Journal of System Simulation
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.
Recommended Citation
Yang, Chunyu; Zhang, Chuang; and Zhang, Xiaofan
(2025)
"Ship Fire Prediction Method Based on Evidence Theory with Fuzzy Reward,"
Journal of System Simulation: Vol. 37:
Iss.
8, Article 20.
DOI: 10.16182/j.issn1004731x.joss.24-0301
Available at:
https://dc-china-simulation.researchcommons.org/journal/vol37/iss8/20
First Page
2152
Last Page
2162
CLC
TP391.9
Recommended Citation
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.
DOI
10.16182/j.issn1004731x.joss.24-0301
Included in
Artificial Intelligence and Robotics Commons, Computer Engineering Commons, Numerical Analysis and Scientific Computing Commons, Operations Research, Systems Engineering and Industrial Engineering Commons, Systems Science Commons