基于路网级检测数据的PQI的数据特点挖掘

PQI based on network-level detection data data feature mining

基于JTG 5210—2018公路技术状况评定标准仅采用PQI的平均值对数据进行评价,过于单一,且未能从数据分布的整体特点出发,在实际管养中产生的流弊就是重排名、重局部提升、重短效提升。试着通过百分位数、z-分数、累计频数分布、箱线图、假设检验、x的抽样分布等手段,认识数据特点,挖掘数据价值,并用中位数对管养单位进行排序,采用假设检验进行分组,画出各组x的抽样分布图,以期丰富数据统计、分析的维度。

The starting point of this paper is that the“Highway Technical Condition Assessment Standard”(JTG 5210—2018)only uses the average value of PQI to evaluate the data,which is too simple,and because it fails to start from the overall characteristics of data distribution,the disadvantages in the actual management are the emphasis on ranking,local improvement,and short-term efficiency improvement.In this paper,we try to understand the characteristics of the data,mine the value of the data,sort the median of the custody units,group them by hypothesis testing,and draw the sampling distribution map of each group of,so as to enrich the dimensions of data statistics and analysis.