大型商业综合体火灾风险性分析

发布时间：2018-05-24 11:34

本文选题：大型商业综合体 + 火灾风险性评价　；参考：《西安科技大学》2015年硕士论文

【摘要】：大型商业综合体作为一种公共聚集场所,结构与功能复杂,人员密集,流动性大,极易发生火灾风危险。我国目前的火灾风险性评价工作主要依据现行防火规范标准,即强调每项指标达标。但大型商业综合体中存在一些规范无法规定的新型设计理念及结构布局,这对以现行规范为参考依据的火灾风险性评价工作提出巨大挑战。本文针对大型商业综合体火灾事故中存在的突出问题以及火灾风险性评价中突显的矛盾,提出大型商业综合体火灾风险性评价体系的研究课题。主要做了以下几个方面的研究:第一,火灾风险性评价体系的构建及指标因素的衡量分析。(1)针对大型商业综合体的火灾发展及防火设计特点,构建了三级火灾风险性评价指标体系。(2)针对超规范大型商业综合体的防火设计方法与现行防火规范之间的矛盾,将三级指标进一步划分为超规范设计类、符合规范设计类和严于规范设计类三大类别,并分析总结了火灾风险性评价工作中存在的问题。(3)在上述分析的基础上,对火灾风险性评价指标进行衡量分析。第二,提出了综合运用模糊层次分析法、模糊综合评价法和遗传神经网络的方法对大型商业综合体火灾风险性进行评价的设计构想。(1)运用FAHP-FCE评价模型生成GA-BP神经网络的样本集。运用MATLAB编程,完成了模糊层次分析法对指标权重的计算过程;并运用模糊综合评价法分析得出各个样本的火灾风险等级。(2)运用遗传算法优化BP神经网络的权值和阈值,构建了基于遗传神经网络的评价模型。运用MATLAB的神经网络工具箱和编写GA-BP程序,完成对GA-BP网络评价模型的训练、学习与测试。第三,将训练好的网络应用于实例评价,结果表明:该评价模型在大型商业综合体火灾风险性评价中具有良好的适用性。
[Abstract]:As a kind of public gathering place, large-scale commercial complex has complex structure and function, dense personnel, high mobility, and is prone to fire and wind hazard. The current fire risk assessment in China is mainly based on the current fire prevention standard, that is, emphasizing that each target is up to standard. However, there are some new design concepts and structure layout which can not be prescribed by the code in large-scale commercial complex, which brings great challenge to fire risk assessment based on current codes. Aiming at the outstanding problems in the fire accident of large-scale commercial complex and the obvious contradiction in fire risk evaluation, this paper puts forward the research subject of fire risk evaluation system for large-scale commercial complex. The main research is as follows: first, the construction of fire risk assessment system and the measurement of index factors. 1) aiming at the characteristics of fire development and fire prevention design of large-scale commercial complex, The third grade fire risk evaluation index system is constructed. (2) aiming at the contradiction between the fire prevention design method of super code large commercial complex and the current fire prevention code, the third grade index is further divided into super code design category. This paper analyzes and summarizes the problems existing in fire risk assessment. Based on the above analysis, the evaluation index of fire risk is measured and analyzed. Secondly, the design conception of comprehensive use of fuzzy analytic hierarchy process, fuzzy comprehensive evaluation and genetic neural network to evaluate the fire risk of large-scale commercial complex is put forward. The FAHP-FCE evaluation model is used to generate the sample set of GA-BP neural network. By using MATLAB programming, the calculation process of index weight by fuzzy analytic hierarchy process (FAHP) is completed, and the fire risk grade of each sample is obtained by fuzzy comprehensive evaluation method. (2) the weight and threshold of BP neural network are optimized by genetic algorithm, and the weight and threshold of BP neural network are optimized by genetic algorithm. The evaluation model based on genetic neural network is constructed. MATLAB neural network toolbox and GA-BP program are used to complete the training, learning and testing of GA-BP network evaluation model. Thirdly, the trained network is applied to the case evaluation. The results show that the evaluation model has good applicability in the fire risk assessment of large-scale commercial complexes.
【学位授予单位】：西安科技大学
【学位级别】：硕士
【学位授予年份】：2015
【分类号】：TU247;TU998.1

【相似文献】