摘要
沥青路面施工工艺数字化是沥青路面智慧施工的基础,其数字化信息特征对提供准确高效的施工方案与控制决策具有决定性作用。采用大样本数据统计方法分析沥青混合料拌和、运输、摊铺、碾压四阶段的工艺参数,并进行相关性和降维分析,获取不同施工阶段工艺参数特征,明确参数相关性。结果表明:拌和参数变异性较低,而材料用量偏低出现的情况较多;摊铺温度的分布值偏低,而复压温度和终压温度偏高;摊铺速度和碾压速度偏高的情况较多,异常值主要集中在分布值上限;不同参数的最佳拟合分布函数存在差异,Lognorm函数对施工参数的拟合优度较高,可用于构建施工温度预测模型;拌和参数间的相关性较高,但其与摊铺和碾压参数的相关性低,且摊铺参数和碾压参数间的相关性也低;将十维拌和参数降至二维能够有效保留原十维参数的特征,降维后参数和摊铺碾压参数均具有更高的独立性,但在构建施工控制模型时仍需要慎重选择这些独立参数,以提高模型的精度和泛化能力。
The digitalization of asphalt pavement construction technology was the basis of intelligent construction of asphalt pavement.The digital information features played a decisive role in providing accurate and efficient construction plans and control decisions.Statistics method of big data was used to analyze the process parameters of asphalt mixture in four stages of mixing,transportation,paving and rolling.In addition,correlation and dimensional reduction analyses were carried out,to obtain the characteristics of process parameters in different construction stages and clarify the correlation.The results show that the variability of mixing parameters is low,while the amount of materials used is low.The distribution of paving value is low,while the re-rolling temperature and final-rolling temperature is high.The paving speed and rolling speed tend to be greater,and the abnormal value mainly appeares in the upper limit of the distribution.The best fitting distribution functions of different parameters are different.Lognorm function has a great goodness of fit for construction parameters,which can be used to build a construction temperature prediction model.The correlation between mixing parameters is great,but it is low with paving and rolling parameters.Moreover,the correlation between paving parameters and rolling parameters is also low.With the dimensional reduction analysis,the 10 dimensions of mixing parameters are reduced to 2dimensions,which can effectively retain the characteristics of the original 10dimensions parameters.After dimensional reduction,paving and rolling parameters highly independent,but these independent parameters still need to be carefully selected to establish the construction control model,so as to improve the accuracy and generalization of the model.2tabs,12figs,20refs.
作者
司伟
王锐
张博文
李宁
次旦多杰
马骉
SI Wei;WANG Rui;ZHANG Bo-wen;LI Ning;CIDAN Duo-jie;MA Biao(Key Laboratory of Special Area Highway Engineering of Ministry of Education,Chang'an University,Xi'an 710064,Shaanxi,China;Tibet Tianlu Co.,Ltd,Lhasa 850000,Tibet,China;School of Civil Engineering,Xi'an University of Architecture and Technology,Xi'an 710055,Shaanxi,China)
出处
《长安大学学报（自然科学版）》
CAS
CSCD
北大核心
2023年第1期18-29,共12页
Journal of Chang’an University(Natural Science Edition)
基金
国家自然科学基金项目(52278430)
西藏自治区自然科学基金重点项目(XZ202101ZR0046G)
西藏自治区科技厅重大科技专项西藏天路科创基金项目(XZ 2019TL-G-05)
中国博士后科学基金项目(2022MD713805)
陕西省自然科学基础研究计划项目(2022JQ-560)。
关键词
道路工程
沥青路面
施工工艺
参数特征
降维分析
相关性
数字化信息
road engineering
asphalt pavement
construction technology
parameter characteristic
dimensional reduction analysis
correlation
digital information
