Research on Building Fire Risk Fast Assessment Method Based on Fuzzy comprehensive evaluation and SVM

Abstract In order to improve the efficiency of building fire risk assessment, this paper puts forward a new method of fire risk fast assessment based on fuzzy mathematics and support vector machine (SVM) algorithm. As the building fire risk factors were considered comprehensive, a flexible and operable fire risk assessment index system was established. Through the analysis of the data from a small number of actual risk assessment project, the thesis obtained the index values, as well as the fire risk scores by fuzzy comprehensive evaluation, to get the sample data. And then, the SVM fire risk assessment model trained with the sample data was used for the fire risk assessment of a sports architecture. The assessment result was satisfactory and in good agreement with the actual situation of the building, which proved the feasibility of the method in this paper.