Artificial neural network (ANN) modelling to estimate bubble size from macroscopic image and object features

• Autorzy: Vinnett Luis , León Roberto , Mesa Diego

Identyfikatory

DOI

10.37190/ppmp/185759

• Języki publikacji: EN

Abstrakty

EN

Bubble size measurements in aerated systems such as froth flotation cells are critical for controlling gas dispersion. Commonly, bubbles are measured by obtaining representative photographs, which are then analyzed using segmentation and identification software tools. Recent developments have focused on enhancing these segmentation tools. However, the main challenges around complex bubble cluster segmentation remain unresolved, while the tools to tackle these challenges have become increasingly complex and computationally expensive. In this work, we propose an alternative solution, circumventing the need for image segmentation and bubble identification. An Artificial Neural Network (ANN) was trained to estimate the Sauter mean bubble size (D32) based on macroscopic image features obtained with simple and inexpensive image analysis. The results showed excellent prediction accuracy, with a correlation coefficient, R, over 0.998 in the testing stage, and without bias in its error distribution. This machine learning tool paves the way for robust and fast estimation of bubble size under complex bubble images, without the need of image segmentation.

Słowa kluczowe

EN

machine learning; artificial neural network; flotation; bubble size; Sauter diameter

• Wydawca: Oficyna Wydawnicza Politechniki Wrocławskiej
• Czasopismo: Physicochemical Problems of Mineral Processing
• Rocznik: 2023
• Tom: Vol. 59, iss. 5
• Strony: art. no. 185759
• Opis fizyczny: Bibliogr. 59 poz., rys., tab., wykr.

Twórcy

autor

Vinnett Luis

• Department of Chemical and Environmental Engineering, Universidad Técnica Federico Santa María, Valparaíso 2390123, Chile

• https://orcid.org/0000-0001-7173-9054

autor

León Roberto

• Department of Computer Science, Universidad Técnica Federico Santa María, Valparaíso 2390123, Chile

autor

Mesa Diego

• Advanced Mineral Processing Research Group, Department of Earth Science and Engineering, Imperial College London, United Kingdom

