Research on the risk classification of cruise ship fires based on an attention-BP neural network

• Autorzy: Xiong Zhenghua , Xiang Bo , Chen Ye , Chen Bin

Identyfikatory

DOI

10.2478/pomr-2022-0026

• Języki publikacji: EN

Abstrakty

EN

Due to the relatively closed environment, complex internal structure, and difficult evacuation of personnel, it is more difficult to prevent ship fires than land fires. In this paper, taking the large cruise ship as the research object, the physical model of a cruise cabin fire is established through PyroSim software, and the safety indexes such as smoke temperature, CO concentration, and visibility are numerically simulated. An Attention-BP neural network model is designed for realizing the intelligent identification of a cabin fire and dividing the risk level, which integrates the diagnosis results of multiple neural network models through the self-Attention mechanism and adaptively distributes the weight of each BP neural network model. The proposed model can provide decision-making reference for subsequent fire-fighting measures and personnel evacuation. Experimental results show that the proposed Attention-BP neural network model can effectively realize the early warning of the fire risk level. Compared with other machine learning algorithms, it has the highest stability and accuracy and reduces the uncertainty of early cabin fire warning.

Słowa kluczowe

EN

cruise fire; simulation modelling; ensemble learning; BP neural network

• Wydawca: Gdańsk University of Technology, Faculty of Ocean Engineering & Ship Technology
• Czasopismo: Polish Maritime Research
• Rocznik: 2022
• Tom: nr 3
• Strony: 61--68
• Opis fizyczny: Bibliogr. 11 poz., rys., tab.

Twórcy

autor

Xiong Zhenghua

• Sichuan Communications Vocational and Technical College, Chengdu China

• https://orcid.org/0000-0002-2403-8164

autor

Xiang Bo

• Sichuan Communications Vocational and Technical College, Chengdu China

• https://orcid.org/0000-0001-8397-0309

autor

Chen Ye

• Wuhan University of Technology Wuhan China

• https://orcid.org/0000-0001-5979-2071

autor

Chen Bin

• Wuhan University of Technology Wuhan China

• https://orcid.org/0000-0001-5979-2071

Bibliografia

• 1. K. Yoshida, ‘Full-scale model tests of smoke movement in ship passenger accommodations (first report)’, Astm Special Technical Publication, 1998, (1336):163-171.
• 2. B. Zhang, ‘Research on fire simulation and visualization application of ship engine room’ [D], Wuhan University of Technology, 2018.
• 3. Yang Shusen, ‘Research on ship fire alarm and escape strategy based on visual sensor’ [D], Jiangsu University of Science and Technology, 2015.
• 4. Z. Wu Zongkui, Y. Fan, ‘Design of toxic and harmful gas monitoring system based on machine learning method’, Fire Science and Technology, 2020, 39(11):1550-1553.
• 5. P. Wang, ‘Research on control strategy of ship fire intelligent alarm system’ [D], Harbin Engineering University, 2017.
• 6. Y.Y. Wei, J.Y. Zhang, J. Wang, ‘Research on building fire risk fast assessment method based on fuzzy comprehensive evaluation and SVM’, Procedia Engineering, 2018, 211:1141-1150.
• 7. L. Jiang, Y. Liu, Y. Li, et al. Fire prediction based on online sequence extreme learning machine[C]// 2017 7th IEEE International Conference on Electronics Information and Emergency Communication (ICEIEC). IEEE, 2017.
• 8. H. Xu, W. Yuan, M. Yu, ‘Real-time classification of fire hazzard levels in ship cabins’ [J], Ship Science and Technology, 2020, 42(19):72-77.
• 9. H. Shi, “A Fuzzy Approach to Building Fire Risk Assessment and Analysis,” 2009 Third International Symposium on Intelligent Information Technology Application, 2009, pp. 606-609.
• 10. B. Chen, L. Shang, J. Sun, ‘Simulation study on cabin fire and personnel evacuation of passenger ships’, China Ship Repair, 2020, 33(06):34-38.
• 11. X. Wang, M. Zhu, D. Bo, et al. AM-GCN: Adaptive Multichannel Graph Convolutional Networks[J]. ACM, 2020.

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).