Skip to main content

Advertisement

Springer Nature Link
Log in

Deep Learning-based Image Analysis Method for Estimation of Macroscopic Spray Parameters

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Spray strategies contribute to the overall engine efficiency, combustion process, and reduction of pollutant formation in internal combustion engines with direct rail injection systems. Spray shape is determined by several parameters such as nozzle diameter, injection pressure, injector geometry, and cylinder type, which influence spray macroscopic parameters. The spray macroscopic parameters are commonly used to describe the input parameters of numerical simulations. Three main spray macroscopic parameters are spray cone angle, penetration length, and spray area. In this paper, we propose a method for spray macroscopic parameter estimation that achieves the state-of-the-art results. To obtain these results, image segmentation was performed to separate the spray from the rest of the image. Then the spray macroscopic parameters are estimated from the segmented image. To perform image segmentation Min U-Net is used. Min U-Net is a novel lightweight deep learning neural network based on U-Net. Min U-Net achieves the state-of-the-art segmentation results while having more than 500 times fewer parameters and being at least twice as fast as other learning-based methods. To evaluate the proposed method, an available dataset containing a variety of images with various spray shapes and orientations. The experiments performed on the dataset showed that Min U-Net achieved a mean dice coefficient of 0.95 with an inference time of 11.94 ms/image. The spray macroscopic parameters estimation is also highly accurate, with spray cone angle having an error of 1.08\(^{\circ }\), spray penetration length having a relative error of 5.95%, and spray area having a relative error of 4.05%.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data Availability

The datasets generated during and/or analyzed during the current study are available in the “The experimental results of diesel fuel spray with marine engine injector” repository, at https://mostwiedzy.pl/en/open-research-data/the-experimental-results-of-diesel-fuel-spray-with-marine-engine-injector,528075150550713-0 [27].

References

  1. Stančin H, Mikulčić H, Wang X, Duić N (2020) A review on alternative fuels in future energy system. Renew Sustain Energy Rev 128:10992. https://doi.org/10.1016/j.rser.2020.109927

    Article  Google Scholar 

  2. Shahir VK, Jawahar CP, Suresh PR (2015) Comparative study of diesel and biodiesel on CI engine with emphasis to emissions–A review. Renew Sustain Energy Rev 45:686–697. https://doi.org/10.1016/j.rser.2015.02.042

    Article  Google Scholar 

  3. Jones DP, Watkins AP (2012) Droplet size and velocity distributions for spray modelling. J Comput Phys 231(2):676–692. https://doi.org/10.1016/j.jcp.2011.09.030

    Article  MathSciNet  MATH  Google Scholar 

  4. Wu D, Wang W, Pang Z, Cao S, Yan J (2015) Experimental Investigation of Spray Characteristics of Diesel-Methanol-Water Emulsion. At Sprays 25(8):675–694. https://doi.org/10.1615/AtomizSpr.2015011524

    Article  Google Scholar 

  5. Eagle WE, Morris SB, Wooldridge MS (2014) High-speed imaging of transient diesel spray behavior during high pressure injection of a multi-hole fuel injector. Fuel 116:299–309. https://doi.org/10.1016/j.fuel.2013.07.120

    Article  Google Scholar 

  6. Sajjad H, Masjuki HH, Varman M, Kalam MA, Arbab MI, Imtenan S, Rahman SMA (2014) Engine combustion, performance and emission characteristics of gas to liquid (GTL) fuels and its blends with diesel and bio-diesel. Renew Sustain Energy Rev 30:961–986. https://doi.org/10.1016/j.rser.2013.11.039

    Article  Google Scholar 

  7. Xie K, Cui Y, Wang C, Cui G, Wang G, Qiu X, Wang J (2021) Study on threshold selection method of continuous flame images of spray combustion in the low-pressure chamber. Case Studies Thermal Eng. https://doi.org/10.1016/j.csite.2021.101195

    Article  Google Scholar 

  8. Gibou F, Hyde D, Fedkiw R (2019) Sharp interface approaches and deep learning techniques for multiphase flows. J Comput Phys 380:442–463. https://doi.org/10.1016/j.jcp.2018.05.031