Bibliografia

• AHMED, N., JAMESON, G. J., 1985. The effect of bubble size on the rate of flotation of fine particles. Int. J. Miner. Process. 14(3), 195-215.
• AMINI, E., BRADSHAW, D. J., FINCH, J A., BRENNAN, M., 2013. Influence of turbulence kinetic energy on the bubble size in different scale flotation cells. Miner. Eng. 45, 146-150.
• ARANCIBIA-BRAVO, M. P., LUCAY, F. A., LÓPEZ, J., CISTERNAS, L. A., 2019. Modeling the effect of air Flow, impeller speed, frother dosages, and salt concentrations on the bubbles size using response surface methodology. Miner. Eng. 132, 142-148.
• ARENDS, M. A., 2019. Reactivos de flotación: Evaluación de colectores y espumantes. Clariant: Muttenz, Switzerland.
• AZGOMI, F., GOMEZ, C. O., FINCH, J. A., 2007. Correspondence of gas holdup and bubble size in presence of different frothers. Int. J. Miner. Process. 83(1), 1-11.
• BAILEY, M., GOMEZ, C. O., FINCH, J. A., 2005. Development and application of an image analysis method for wide bubble size distributions. Miner. Eng. 18(12), 1214-1221.
• BHUNIA, K., KUNDU, G., MUKHERIEE, D., 2015. Prediction of Gas Holdup in a Flotation Column by Artificial Neural Network. Int. J. Coal Prep. Util. 35(4), 165-175.
• BISHOP, C. M., 2006. Pattern Recognition and Machine Learning (Information Science and Statistics). Springer-Verlag, Berlin, Heidelberg.
• BU, X., ZHOU, S., DANSTAN, J. K., BILAL, M., UL HASSAN, F., & CHAO, N., 2022. Prediction of coal flotation performance using a modified deep neural network model including three input parameters from feed. Energy Sources A: Recovery Util. Environ. Eff. 1-13.
• CALVERT, J. R., NEZHATI, K., 1987. Bubble size effects in foams. Int. J. Heat Fluid Flow 8(2), 102-106.
• CHEN, F., GOMEZ, C. O., FINCH, J. A., 2001. Technical note bubble size measurement in flotation machines. Miner. Eng. 14(4), 427-432.
• CHO, Y. S., LASKOWSKI, J. S., 2002. Effect of flotation frothers on bubble size and foam stability. Int. J. Miner. Process. 64(2), 69-80.
• COUTO, H. J. B., NUNES, D. G., NEUMANN, R., FRANÇA, S. C. A., 2009. Micro-bubble size distribution measurements by laser diffraction technique. Miner. Eng. 22(4), 330-335.
• CUI, Y., LI, C., ZHANG, W., NING, X., SHI, X., GAO, J., LAN, X., 2022. A deep learning-based image processing method for bubble detection, segmentation, and shape reconstruction in high gas holdup sub-millimeter bubbly flows, Chem. Eng. J. 449, 137859.
• DAI, Z., FORNASIERO, D., RALSTON, J., 2000. Particle-bubble collision models – a review. Adv. Colloid Interface Sci. 85(2), 231-256.
• FLOTTEC, 2015. Flottec F120-20 Frother, Safety Datasheet.
• GELDENHUYS, S., MCFADZEAN, B., 2019. The effect of pulp bubble size on the dynamic froth stability measurement. Miner. Eng. 131, 164-169.
• GORAIN, B. K., FRANZIDIS, J. P., MANLAPIG, E. V., 1995. Studies on impeller type, impeller speed and air flow rate in an industrial scale flotation cell – Part 1: Effect on bubble size distribution. Miner. Eng. 8(6), 615-635.
• GORAIN, B. K., FRANZIDIS, J. P., MANLAPIG, E. V., 1999. The empirical prediction of bubble surface area flux in mechanical flotation cells from cell design and operating data. Miner. Eng. 12(3), 309-322.
• GRAU, R. A., HEISKANEN, K., 2002. Visual technique for measuring bubble size in flotation machines. Miner. Eng. 15(7), 507-513.
• GRAU, R. A., LASKOWSKI, J. S., HEISKANEN, K., 2005. Effect of frothers on bubble size. Int. J. Miner. Process. 76(4), 225-233.
• HAAS, T., SCHUBERT, C., EICKHOFF, M., PFEIFER, H., 2020. BubCNN: Bubble detection using Faster RCNN and shape regression network. Chem. Eng. Sci. 216, 115467.
• HARRIS, R., NG, K. W., WRAITH, A. E., 2005. Spargers for controlled bubble size by means of the multiple slot disperser (MSD). Chem. Eng. Sci. 60(11), 3111-3115.
• HE, K., GKIOXARI, G., DOLLÁR, P., GIRSHICK, R., 2020. Mask R-CNN. PAMI 42(2), 386-397.
• HE, K., ZHANG, X., REN, S., SUN, J., 2015. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. IEEE International Conference on Computer Vision.
• HERNANDEZ-AGUILAR, J., GOMEZ, C., FINCH, J., 2002. A technique for direct measurement of bubble size distributions in industrial flotation cells. 34th Annual Meeting of the Canadian Mineral Processors.
• HESSENKEMPER, H., STARKE, S., ATASSI, Y., ZIEGENHEIN, T., LUCAS, D., 2022. Bubble identification from images with machine learning methods. Int. J. Multiph. Flow, 155, 104169.
• JUNKER, B., 2006. Measurement of bubble and pellet size distributions: past and current image analysis technology. Bioproc. Biosyst. Eng. 29(3), 185-206.
• KAM, A., ELLIS, C., ARNDT, R., HONG, J., 2015. An integrative image measurement technique for dense bubbly flows with a wide size distribution. Chem. Eng. Sci. 122, 240-249.
• KIM, Y., PARK, H., 2021. Deep learning-based automated and universal bubble detection and mask extraction in complex two-phase flows. Sci. Rep. 11(1), 8940.
