基于高密度數(shù)據(jù)和聚類分析的獨立車轍識別和評價
發(fā)布時間：2018-12-11 11:57
【摘要】：現(xiàn)行規(guī)范《公路技術(shù)狀況評定標準》(JTG H20—2007)以一定長度內(nèi)車轍檢測的平均值作為車轍評價值,而均值會對實際的車轍深度產(chǎn)生平滑作用。為量化現(xiàn)行規(guī)范車轍評價方法對車轍評價的誤差,充分挖掘高密度檢測數(shù)據(jù),更加準確地對車轍進行評價,定義獨立車轍,提出了基于高密度數(shù)據(jù)和聚類分析的獨立車轍識別和評價方法。研究了不同數(shù)據(jù)密度識別獨立車轍的結(jié)果,并利用實際1km和20km的自動化車轍檢測數(shù)據(jù),說明所提方法識別和評價獨立車轍的嚴重程度及分布位置的有效性和準確性,將結(jié)果與現(xiàn)行規(guī)范車轍評價方法所得結(jié)果進行對比,對2種結(jié)果的誤差進行了量化。研究結(jié)果表明:所提方法適用于所有等間隔的高密度車轍檢測數(shù)據(jù),而現(xiàn)行規(guī)范采用1km車轍深度平均的評價方法所得結(jié)果已不能準確反映車轍的嚴重程度及位置。1km路段中,利用所提方法能夠找到3條獨立車轍,并確定其位置和嚴重程度,對獨立車轍的評價結(jié)果較現(xiàn)行規(guī)范車轍評價結(jié)果更加準確;20km路段中,利用現(xiàn)行規(guī)范車轍評價方法只有25.1%的車轍被識別出,其中僅18.52%的車轍能夠正確判斷嚴重程度。而利用所提方法可識別全部車轍,且車轍嚴重程度判斷正確率達到82.3%。結(jié)果顯示現(xiàn)行規(guī)范采用1km車轍深度平均的評價方法不適用于分布不均勻的車轍評價,且車轍嚴重程度越高,分布不均勻程度越大,評價誤差越大。
[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.
【作者單位】： 長安大學公路學院;
【基金】：國家自然科學基金項目(51508034) 陜西省交通運輸科技項目(12-15K) 內(nèi)蒙古自治區(qū)交通運輸科技項目(NJ-2015-31) 中央高校基本科研業(yè)務(wù)費專項資金項目(310821153104,310821151006)
【分類號】：U418.68
[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.
【作者單位】： 長安大學公路學院;
【基金】：國家自然科學基金項目(51508034) 陜西省交通運輸科技項目(12-15K) 內(nèi)蒙古自治區(qū)交通運輸科技項目(NJ-2015-31) 中央高校基本科研業(yè)務(wù)費專項資金項目(310821153104,310821151006)
【分類號】：U418.68
【參考文獻】
相關(guān)期刊論文 前4條
1 車法;陳拴發(fā);馬慶雷;李洪印;;重載路面車轍評價物元模型構(gòu)建及應(yīng)用[J];廣西大學學報(自然科學版);2010年04期
2 萬成;張肖寧;王紹懷;;RLWT車轍儀車轍評價及應(yīng)用研究[J];筑路機械與施工機械化;2007年12期
3 侯相深;馬松林;王彩霞;;基于行車安全的瀝青路面車轍測量與評價指標的研究[J];公路交通科技;2006年08期
4 武建民,伍石生;瀝青路面長期使用性能指標[J];長安大學學報(自然科學版);2004年03期
【共引文獻】
相關(guān)期刊論文 前10條
1 李會勛;;路基回彈模量對瀝青路面結(jié)構(gòu)設(shè)計的影響分析[J];交通世界;2016年32期
2 惠冰;李甜甜;王迪;;檢測車輛橫向偏移對車轍深度計算誤差分析[J];長安大學學報(自然科學版);2016年03期
3 盧超;蔣龍松;劉化學;;基于LCCA的瀝青路面養(yǎng)護決策及處治方案研究[J];路基工程;2016年01期
4 汪勇;吳麗霞;蔡明;;基于熵權(quán)模糊物元的軌道交通運營安全評價[J];交通運輸研究;2015年06期
5 黃偉業(yè);張亞t，
本文編號：2372508
本文鏈接：http://www.sikaile.net/kejilunwen/daoluqiaoliang/2372508.html
