Synthesis Risk Pattern Recognition Model for Building Fire Utilizing Sensor Network

Fire simulations and sensors are widely used in building fires, various data such as temperature, concentration, and visibility can be obtained by sensors. It is important to generate a risk map based on such data so that we can use it to estimate safety of the building. In this paper, we propose a method to generate a dynamical, integrated risk map using sensor readings in a building fire. Such risk evaluation model is developed using similarity comparison between the space pattern and dangerous pattern by a likelihood distance calculating and data grouping from a cluster method. Using simulation results as sensor information, the fire risk pattern recognition model has generated a dynamic risk map and predicated temperature of zones without sensors. The model can be used to support evacuation command and control.