• KINGMA, D. P., BA, J., 2014. Adam: A Method for Stochastic Optimization. arXiv, arXiv:1412.6980.
• KRACHT, W., EMERY, X., PAREDES, C., 2013. A stochastic approach for measuring bubble size distribution via image analysis. Int. J. Miner. Process. 121, 6-11.
• KRACHT, W., GOMEZ, C. O., FINCH, J. A., 2008. Controlling bubble size using a frit and sleeve sparger. Miner. Eng. 21(9), 660-663.
• KRACHT, W., MORAGA, C., 2016. Acoustic measurement of the bubble Sauter mean diameter d32. Miner. Eng. 98, 122-126.
• LICHTI, M., BART, H.-J., 2018. Bubble size distributions with a shadowgraphic optical probe. Flow Meas. Instrum. 60, 164-170.
• MA, Y., YAN, G., SCHEUERMANN, A., BRINGEMEIER, D., KONG, X.-Z., LI, L., 2014. Size distribution measurement for densely binding bubbles via image analysis. Exp. Fluids 55(12), 1860.
• MARTÍN, M., MONTES, F. J., GALÁN, M. A., 2008. Bubbling process in stirred tank reactors I: Agitator effect on bubble size, formation and rising. Chem. Eng. Sci. 63(12), 3212-3222.
• MASSINAEI, M., DOOSTMOHAMMADI, R., 2010. Modeling of bubble surface area flux in an industrial rougher column using artificial neural network and statistical techniques. Miner. Eng. 23(2), 83-90.
• MESA, D., BRITO-PARADA, P. R., 2020. Bubble size distribution in aerated stirred tanks: Quantifying the effect of impellerstator design. Chem. Eng. Res. Des. 160, 356-369.
• MESA, D., MORRISON, A. J., BRITO-PARADA, P. R., 2020. The effect of impeller-stator design on bubble size: Implications for froth stability and flotation performance. Miner. Eng. 157, 106533.
• MESA, D., QUINTANILLA, P., REYES, F., 2022. Bubble Analyser — An open-source software for bubble size measurement using image analysis. Miner. Eng. 180, 107497.
• POLETAEV, I., TOKAREV, M. P., PERVUNIN, K. S., 2020. Bubble patterns recognition using neural networks: Application to the analysis of a two-phase bubbly jet, Int. J. Multiph. Flow 126, 103194.
• PRASSER, H. M., SCHOLZ, D., ZIPPE, C., 2001. Bubble size measurement using wire-mesh sensors. Flow Meas. Instrum. 12(4), 299-312.
• REN, S., HE, K., GIRSHICK, R., SUN, J., 2017. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(06), 1137-1149.
• SAAVEDRA MORENO, Y., BOURNIVAL, G., ATA, S., 2022. Classification of flotation frothers – A statistical approach. Chem. Eng. Sci. 248, 117252.
• SCHMIDHUBER, J., 2015. Deep learning in neural networks: An overview. Neural Netw. 61, 85-117.
• SOLVAY, 2018. AeroFroth® 70 Safety Datasheet.
• TAO, D., 2005. Role of Bubble Size in Flotation of Coarse and Fine Particles—A Review. Sep. Sci. Technol. 39(4), 741-760.
• VAZQUEZ, A., SANCHEZ, R. M., SALINAS-RODRÍGUEZ, E., SORIA, A., MANASSEH, R., 2005. A look at three measurement techniques for bubble size determination. Exp. Therm. Fluid Sci. 30(1), 49-57.
• VINNETT, L., 2023. A discussion on the limitations of image analysis for determining bubble size in industrial flotation when using algorithms successfully tested from idealized images. Physicochem. Probl. Miner. Process. 59(5), 174474.
• VINNETT, L., ALVAREZ-SILVA, M., 2015. Indirect estimation of bubble size using visual techniques and superficial gas rate. Miner. Eng. 81, 5-9.
• VINNETT, L., CORNEJO, I., YIANATOS, J., ACUÑA, C., URRIOLA, B., GUAJARDO, C., ESTEBAN, A., 2022. The correlation between macroscopic image and object properties with bubble size in flotation. Minerals 12(12), 1528.
• VINNETT, L., SOVECHLES, J., GOMEZ, C. O., WATERS, K. E., 2018. An image analysis approach to determine average bubble sizes using one-dimensional Fourier analysis. Miner. Eng. 126, 160-166.
• VINNETT, L., URRIOLA, B., ORELLANA, F., GUAJARDO, C., ESTEBAN, A., 2022. Reducing the presence of clusters in bubble size measurements for gas dispersion characterizations. Minerals 12(9), 1148.
• VINNETT, L., YIANATOS, J., ACUÑA, C., CORNEJO, I., 2022. A method to detect abnormal gas dispersion conditions in flotation machines. Minerals 12(2), 125.
• VINNETT, L., YIANATOS, J., ARISMENDI, L., WATERS, K. E., 2020. Assessment of two automated image processing methods to estimate bubble size in industrial flotation machines. Miner. Eng. 159, 106636.
• VINNETT, L. E., CONTRERAS, F. A., YIANATOS, J. B., 2009. Bubble size analysis and boundary conditions for automatic control of industrial flotation cells. IFAC Proc. 42(23), 161-166.
• WANG, G., NGUYEN, A. V., MITRA, S., JOSHI, J. B., JAMESON, G. J., EVANS, G. M., 2016. A review of the mechanisms and models of bubble-particle detachment in froth flotation. Sep. Purif. Technol. 170, 155-172.
• WANG, H., YANG, Y., DOU, G., LOU, J., ZHU, X., SONG, L., DONG, F., 2023. A 3D reconstruction method of bubble flow field based on multi-view images by bi-direction filtering maximum likelihood expectation maximization algorithm. Int. J. Multiph. Flow, 165, 104480.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).