投影寻踪法在高层建筑火灾风险评估中的应用  被引量:4

Application of Projection Pursuit Method to Evaluation of Fire Risk of High-rise Building

在线阅读下载全文

作  者:吴瑶[1] 冯国珍[2] 楼文高[1,2] 

机构地区:[1]上海理工大学管理学院,上海200093 [2]上海商学院管理学院,上海200235

出  处:《灾害学》2016年第3期196-201,共6页Journal of Catastrophology

基  金:上海高校知识服务平台"上海商贸服务业知识服务中心"项目(ZF1226);上海高校工商管理一流学科项目资助

摘  要:针对现有高层建筑火灾风险评价方法中主观性强、分辨率低的问题,提出了一种新模型——基于投影寻踪的高层建筑火灾风险评价模型。利用该模型将火灾风险指标的多维数据投影到一维空间上,采用粒子群算法进行优化,根据最优投影方向计算了各实测火灾样本的投影值,通过比较各等级投影输出值与各实测样本的投影值进行火灾风险评估,并将评估结果与其他几种常用方法的结果进行比较研究。研究表明,该模型的评价结果比其他几种方法的结果更加合理可靠,不仅克服了权重取值受人为因素影响的局限性,而且有较高的分辨率和分类精度,在该领域具有较强的适用性,是一种更具有应用和推广价值的新方法。In order to solve we problem of subjectivity and low distinguish ability in the published literatures on evaluation method of the high-rise building fire risk evaluation,we propose a new model——Fire risk evaluation of the high-rise building based on projection pursuit clustering( PPC). The multi-dimensional data can be synthesized with one-dimensional space in this model; the model was optimized by Particle Swarm Optimization,and then calculated projection values of the measured samples according to the optimal projection direction. Finally,analysis fire risk by comparing the level projection output value to the projection values of the measured samples,and comparative its evaluation results with other typical methods. Studies shows that this model is more reasonable and reliable than several other methods,not only overcome the limitations of weight values influenced by human,but also had higher resolution and classification accuracy. It had good applicability,provides a more application and popularization new method for the high-rise building fire risk evaluation.

关 键 词:投影寻踪模型 综合评价 高层建筑 火灾风险评价 

分 类 号:X913.4[环境科学与工程—安全科学] X43

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象