摘要：As an independent building entity on the sea, the ship has a large number of internal electrical equipment and a compact space structure, which is prone to fire. This paper proposes a key technology of virtual dynamic escape of ships based on the fire spread prediction model for research. Taking the 63,500 DWT(Dead Weight Tonnage) tanker cabin as a research entity, the mathematical and physical models of ship fire simulation are established. Through the graphical analysis of the experimental data of the fire spread simulation, the temperature, CO concentration, and smoke concentration change rules under different working conditions at the fixed detection point position are obtained. Then, based on temperature, CO concentration and smoke concentration three impact factors, set up a comprehensive fire real-time situational risk evaluation index system. Using the MATLAB software, based on the principle of the fuzzy neural network fire ship’s integrated real-time situational risk evaluation model structure design and simulation test, obtained the corresponding training to comprehensive risk evaluation model of the network. Generate navigation grid according to the law of fire sprawl, and plan escape path. The traditional A* algorithm is improved, and an example is used to prove that the path-finding result after the improved algorithm is shorter than the path found by the traditional algorithm, which meets the path-finding requirements in a three-dimensional environment.
