基于极限梯度提升的公路深层病害雷达识别
作者:
作者单位:

同济大学 道路与交通工程教育部重点实验室,上海201804

作者简介:

杜豫川(1976—),男,教授,工学博士,主要研究方向为交通全息感知与智能计算技术及其在智慧高速、车路协同领域的应用技术。 E-mail: ycdu@tongji.edu.cn

通讯作者:

基金项目:


Road Diseases Recognition of Ground Penetrating Radar Based on Extreme Gradient Boosting
Author:
Affiliation:

Key Laboratory of Road and Traffic Engineering of the Ministry of Education, Tongji University, Shanghai 201804, China

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
    摘要:

    针对探地雷达A-scan数据检测多类公路深层病害准确率不高的问题,首先通过实地数据采集、钻芯取样技术,结合数据预处理和专家解释过程,建立大量具有公路深层病害类别标签的A-scan数据库。对不同类别与不同严重程度的病害表征进行对比分析,充分挖掘公路深层病害的细节表征。最后,基于时域-频域多维度,选取A-scan反射波的能量、方差、峰度和对数功率谱作为特征值,引入人工智能分类方法中表现出色的极限梯度提升XGBoost算法(Extreme Gradient Boosting)对数据进行训练和分类预测。结果表明:通过对病害特征的有效提取,XGBoost分类算法对脱空、疏松、裂缝或断层类病害的识别精度均可达90%以上。

    Abstract:

    Based on the GPR A-scan data, in order to further implement rapid intelligent detection of highway diseases, first of all, through data collection, sampling, data pre-processing and expert interpretation, road disease datasets with labels were established. A comparative analysis on different diseases and its degrees of severity was carried out to fully explore the characteristics of underground diseases. Based on the dimensions of time and frequency domain, the energy, variance, kurtosis and log power spectrum of A-scan were selected as the features to research the distribution of various road diseases. Finally, a state-of-art classification named Extreme Gradient Boosting algorithm (XGBoost, Extreme Gradient Boosting) was introduced to train and classify the data. The results show that the XGBoost classification algorithm achieves the accuracy of more than 90% for voids, looseness, cracks recognition.

    表 4 不同分类算法效果对比Table 4
    表 1 探地雷达系统参数设置Table 1
    表 3 试验数据集的样本构成Table 3
    图1 数据采集与验证Fig.1 Data collection and verification
    图2 各类病害的A-scan和B-scan图像Fig.2 A-scan and B-scan data of different diseases
    图3 训练集数据的特征分布Fig.3 Feature distribution of training data
    图4 XGBoost学习模型的测试效果Fig.4 Training results based on XGBoost model
    表 2 A-scan数据集的病害类型与数量Table 2
    参考文献
    相似文献
    引证文献
引用本文

杜豫川,都州扬,刘成龙.基于极限梯度提升的公路深层病害雷达识别[J].同济大学学报(自然科学版),2020,48(12):1742~1750

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
历史
  • 收稿日期:2020-05-18
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2020-12-31