Font Size: a A A

Study On Fire Risk Assessment And Emergency Evacuation Of Universit Dormitory

Posted on:2022-06-18Degree:MasterType:Thesis
Country:ChinaCandidate:L Q FanFull Text:PDF
GTID:2492306524959599Subject:Safety engineering
Abstract/Summary:PDF Full Text Request
Due to the particularity of the people living in college dormitory,the fire in college dormitory is an important issue to be solved in the field of fire safety research.The purpose of this paper is to study how to reduce the fire incidence of College Students’ dormitory in China,and apply PCA-RBF neural network model to the fire risk assessment of College Students’ dormitory for the first time.In addition,combined with building information modeling technology and personnel evacuation technology,this paper carries out further research on the evaluation object,and puts forward reasonable opinions and suggestions for the fire emergency management of College Students’ dormitory.First of all,this study analyzes the main influencing factors of dormitory fire in Colleges and universities by using the accident cause theory,and establishes the fire risk evaluation index system,which has 4 first level indicators and 16 second level indicators.Among them,the first level indicators are unsafe behavior of people,unsafe state of objects,defects in management and influence of surrounding environment.Secondly,the intelligent evaluation method based on radial basis function(RBF)is introduced.In order to avoid the redundancy of evaluation indexes and the limitation of dimension disaster in neural network evaluation,principal component analysis(PCA)is introduced to reduce the dimension of the index system and realize the scientific coupling of PCA and RBF,so as to build a fire risk evaluation model based on PCA-RBF.At the same time,the building information model(BIM)is applied to the evaluation object data acquisition,and the visual building information model is successfully built by using the software of Revit to assist experts to give more scientific and reasonable scores.Furthermore,through the case analysis,the results show that the dispersion of the first model is reduced by 63.43% compared with the evaluation results based on RBF neural network model only.Therefore,the feasibility and effectiveness of the fire risk assessment system for college students’ dormitories are verified.Finally,according to the results of risk assessment and based on the building information model of the evaluation object,the evacuation of the evaluation object is studied by using the evacuation software Pathfinder.Through the design of a variety of scenarios for simulation experiments,this paper discusses the effective methods of evacuation management in the case of fire.This study deepens the research on fire risk assessment of college dormitory in China,and provides substantive suggestions for the current college dormitory fire prevention and emergency evacuation management.This paper has(16)(20)figures,(16)(15)tables and(22)(22)references.
Keywords/Search Tags:Safety Engineering, College Dormitory Fire, Principal Component Analysis, Radial Basis Function Neural Network, Fire Risk Assessment
PDF Full Text Request
Related items