‒66.

15. Tomakova R. A., Filist S. A., ZhilinV. V., Borisovskij S. A. Programmnoe obespechenie intellektual'noj sistemy klassifikacii formennyh elementov krovi [Software of the intelligent classification system of shaped blood elements]. Fundamental'nye issledovaniya = Fundamental Research, 2013, vol. 10, no. 2, pp. 303‒307.

16. Savvin S. V., Sirota A. A. Algoritm postroeniya mnogokadrovogo sverhrazresheniya izobrazhenij v usloviyah applikativnyh pomekh na osnove glubokih nejronnyh setej [Algorithm for constructing multi-frame super-resolution of images in the conditions of applicative interference based on deep neural networks]. Komp'yuternaya optika = Computer Optics, 2022, vol. 46, no. 1, pp. 130‒138.

17. Berezhnov N. I., Sirota A. A. Universal'nyj algoritm uluchsheniya izobrazhenij s ispol'zovaniem glubokih nejronnyh setej [Universal image enhancement algorithm using deep neural networks]. Vestnik Voronezhskogo gosudarstvennogo universiteta. Seriya: Sistemnyj analiz i informacionnye tekhnologii = Bulletin of the Voronezh State University. Series: System analysis and Information Technology, 2022, no. 2, pp. 81–92.

18. Tomakova R. A., Filist S. A., Pykhtin A. I. Development and Research of Methods and Algorithms for Intelligent Systems for Complex Structured Images Classification. Journal of Engineering and Applied Sciences, 2017, vol. 12, no. 22, pp. 6039‒6041.

19. Filist S. A., Tomakova R. A., Brezhneva A. N., Malyutina I. A., Alekseev V. A. Kletochnye processory v klassfikatorah mnogokanal'nyh izobrazhenij [Cellular processors in multichannel image classifiers]. Radiopromyshlennost' = Radio Industry, 2019, no. 1, pp. 45‒52.

20. Sirota A. A., Dryuchenko M. A., Puzatyh M. S. Modelirovanie applikativnyh pomekh na izobrazheniyah s ispol'zovaniem glubokih nejronnyh setej [Modeling of applicative interference in images using deep neural networks]. Vestnik Voronezhskogo gosudarstvennogo universiteta. Seriya: Sistemnyj analiz i informacionnye tekhnologii = Bulletin of the Voronezh State University. Series: System Analysis and Information Technology, 2022, no. 4, pp. 87‒98.