Journal of the Society of Naval Architects of Korea (대한조선학회논문집)

The Society of Naval Architects of Korea (대한조선학회)
권호 표지
DOI QR코드

DOI QR Code

Naval Ship Evacuation Path Search Using Deep Learning

딥러닝을 이용한 함정 대피 경로 탐색

  • Ju-hun, Park (Grad. School, Dept. of Naval Architecture & Ocean engineering, Chung-nam National University) ;
  • Won-sun, Ruy (Dept. of Naval Architecture and Ocean Engineering, Chung-nam National University) ;
  • In-seok, Lee (Grad. School, Dept. of Naval Architecture & Ocean engineering, Chung-nam National University) ;
  • Won-cheol, Choi (Dept. of Naval Architecture and Ocean Engineering, Chung-nam National University)
  • 박주헌 (충남대학교 선박해양공학과 대학원) ;
  • 유원선 (충남대학교 선박해양공학과) ;
  • 이인석 (충남대학교 선박해양공학과 대학원) ;
  • 최원철 (충남대학교 선박해양공학과)
  • Received : 2022.07.07
  • Accepted : 2022.10.18
  • Published : 2022.12.20
Download PDF
⟨ Previous Next ⟩

Abstract

Naval ship could face a variety of threats in isolated seas. In particular, fires and flooding are defined as disasters that are very likely to cause irreparable damage to ships. These disasters have a very high risk of personal injury as well. Therefore, when a disaster occurs, it must be quickly suppressed, but if there are people in the disaster area, the protection of life must be given priority. In order to quickly evacuate the ship crew in case of a disaster, we would like to propose a plan to quickly explore the evacuation route even in urgent situations. Using commercial escape simulation software, we obtain the data for deep neural network learning with simulations according to aisle characteristics and the properties and number of evacuation person. Using the obtained data, the passage prediction model is trained with a deep learning, and the passage time is predicted through the learned model. Construct a numerical map of a naval ship and construct a distance matrix of the vessel using predicted passage time data. The distance matrix configured in one of the path search algorithms, the Dijkstra algorithm, is applied to explore the evacuation path of naval ship.

Keywords

Acknowledgement

본 연구는 한국산업기술진흥원(사업명 : 산업혁신인재성장지원사업, 과제번호: P0001968)과 국방기술품질원의 지원(사업명: 글로벌 방위산업 강소기업 육성사업, 과제번호: E200012)하에 수행되었습니다.

References

  1. Choi, S.H. and Yoo, S.J., 2021. Q-learning based optimal escape route decision in a disaster environment. The Journal of Korean Institute of Communications and Information Sciences, 46(4), pp.638-650. https://doi.org/10.7840/kics.2021.46.4.638
  2. Ha, S., Cho, Y.O., Ku, N.K., Lee, K.Y. and Roh, M.I., 2013a. Passenger ship evacuation simulation considering external forces due to the inclination of damaged ship. Journal of the Society of Naval Architects of Korea, 50(3), pp.175-181. https://doi.org/10.3744/SNAK.2013.50.3.175
  3. Ha, S., Cho, Y.O., Ku, N.K., Park, K.P., Lee, K.Y. and Roh, M.I., 2013b, Passenger ship evacuation simulation using algorithm for determination of evacuating direction based on walking direction potential function. Journal of the Society of Naval Architects of Korea, 50(5), pp.307-313. https://doi.org/10.3744/SNAK.2013.50.5.307
  4. Kim, H.T., Lee, D.K., Park, J.H. and Hong, S.K., 2004, The effect on the mobility of evacuating passengers in ship with regard to sist and motion. IE interfaces, 17(1), pp.22-32.
  5. Kang, M.B. and Joo, Y.I., 2016, Intelligent evacuation systems for accidents aboard a ship. Journal of the Korean Society of Marine Engineering, 40(9), pp.824-829.
  6. Keras, 2016. Keras API reference [Online] (Updated 12 April 2020) Available at: https://keras.io/ [Accessed 2 September 2022].
  7. Liu, Y., Zhang, H.J., Zhan, Y., Deng, K.X. and Dong, L.Z., 2022a, Evacuation strategy considering path capacity and risk level for cruise ship. Journal of Marine Science and Engineering, 10(3), pp.398.
  8. Liu, L., Zhang, H., Zhan, Y., Su, Y. and Zhang, C., 2022b. Intelligent optimization method for the evacuation routes of dense crowds on cruise ships. Simulation Modelling Practice and Theory, 117.
  9. Park, K.P., Cho, Y.O., Ha, S. and Lee, K.Y., 2010. Acceleration based passenger evacuation simulation considering rotation of passenger on horizontal plane. Korean Journal of Computational Design and Engineering, 15(4), pp.306-313.
  10. Park, J.H., Ruy, W.S., Chung, J.H. and Kim, S.K., 2020. A study on the path search for the rapid suppression of naval ships casualties. Journal of the Society of Naval Architects of Korea, 57(4), pp.221-229. https://doi.org/10.3744/SNAK.2020.57.4.221
  11. Seo, S. K., Yoon, Y. G., Lee, J. S., Na, J. G. and Lee, C. J., 2022, Deep neural network-based optimization framework for safety evacuation route during toxic gas leak incidents, Reliability Engineering & System Safety, 218.
  12. Thunderhead Engineering, 2020. Pathfinder technical reference manual, [Online] (Update 28 March 2022) Available at : https://support.thunderheadeng.com/docs/pathfinder [Accessed 20 June 2022].
  13. Wang, Y. F., Ma, W. K., Wang, T., Liu, J. L., Wang, X. J., Sean, M. K., Yang, Z. L. and Wang, J., 2020, Dynamic optimisation of evacuation route in the fire scenarios of offshore drilling platforms. Ocean Engineering, 247.