基于粗糙集和神经网络的地铁站台空气品质综合评价研究

发布时间：2018-07-07 19:28

本文选题：空气品质 + 地铁站台　；参考：《青岛理工大学》2016年硕士论文

【摘要】：随着我国综合国力的提升和经济社会的快速发展,城市生活节奏也在加快,地铁以其快速、便捷的特点在我国得到了飞速的发展,已经成为人们上班出行的首选交通工具。越来越多的人乘坐地铁,人们在地铁站内的停滞时间随之增加,也让地铁站内空气品质问题日益暴露:空气污浊、通风不足、颗粒物污染、噪声污染等。在这样的背景下,人们逐渐开始关注地铁站台的空气品质,也极大地引起了国内外专家学者对地铁站台空气品质的综合评价研究。本文主要针对地铁系统中站台区域的空气品质问题进行研究,选取北京市四个车站:西直门站、复兴门站、灵境胡同站、安德里北街站,在夏季进行温度、相对湿度、风速、噪声、CO_2、甲醛、TVOC、PM_(10)八个指标的现场测试,测试的时间段为早高峰7:00~9:00、非高峰13:00~15:00、晚高峰17:00~19:00,并对测试数据进行了统计与分析,探究了站台空气品质指标的主要影响因素。本文首先在基于对客观实测数据统计分析的基础上,然后尝试通过粗糙集与BP神经网络理论相结合,借助MATLAB平台建立了地铁站台空气品质的综合评价模型,将该模型应用到所测试车站的站台空气品质综合评价研究中,最终得出站台空气品质的等级分类。结合离散化后的指标属性值和评价结果,得到各指标对地铁站台空气品质等级评价的影响由大到小的排序为:温度、相对湿度、噪声、PM_(10)、风速、CO_2。并且对评价结果进行了分析,证明了该模型的合理性。这对于我国地铁建立实用的空气品质评价系统、改善地铁空气品质具有重要的理论和指导意义。在测试与研究过程中得出以下主要结论:(1)四个站点的相对湿度、风速、CO_2浓度、甲醛和TVOC平均水平都低于推荐的标准范围,噪声平均水平都超出推荐的标准,而温度、PM_(10)浓度仅在非换乘小站满足推荐的标准。(2)客流量和屏蔽门是影响地铁站台空气品质最主要的因素。在客流量较大的换乘站地铁站台,空气温度、噪声、CO_2浓度、PM_(10)浓度显著高于客流量较小的非换乘站;在安装有屏蔽门的地铁站台,风速、噪声、PM_(10)浓度低于未安装屏蔽门的地铁站台。(3)一天中地铁站台的空气温度、相对湿度、风速相对稳定,其中人员和设备散热是地铁站台空气温度的主要影响因素,人员散湿、温度及室外气候是影响地铁站台相对湿度不可忽视的因素,“活塞风”以及有无屏蔽门对站台风速影响较大。(4)一天中噪声、CO_2浓度、甲醛、TVOC、PM_(10)浓度呈现出随时间段变化的趋势,其中噪声、CO_2浓度、PM_(10)浓度都是早、晚高峰时段高于非高峰时段,而甲醛、TVOC浓度则随时间段降低。
[Abstract]:With the improvement of our country's comprehensive national strength and the rapid development of economy and society, the rhythm of urban life is also speeding up. The subway has been developing rapidly in our country with its rapid and convenient characteristics, and has become the first choice of transportation for people to go to work. More and more people take the subway, people in the subway station stagnation time increases, also makes the subway station air quality problems increasingly exposed: air pollution, inadequate ventilation, particulate pollution, noise pollution and so on. Under this background, people begin to pay more and more attention to the air quality of the subway platform, which has caused the comprehensive evaluation of the air quality of the subway platform by experts and scholars at home and abroad. In this paper, the air quality problem in platform area of subway system is studied. Four stations in Beijing are selected: Xizhimen Station, Fuxingmen Station, Lingjing Hutong Station, Andriy North Street Station. Temperature, relative humidity, wind speed are carried out in summer. In this paper, the field test of eight indexes of CO2, formaldehyde and TVOC _ (10) is carried out. The test time periods are: morning peak 7: 00 9: 00, off-peak 13: 00 15: 00, late peak 17: 00 / 19: 00. The test data are statistically analyzed and the main influencing factors of air quality index of the platform are explored. On the basis of statistical analysis of objective measured data, this paper attempts to establish a comprehensive evaluation model of air quality of subway platform by combining rough set with BP neural network theory and MATLAB platform. The model is applied to the comprehensive evaluation of platform air quality of the stations tested, and finally the classification of platform air quality is obtained. Combined with the discrete index attribute value and evaluation result, the order of the influence of each index on the air quality grade evaluation of subway platform is as follows: temperature, relative humidity, noise and PM10, wind speed and CO _ 2. The evaluation results are analyzed and the rationality of the model is proved. It has important theoretical and guiding significance for the establishment of practical air quality evaluation system and the improvement of subway air quality in China. The main conclusions are as follows: (1) the relative humidity, the concentration of wind speed, the average level of formaldehyde and TVOC are all lower than the recommended standard range, and the average noise level is higher than the recommended standard. The temperature and PM10 concentration only meet the recommended standard at the non-transfer station. (2) passenger flow and shielding door are the most important factors affecting the air quality of subway platform. The air temperature, noise and PM10 concentration in the subway platform with larger passenger flow are significantly higher than those in the non-transfer station with lower passenger flow, and in the subway platform with shielded doors, the wind speed, (3) the air temperature, relative humidity and wind speed of the subway platform are relatively stable during the day, in which the heat dissipation of the personnel and equipment is the main influencing factor of the air temperature of the subway platform. Temperature and outdoor climate are the factors that can not be ignored in the relative humidity of subway platform. "Piston wind" and the presence of shielding door have great influence on the wind speed of the platform. (4) the concentration of noise CO-2 and formaldehyde TVOC _ (10) show a trend of change with time. The noise CO2 concentration and PM10 concentration were all early, the late peak period was higher than the non-peak period, while the formaldehyde TOC concentration decreased with the time.
【学位授予单位】：青岛理工大学
【学位级别】：硕士
【学位授予年份】：2016
【分类号】：U231.4

【参考文献】