基于高密度数据和聚类分析的独立车辙识别和评价

发布时间：2018-12-11 11:57

【摘要】：现行规范《公路技术状况评定标准》(JTG H20—2007)以一定长度内车辙检测的平均值作为车辙评价值,而均值会对实际的车辙深度产生平滑作用。为量化现行规范车辙评价方法对车辙评价的误差,充分挖掘高密度检测数据,更加准确地对车辙进行评价,定义独立车辙,提出了基于高密度数据和聚类分析的独立车辙识别和评价方法。研究了不同数据密度识别独立车辙的结果,并利用实际1km和20km的自动化车辙检测数据,说明所提方法识别和评价独立车辙的严重程度及分布位置的有效性和准确性,将结果与现行规范车辙评价方法所得结果进行对比,对2种结果的误差进行了量化。研究结果表明:所提方法适用于所有等间隔的高密度车辙检测数据,而现行规范采用1km车辙深度平均的评价方法所得结果已不能准确反映车辙的严重程度及位置。1km路段中,利用所提方法能够找到3条独立车辙,并确定其位置和严重程度,对独立车辙的评价结果较现行规范车辙评价结果更加准确;20km路段中,利用现行规范车辙评价方法只有25.1%的车辙被识别出,其中仅18.52%的车辙能够正确判断严重程度。而利用所提方法可识别全部车辙,且车辙严重程度判断正确率达到82.3%。结果显示现行规范采用1km车辙深度平均的评价方法不适用于分布不均匀的车辙评价,且车辙严重程度越高,分布不均匀程度越大,评价误差越大。
[Abstract]:JTG H20-2007, the current standard for evaluation of highway technical status, takes the average value of rutting detection within a certain length as the rut evaluation value, and the mean value will have a smoothing effect on the actual rut depth. In order to quantify the error of the current rut evaluation method, fully excavate the data of high density detection, evaluate the rut more accurately and define the independent rut. An independent rut recognition and evaluation method based on high density data and cluster analysis is proposed. The results of identifying independent ruts with different data densities are studied, and the validity and accuracy of the proposed method for identifying and evaluating the severity, distribution and location of independent ruts are illustrated by using the actual automatic rutting detection data of 1km and 20km. The results are compared with the results obtained by the current rutting evaluation method, and the errors of the two results are quantified. The results show that the proposed method is suitable for all the data of high-density rutting detection at equal intervals, but the evaluation results obtained by using 1km rutting depth average method in current codes can no longer accurately reflect the severity and location of ruts. Using the proposed method, three independent ruts can be found, and their position and severity can be determined. The evaluation results of the independent ruts are more accurate than those of the current standard ruts. In 20km section, only 25.1% ruts are identified by using the current rut evaluation method, and only 18.52% ruts can correctly judge the severity. By using the proposed method, all ruts can be identified, and the correct rate of judging the severity of rutting is 82.3%. The results show that the 1km rutting depth averaging method is not suitable for the rutting evaluation with uneven distribution, and the higher the rutting severity is, the greater the uneven distribution degree is and the greater the evaluation error is.
【作者单位】：长安大学公路学院;
【基金】：国家自然科学基金项目(51508034) 陕西省交通运输科技项目(12-15K) 内蒙古自治区交通运输科技项目(NJ-2015-31) 中央高校基本科研业务费专项资金项目(310821153104,310821151006)
【分类号】：U418.68

【参考文献】