    Article  MathSciNet  MATH  Google Scholar 

  9. Parrish SE, Zink RJ (2012) Development and application of imaging system to evaluate liquid and vapor envelopes of multi-hole gasoline fuel injector sprays under engine-like conditions. At Sprays 22(8):647–661. https://doi.org/10.1615/AtomizSpr.2012006215

    Article  Google Scholar 

  10. Zhang A, Montanaro A, Allocca L, Naber J, Lee SY (2014) Measurement of Diesel Spray Formation and Combustion upon Different Nozzle Geometry using Hybrid Imaging Technique. SAE Int J Engines 7(2):1034–1043. https://doi.org/10.4271/2014-01-1410

    Article  Google Scholar 

  11. Kapusta ŁJ (2017) LIF/Mie Droplet Sizing of Water Sprays from SCR System Injector using Structured Illumination. In: Proceedings ILASS–Europe 2017. 28th Conference on Liquid Atomization and Spray Systems, pp. 6–8. Universitat Politècnica València, Valencia. https://doi.org/10.4995/ILASS2017.2017.5031

  12. Carter DW, Hassaini R, Eshraghi J, Vlachos P, Coletti F (2020) Multi-scale imaging of upward liquid spray in the far-field region. Int J Multiph Flow. https://doi.org/10.1016/j.ijmultiphaseflow.2020.103430

    Article  MathSciNet  Google Scholar 

  13. Özlüoymak ÖB, Bolat A (2020) Development and assessment of a novel imaging software for optimizing the spray parameters on water-sensitive papers. Comput Electron Agric. https://doi.org/10.1016/j.compag.2019.105104

    Article  Google Scholar 

  14. Payri R, Salvador FJ, Martí-Aldaraví P, Vaquerizo D (2017) ECN Spray G external spray visualization and spray collapse description through penetration and morphology analysis. Appl Therm Eng 112:304–316. https://doi.org/10.1016/j.applthermaleng.2016.10.023

    Article  Google Scholar 

  15. Rubio-Gómez G, Martínez-Martínez S, Rua-Mojica LF, Gómez-Gordo P, de la Garza OA (2018) Automatic macroscopic characterization of diesel sprays by means of a new image processing algorithm. Meas Sci Technol 29(5):055406. https://doi.org/10.1088/1361-6501/aab121

    Article  Google Scholar 

  16. Bottega Dongiovanni (2019) Diesel Spray Macroscopic Parameter Estimation Using a Synthetic Shapes Database. Appl Sci 9(23):5248. https://doi.org/10.3390/app9235248

    Article  Google Scholar 

  17. Borujeni AT, Lane NM, Thompson K, Tyagi M (2013) Effects of image resolution and numerical resolution on computed permeability of consolidated packing using LB and FEM pore-scale simulations. Comput Fluids 88:753–763. https://doi.org/10.1016/j.compfluid.2013.05.019

    Article  MathSciNet  MATH  Google Scholar 

  18. Farhadian N, Behin J, Parvareh A (2018) Residence time distribution in an internal loop airlift reactor: CFD simulation versus digital image processing measurement. Comput Fluids 167:221–228. https://doi.org/10.1016/j.compfluid.2018.02.030

    Article  MathSciNet  MATH  Google Scholar 

  19. Li H, Cryer S, Acharya L, Raymond J (2020) Video and image classification using atomisation spray image patterns and deep learning. Biosyst Eng 200:13–22. https://doi.org/10.1016/j.biosystemseng.2020.08.016

    Article  Google Scholar 

  20. Hasti VR, Shin D (2022) Denoising and fuel spray droplet detection from light-scattered images using deep learning. Energy and AI. https://doi.org/10.1016/j.egyai.2021.100130

    Article  Google Scholar 

  21. Yilmaz S, Bilgin MZ (2013) Modeling and simulation of injection control system on a four-stroke type diesel engine development platform using artificial neural networks. Neural Comput Appl 22(7–8):1713–1725. https://doi.org/10.1007/s00521-012-1054-7

    Article  Google Scholar 

  22. Akolaş HI, Kaleli A, Bakirci K (2021) Design and implementation of an autonomous EGR cooling system using deep neural network prediction to reduce NOx emission and fuel consumption of diesel engine. Neural Comput Appl 33(5):1655–1670. https://doi.org/10.1007/s00521-020-05104-1

