Skip to main content
SpringerLink
Log in

Deep Learning Based Stable and Unstable Candle Flame Detection

  • Conference paper
  • First Online:
Machine Learning and Metaheuristics Algorithms, and Applications (SoMMA 2020)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1366))

  • 1228 Accesses

Abstract

This paper presents a deep learning based solution for identification of normal and abnormal candle flames, controlled and uncontrolled flames. Candle flames affected by external factors like wind, improper combustion of fuel etc. Proposed CNN based deep neural network can successfully classify the stable and unstable candle flame with an accuracy of 67% for generated test set and an accuracy of 83% for random images taken from open source on internet.

Supported by University Women’s Polytechnic, Aligarh Muslim University.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    http://tiny.cc/ut0dlz.

  2. 2.

    http://www.image-net.org/challenges/LSVRC/.

  3. 3.

    https://keras.io/applications/#mobilenetv2.

References

  1. Candle-us-august 2013. https://store.mintel.com/candles-us-august-2013. Accessed 12 Mar 2019

  2. Candles. https://www.nfpa.org/Public-Education/Fire-causes-and-risks/Top-fire-causes/Candles. Accessed 12 Mar 2019

  3. Abdurakipov, S., Gobyzov, O., Tokarev, M., Dulin, V.: Combustion regime monitoring by flame imaging and machine learning. Optoelectron. Instrum. Data Process. 54(5), 513–519 (2018)

    Article  Google Scholar 

  4. Akintayo, A., Lore, K.G., Sarkar, S., Sarkar, S.: Prognostics of combustion instabilities from hi-speed flame video using a deep convolutional selective autoencoder. Int. J. Prognostics Health Manag. 7(023), 1–14 (2016)

    Google Scholar 

  5. Allan, K.M., Kaminski, J.R., Bertrand, J.C., Head, J., Sunderland, P.B.: Laminar smoke points of wax candles. Combust. Sci. Technol. 181(5), 800–811 (2009)

    Article  Google Scholar 

  6. Alsairafi, A., Lee, S.T., T’ien, J.S.: Modeling gravity effect on diffusion flames stabilized around a cylindrical wick saturated with liquid fuel. Combust. Sci. Technol. 176(12), 2165–2191 (2004)

    Google Scholar 

  7. Ballester, J., García-Armingol, T.: Diagnostic techniques for the monitoring and control of practical flames. Prog. Energy Combust. Sci. 36(4), 375–411 (2010)

    Article  Google Scholar 

  8. Buckmaster, J., Peters, N.: The infinite candle and its stability—a paradigm for flickering diffusion flames. In: Symposium (International) on Combustion, vol. 21, pp. 1829–1836. Elsevier (1988)

    Google Scholar 

  9. Chen, T., Guo, X., Jia, J., Xiao, J.: Frequency and phase characteristics of candle flame oscillation. Sci. Rep. 9(1), 1–13 (2019)

    Article  Google Scholar 

  10. Faraday, M.: The Chemical History of a Candle. Courier Corporation (2002)

    Google Scholar 

  11. Hamins, A., Bundy, M., Dillon, S.E.: Characterization of candle flames. J. Fire. Prot. Eng. 15(4), 265–285 (2005)

    Article  Google Scholar 

  12. Li, N., Lu, G., Li, X., Yan, Y.: Prediction of NOx emissions from a biomass fired combustion process based on flame radical imaging and deep learning techniques. Combust. Sci. Technol. 188(2), 233–246 (2016)

    Article  MathSciNet  Google Scholar 

  13. Muhammad, K., Ahmad, J., Baik, S.W.: Early fire detection using convolutional neural networks during surveillance for effective disaster management. Neurocomputing 288, 30–42 (2018)

    Article  Google Scholar 

  14. Riley, N.: A sheet model for the candle flame. Proc. R. Soc. Lond. Ser. A: Math. Phys. Sci. 442(1915), 361–372 (1993)

    Google Scholar 

  15. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)

    Google Scholar 

  16. Sarkar, S., et al.: Early detection of combustion instability from hi-speed flame images via deep learning and symbolic time series analysis. In: Annual Conference on of the Prognostics and Health Management (2015)

    Google Scholar 

  17. Sunderland, P., Quintiere, J., Tabaka, G., Lian, D., Chiu, C.W.: Analysis and measurement of candle flame shapes. Proc. Combust. Inst. 33(2), 2489–2496 (2011)

    Article  Google Scholar 

  18. Wang, Q., Hu, L., Palacios, A., Chung, S.H.: Burning characteristics of candle flames in sub-atmospheric pressures: an experimental study and scaling analysis. Proc. Combust. Inst. 37(2), 2065–2072 (2019)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Aligarh Muslim University, Aligarh, India

    Amir Khan & Mohammad Samar Ansari

  2. Software Research Institute, Athlone Institute of Technology, Athlone, Ireland

    Mohammad Samar Ansari

Authors
  1. Amir Khan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mohammad Samar Ansari
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Amir Khan .

Editor information

Editors and Affiliations

  1. Indian Institute of Information Technology and Management - Kerala, Trivandrum, India

    Sabu M. Thampi

  2. University of Florida, Gainesville, FL, USA

    Selwyn Piramuthu

  3. Providence University, Taichung, Taiwan

    Kuan-Ching Li

  4. Università degli Studi di Firenze, Florence, Italy

    Stefano Berretti

  5. Wrocław University of Technology, Wrocław, Poland

    Michal Wozniak

  6. Hankuk University of Foreign Studies, Yongin, Korea (Republic of)

    Dhananjay Singh

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Khan, A., Ansari, M.S. (2021). Deep Learning Based Stable and Unstable Candle Flame Detection. In: Thampi, S.M., Piramuthu, S., Li, KC., Berretti, S., Wozniak, M., Singh, D. (eds) Machine Learning and Metaheuristics Algorithms, and Applications. SoMMA 2020. Communications in Computer and Information Science, vol 1366. Springer, Singapore. https://doi.org/10.1007/978-981-16-0419-5_5

Download citation

  • DOI: https://doi.org/10.1007/978-981-16-0419-5_5

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-16-0418-8

  • Online ISBN: 978-981-16-0419-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation