Ship Fire Prediction Method Based on Evidence Theory with Fuzzy Reward

doi:10.16182/j.issn1004731x.joss.24-0301

Abstract

Abstract:

A multi-source information fusion approach based on the dempster-shafer (D-S) evidence theory with a fuzzy reward-penalty mechanism was proposed to address the issues of underreporting and false reporting in the early prediction of ship fires. PyroSim was utilized to construct a ship's laboratory model for fire simulation. Variations in carbon monoxide, temperature, and smoke concentration were recorded for data acquisition, followed by the application of a sigmf function for membership assignment. By leveraging the classical D-S theory, a reward-penalty mechanism was applied in weighted evidence fusion. Reward-penalty factors were utilized to differentiate various basic probability assignments, with unified belief assignmentsbeing incorporated to mitigate the risk of failure due to high conflicts among evidence, thereby enhancing the convergence of evidence fusion. The research findings demonstrate that the proposed method can increase the prediction accuracy from 57.3% to 95.41% at the same time point for fire prediction, effectively reducing the imprecision of fire prediction.

Key words: simulation technology, dempster-shafer(D-S) evidence theory, ship, data fusion, fire prediction

CLC Number:

TP391.9

Yang Chunyu, Zhang Chuang, Zhang Xiaofan. Ship Fire Prediction Method Based on Evidence Theory with Fuzzy Reward[J]. Journal of System Simulation, 2025, 37(8): 2152-2162.

Figures/Tables 18

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Fig. 8

Fig. 9

Fig. 10

Table 1

Table 2

Table 3

Table 4

Table 5

Similarity and credibility among evidence

$ξ$ (m₁₁,m₁₂)	$ξ$ (m₁₁,m₁₃)	$ξ$ (m₁₂,m₁₃)
0.786	0.687	0.915
$ξ$ (m₂₁,m₂₂)	$ξ$ (m₂₁,m₂₃)	$ξ$ (m₂₂,m₂₃)
0.804	0.571	0.933
$ξ$ (m₃₁,m₃₂)	$ξ$ (m₃₁,m₃₃)	$ξ$ (m₃₂,m₃₃)
0.956	0.883	0.964
$τ$ ₁	$τ$ ₂	$τ$ ₃
2.387	2.308	2.801

Table 5

Table 6

Fig. 11

Fig. 12

References 15

[1]	蔡晶. 船舶火灾自动报警系统控制策略的研究[D]. 哈尔滨: 哈尔滨工程大学, 2013.
	Cai Jing. Research on Control Strategy of Ship FireAutomatic Alarm System[D]. Harbin: Harbin Engineering University, 2013.
[2]	刘宝元, 张义伟. 基于STM32船舶火灾报警系统的研究[J]. 船舶物资与市场, 2019(6): 22-24.
[3]	王锡淮, 肖健梅. 模糊神经网络在船舶火灾报警系统中的应用[J]. 船舶工程, 2000(2): 57-59.
	Wang Xihuai, Xiao Jianmei. Application of Fuzzy Neural Network to Ship Fire Alarm System[J]. Ship Engineering, 2000(2): 57-59.
[4]	Xie Qimiao, Guo Shuaishuai, Zhang Yijia, et al. An Integrated Method for Assessing Passenger Evacuation Performance in Ship Fires[J]. Ocean Engineering, 2022, 262: 112256.
[5]	Yazir Devran. Application of IF-TOPSIS Method on Fixed Fire Fighting Systems for Cargo Hold Fires on the Dry/Bulk Cargo Ships[J]. Ocean Engineering, 2022, 260: 111891.
[6]	Spyrou Kostas J, Koromila Ioanna A. A Risk Model of Passenger Ship Fire Safety and Its Application[J]. Reliability Engineering & System Safety, 2020, 200: 106937.
[7]	Puisa R, Williams S, Vassalos D. Towards an Explanation of Why Onboard Fires Happen: The Case of an Engine Room Fire on the Cruise Ship "Le Boreal"[J]. Applied Ocean Research, 2019, 88: 223-232.
[8]	谢锦涛. 基于视频的船舶舱室火灾烟雾检测算法研究[D]. 大连: 大连理工大学, 2020.
	Xie Jintao. Research on Fire Smoke Detection Algorithm of Ship Cabin Based on Video[D]. Dalian: Dalian University of Technology, 2020.
[9]	王署光, 李晓丽. 基于红外探测技术的船舶控制室火灾监控系统研究[J]. 舰船科学技术, 2018, 42(2): 206-208.
	Wang Shuguang, Li Xiaoli. Research on Fire Monitoring System of Ship Control Room Based on Infrared Detection Technology[J]. Ship Science and Technology, 2018, 40(2): 206-208.
[10]	李光, 张铁壁. 多传感器数据融合技术在火灾报警中的应用[J]. 河北工业大学学报, 2010, 39(4): 35-38.
	Li Guang, Zhang Tiebi. The Apply of a Fire Alarm System Based on Mmultisensor Data Fusion Technology[J]. Journal of Hebei University of Technology, 2010, 39(4): 35-38.
[11]	赵英, 陈淑娟. 基于多传感器数据融合的火灾预警系统[J]. 现代电子技术, 2010, 33(24): 173-175, 179.
	Zhao Ying, Chen Shujuan. Fire Early Alarm System Based on Multi-sensor Data Fusion[J]. Modern Electronics Technique, 2010, 33(24): 173-175, 179.
[12]	Jin Kang Hee, Jin Choi, Lee Dongkon, et al. A Framework for Using Computational Fire Simulations in the Early Phases of Ship Design[J]. Ocean Engineering, 2017, 129: 335-342.
[13]	Ji Zhengxiong, Tian Jianyan, Chen Haibin, et al. A New Method for Weighted Fusion of Evidence Based on the Unified Trust Distribution Mechanism and the Reward-punishment Mechanism[J]. Information Sciences, 2023, 629: 798-815.
[14]	Qiu Daohong, Li Xuebing, Xue Yiguo, et al. Analysis and Prediction of Rockburst Intensity Using Improved D-S Evidence Theory Based on Multiple Machine Learning Algorithms[J]. Tunnelling and Underground Space Technology, 2023, 140: 105331.
[15]	Zhang Chao, Zhang Jingjing, Li Wentao, et al. A Regret Theory-based Multi-granularity Three-way Decision Model with Incomplete T-spherical Fuzzy Information and Its Application in Forest Fire Management[J]. Applied Soft Computing, 2023, 145: 110539.

指标	m	Y	N	U
CO含量	m₁₁	0.231	0.501	0.268
	m₁₂	0.401	0.269	0.330
	m₁₃	0.498	0.314	0.188
温度	m₂₁	0.213	0.511	0.276
	m₂₂	0.447	0.311	0.242
	m₂₃	0.573	0.217	0.210
烟雾浓度	m₃₁	0.305	0.301	0.394
	m₃₂	0.432	0.198	0.401
	m₃₃	0.496	0.201	0.301

指标	m	Y	N	U
CO含量	m₁	0.439 1	0.402 7	0.158 2
温度	m₂	0.530 8	0.334 6	0.134 6
烟雾浓度	m₃	0.523 3	0.095 9	0.380 8