    Article  Google Scholar 

  23. Farahani A, Mohseni H (2021) Medical image segmentation using customized U-Net with adaptive activation functions. Neural Comput Appl 33(11):6307–6323. https://doi.org/10.1007/s00521-020-05396-3

    Article  Google Scholar 

  24. Hurtik P, Ozana S (2021) Dragonflies segmentation with U-Net based on cascaded ResNeXt cells. Neural Comput Appl 33(9):4567–4578. https://doi.org/10.1007/s00521-020-05274-y

    Article  Google Scholar 

  25. Çiçek O, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O (2016) 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation. In: Ourselin S, Joskowicz L, Sabuncu MR, Unal G, Wells W (eds) Medical image computing and computer-assisted intervention - MICCAI 2016, vol 9901. Lecture Notes in Computer Science. Springer, Cham, pp 424–432. https://doi.org/10.1007/978-3-319-46723-8_49

    Chapter  Google Scholar 

  26. Ronneberger O, Fischer P, Brox T (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab N, Hornegger J, Wells WM, Frangi AF (eds) Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015, vol 9351. Lecture Notes in Computer Science. Springer, Cham, pp 234–241. https://doi.org/10.1007/978-3-319-24574-4_28

    Chapter  Google Scholar 

  27. Grochowalska J, Kowalski J, Kapusta ŁJ, Jaworski P (2021) The experimental results of diesel fuel spray with marine engine injector. https://doi.org/10.34808/c3aw-dq41

  28. Minaee S, Boykov YY, Porikli F, Plaza AJ, Kehtarnavaz N, Terzopoulos D (2021) Image Segmentation Using Deep Learning: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, p. 1. https://doi.org/10.1109/TPAMI.2021.3059968. Conference Name: IEEE Transactions on Pattern Analysis and Machine Intelligence

  29. Sorensen TA (1948) A method of establishing groups of equal amplitude in plant sociology based on similarity of species content and its application to analyses of the vegetation on danish commons. Biol Skar 5:1–34

    Google Scholar 

  30. Naruemon I, Liu L, Liu D, Ma X, Nishida K (2020) An Analysis on the Effects of the Fuel Injection Rate Shape of the Diesel Spray Mixing Process Using a Numerical Simulation. Appl Sci 10(14):4983. https://doi.org/10.3390/app10144983

    Article  Google Scholar 

  31. Zhang A, Montanaro A, Allocca L, Naber J, Lee S-Y (2014) Measurement of Diesel Spray Formation and Combustion upon Different Nozzle Geometry using Hybrid Imaging Technique. SAE Int J Engines 7(2):1034–1043. https://doi.org/10.4271/2014-01-1410

    Article  Google Scholar 

  32. Naber JD, Siebers DL (1996) Effects of Gas Density and Vaporization on Penetration and Dispersion of Diesel Sprays. SAE Transactions 105:82–111. Publisher: SAE International

  33. Kang J, Bae C, Lee KO (2003) Initial development of non-evaporating diesel sprays in common-rail injection systems. Int J Engine Res 4(4):283–298. https://doi.org/10.1243/146808703322743895

    Article  Google Scholar 

  34. Payri R, Gimeno J, Bracho G, Vaquerizo D (2016) Study of liquid and vapor phase behavior on Diesel sprays for heavy duty engine nozzles. Appl Therm Eng 107:365–378. https://doi.org/10.1016/j.applthermaleng.2016.06.159

    Article  Google Scholar 

  35. Pastor JV, Arrègle J, Palomares A (2001) Diesel spray image segmentation with a likelihood ratio test. Appl Optics 40(17):2876. https://doi.org/10.1364/AO.40.002876

    Article  Google Scholar 

  36. Mo J, Tang C, Li J, Guan L, Huang Z (2016) Experimental investigation on the effect of n-butanol blending on spray characteristics of soybean biodiesel in a common-rail fuel injection system. Fuel 182:391–401. https://doi.org/10.1016/j.fuel.2016.05.109

    Article  Google Scholar 

  37. Hiroyasu H, Arai M (1990) Structures of Fuel Sprays in Diesel Engines. SAE trans. https://doi.org/10.4271/900475

    Article  Google Scholar 

  38. Payri F, Bermúdez V, Payri R, Salvador FJ (2004) The influence of cavitation on the internal flow and the spray characteristics in diesel injection nozzles. Fuel 83(4–5):419–431. https://doi.org/10.1016/j.fuel.2003.09.010

