基于DNN改性沥青中SBS含量的预测模型
作者:
基金项目:

广东省交通运输厅科技项目(科技 2016 02 004)


Determination Model of SBS Content in Modified Asphalt Based on DNN
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [23]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    为准确预测苯乙烯丁二烯苯乙烯嵌段共聚物(SBS)改性沥青中SBS的含量,采用傅里叶变换红外光谱(FTIR)采集了不同SBS含量改性沥青的FTIR图谱,建立了基于深度神经网络(DNN)改性沥青中SBS含量的预测模型,并研究了不同因素对模型预测精度的影响,对比评价了模型的预测精度、敏感性及适用性.结果表明:数据的降维、降噪预处理使SBS含量预测模型的均方误差降低了70%;基于DNN改性沥青中SBS含量预测模型的精度高于标准曲线法和随机森林方法,其对改性沥青中SBS含量的预测具有较好的敏感性及适用性.

    Abstract:

    In order to determinate the content of styrene butadiene styrene block copolymer(SBS) in SBS modified asphalt accurately, the Fourier transform infrared spectroscopy(FTIR) spectra of modified asphalts containing different SBS contents were collected by using FTIR instrument, and the determination model for SBS content in modified asphalt was established based on deep neural network(DNN). The influences of different factors on the accuracy of the determination model were studied, and the accuracy, susceptibility and applicability of the model were evaluated. The results show that mean square error of the SBS content determination model is reduced by 70% by dimension reduction and noise reduction. Determination accuracy for SBS content in modified asphalt using DNN method compares favourably with that using standard curve method and random forest method. It also has good sensitivity and applicability to determination of SBS content in modified asphalt by the DNN determination model.

    参考文献
    [1]LIANG M,XIN X,FAN W Y,et al.Effects of polymerized sulfur on rheological properties,morphology and stability of SBS modified asphalt[J].Construction and Building Materials,2017,150:860 871.
    [2]HUANG W D,TANG N P.Characterizing SBS modified asphalt with sulfur using multiple stress creep recovery test[J].Construction and Building Materials,2015,93:514 521.
    [3]YE F,YIN W,LU H.A model for the quantitative relationship between temperature and microstructure of styrene butadiene styrene modified asphalt[J].Construction and Building Materials,2015,79:397 401.
    [4]LIANG M,LIANG P,FAN W Y,et al.Thermo rheological behavior and compatibility of modified asphalt with various styrene butadiene structures in SBS copolymers[J].Materials and Design,2015,88:177 185.
    [5]ISACSSON U,LU X H.Testing and appraisal of polymer modified road bitumens state of the art[J].Materials and Structures,1995,28(3):139 159.
    [6]LU X H,ISACSSON U,EKBLAD J.Phase separation of SBS polymer modified bitumens[J].Journal of Materials in Civil Engineering,1999,11(1):51 57.
    [7]ZHU J Q,LU X H,KRINGGOS N.Experimental investigation on storage stability and phase separation behaviour of polymer modified bitumen[J].International Journal of Pavement Engineering,2018,19(9):832 841.
    [8]NIU Y F,ZHU Z Q,XIAO J Y,et al.Evaluation of storage stability of styrene butadiene styrene block copolymer modified asphalt via electrochemical analysis[J].Construction and Building Materials,2016,107:38 43.
    [9]MIRZAIYAN D,AMERI M,AMINI A,et al.Evaluation of the performance and temperature susceptibility of gilsonite and SBS modified asphalt binders[J].Construction and Building Materials,2019,207:679 692.
    [10]YAN C Q,HUANG W D,XIAO F P,et al.Proposing a new infrared index quantifying the aging extent of SBS modified asphalt[J].Road Materials and Pavement Design,2018,19(6):1406 1421.
    [11]王康.红外光谱结合神经元网络测定改性沥青SBS含量[J].化学研究与应用,2018,30(12):1938 1942.
    WANG Kang.Determination of SBS content in modified asphalt by infrared spectroscopy combined with neural network[J].Chemical Research and Application,2018,30(12):1938 1942.(in Chinese)
    [12]AZEEZ O S,PRADHAN B,SHAFRI H Z M,et al.Modeling of CO emissions from traffic vehicles using artificial neural networks[J].Applied Sciences,2019,9(2):313.
    [13]张帆,李三喜,李旭日,等.SBS改性沥青的制备与性能[J].沈阳化工大学学报,2003(1):25 28.
    ZHANG Fan,LI Sanxi,LI Xuri,et al.Preparation and properties of SBS modified asphalt[J].Journal of Shenyang University of Chemical Technology,2003(1):25 28.(in Chinese)
    [14]FENG Z G,WANG S J,WANG H J,et al.FTIR and rheology analysis of aging on different ultraviolet absorber modified bitumens[J].Construction and Building Materials,2016,115:48 53.
    [15]LEE D,KIM J,LEE D.Robust concrete crack detection using deep learning based semantic segmentation[J].International Journal of Aeronautical and Space Sciences,2019,20:287 299.
    [16]朱尔一,王小华,杭纬.一种三维矩阵的奇异值分解算法[J].光谱学与光谱分析,2015,35(3):587 590.
    ZHU Eryi,WANG Xiaohua,HANG Wei.A singular value decomposition algorithm for three dimensional matrix[J].Spectroscopy and Spectral Analysis,2015,35(3):587 590.(in Chinese)
    [17]邢安昊,张鹏远,潘接林,等.基SVD的DNN裁剪方法和重训练[J].清华大学学报(自然科学版),2016,56(7):772 776.
    XING Anhao,ZHANG Pengyuan,PAN Jielin,et al.DNN cutting method and retraining based on SVD[J].Journal of Tsinghua University(Natural Science),2016,56(7):772 776.(in Chinese)
    [18]莫菲凡,范伟,周冀衡,等.基于近红外光谱和随机森林方法鉴别蜂蜜真伪[J].食品安全质量检测学报,2014(8):2430 2434.
    MO Feifan,FAN Wei,ZHOU Jiheng,et al.Identification of honey based on near infrared spectroscopy and random forest method[J].Journal of Food Safety and Quality Inspection,2014(8):2430 2434.(in Chinese)
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

王志祥,李建阁.基于DNN改性沥青中SBS含量的预测模型[J].建筑材料学报,2021,24(3):630-636

复制
分享
文章指标
  • 点击次数:211
  • 下载次数: 42
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2019-11-21
  • 最后修改日期:2020-01-08
  • 在线发布日期: 2021-07-02
文章二维码