    Article  Google Scholar 

  39. Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) ImageNet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. https://doi.org/10.1109/CVPR.2009.5206848. ISSN: 1063-6919

  40. Smith LN (2017) Cyclical Learning Rates for Training Neural Networks. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 464–472. https://doi.org/10.1109/WACV.2017.58

  41. Dhanachandra N, Manglem K, Chanu YJ (2015) Image Segmentation Using K -means Clustering Algorithm and Subtractive Clustering Algorithm. Proc Comput Sci 54:764–771. https://doi.org/10.1016/j.procs.2015.06.090

    Article  Google Scholar 

  42. Feng D, Wenkang S, Liangzhou C, Yong D, Zhenfu Z (2005) Infrared image segmentation with 2-D maximum entropy method based on particle swarm optimization (PSO). Pattern Recognit Lett 26(5):597–603. https://doi.org/10.1016/j.patrec.2004.11.002

    Article  Google Scholar 

  43. Leung C-K, Lam F-K (1994) Image segmentation using maximum entropy method. In: Proceedings of ICSIPNN ’94. International Conference on Speech, Image Processing and Neural Networks, pp. 29–321. https://doi.org/10.1109/SIPNN.1994.344973

  44. Pickett LM, Manin J, Payri R, Bardi M, Gimeno J (2013) Transient Rate of Injection Effects on Spray Development, pp. 2013–240001. https://doi.org/10.4271/2013-24-0001

  45. Eagle WE, Malbec L-M, Musculus MP (2016) Measurements of Liquid Length, Vapor Penetration, Ignition Delay, and Flame Lift-Off Length for the Engine Combustion Network Spray B in a 2.34 L Heavy-Duty Optical Diesel Engine. SAE Int J Engines 9(2):910–931. https://doi.org/10.4271/2016-01-0743

    Article  Google Scholar 

  46. Ruiz-Rodriguez I, Pos R, Megaritis T, Ganippa LC (2019) Investigation of Spray Angle Measurement Techniques. IEEE Access 7:22276–22289. https://doi.org/10.1109/ACCESS.2019.2899214. Conference Name: IEEE Access

  47. Otsu N (1979) A Threshold Selection Method from Gray-Level Histograms. IEEE Trans Syst Man Cybern 9(1):62–66. https://doi.org/10.1109/TSMC.1979.4310076

    Article  MathSciNet  Google Scholar 

  48. Lin T-Y, Dollar P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature Pyramid Networks for Object Detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 936–944. IEEE, Honolulu, HI. https://doi.org/10.1109/CVPR.2017.106

  49. Chaurasia A, Culurciello E (2017) LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation. 2017 IEEE Visual Communications and Image Processing (VCIP), 1–4. https://doi.org/10.1109/VCIP.2017.8305148. arXiv: 1707.03718

  50. Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid Scene Parsing Network. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6230–6239. IEEE, Honolulu, HI. https://doi.org/10.1109/CVPR.2017.660

Download references

Acknowledgements

This research was funded by the European Regional Development Fund, Operational Programme Competitiveness and Cohesion 2014-2020, KK.01.1.1.04.0070. Authors gratefully acknowledge Grochowalska, J., Kowalski, J., Kapusta, Łukasz J., & Jaworski, P. for the dataset “The experimental results of diesel fuel spray with marine engine injector”, produced by the Gdańsk University of Technology.

Author information

Authors and Affiliations

  1. Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia

    Fran Huzjan & Sven Lončarić

  2. Faculty of Mechanical Engineering and Naval Architecture, University of Zagreb, Zagreb, Croatia

    Filip Jurić & Milan Vujanović

Authors
  1. Fran Huzjan
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Filip Jurić
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Sven Lončarić
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Milan Vujanović
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Fran Huzjan.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Huzjan, F., Jurić, F., Lončarić, S. et al. Deep Learning-based Image Analysis Method for Estimation of Macroscopic Spray Parameters. Neural Comput & Applic 35, 9535–9548 (2023). https://doi.org/10.1007/s00521-022-08184-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-022-08184-3

Keywords