基于GA-BP神经网络的碾压混凝土压实度实时评价方法
|
摘要
针对碾压混凝土现场压实程度的实时工艺评价需求,选择含湿率、碾压层表面应力横波波速、级配以及胶砂比为预测参数,构建了GA-BP神经网络压实度预测模型;结合现场应用实例,验证该方法实时预测评价的有效性。结果表明:与BP神经网络模型比较,GA-BP神经网络模型不仅预测精度更高,而且偏差波动范围更小,稳定性好,能更准确有效地预测现场碾压层混凝土压实性;GA-BP神经网络模型对碾压混凝土压实度下限值更敏感,压实度处于93%～96%的样本点,模型预测值的平均误差仅为0.08%,最大误差仅为0.17%,预测精度很高。
Aiming at the requirements of the real-time process evaluation for the on-site compaction degree of roller-compacted concrete(RCC), prediction parameters such as the moisture content, the shear wave velocity on the surface of compacted fresh concrete, aggregate gradation, the ratio of cementitious material and sand are selected to construct a prediction model based on GA-BP neural network. The effectiveness of the proposed real-time evaluation method was validated by an on-site application case. The results show that compared with BP neural network models, GA-BP model has a higher prediction accuracy with a smaller range of deviation fluctuation and it can predict the real-time compaction degree of RCC accurately and effectively with higher stability. GA-BP model is more sensitive to the lower limit value of the compaction degree. For samples with the compaction degree ranging from 93% to 96%, the average error of the GA-BP model is only 0.08% and the maximum one is only 0.17%, revealing very high prediction accuracy.
Aiming at the requirements of the real-time process evaluation for the on-site compaction degree of roller-compacted concrete(RCC), prediction parameters such as the moisture content, the shear wave velocity on the surface of compacted fresh concrete, aggregate gradation, the ratio of cementitious material and sand are selected to construct a prediction model based on GA-BP neural network. The effectiveness of the proposed real-time evaluation method was validated by an on-site application case. The results show that compared with BP neural network models, GA-BP model has a higher prediction accuracy with a smaller range of deviation fluctuation and it can predict the real-time compaction degree of RCC accurately and effectively with higher stability. GA-BP model is more sensitive to the lower limit value of the compaction degree. For samples with the compaction degree ranging from 93% to 96%, the average error of the GA-BP model is only 0.08% and the maximum one is only 0.17%, revealing very high prediction accuracy.
引文
[1]房纯钢,姜福田,鲁英,等.实时控制碾压混凝土压实质量[J].水力发电,1996(10):26-30.(FANG Chungang,JIANG Futian,LU Ying,et al.Real-time control of the RCC compaction quality[J].Water Power,1996(10):26-30.(in Chinese))
[2]林达.碾压混凝土坝施工压实质量预测模型研究[D].天津:天津大学,2012.
[3]刘东海,李丙扬,崔博.高碾压混凝土坝智能碾压理论研究[J].中国工程科学,2011,13(12):74-79.(LIUDonghai,LI Bingyang,CUI Bo.Intelligent compaction theory of high roller compacted concrete dam[J].Engineering Sciences,2011,13(12):74-79.(in Chinese))
[4]杨斌.高填方渠道填筑碾压质量实时监控与压实度预测模型研究[D].天津:天津大学,2012.
[5]WANG Q W,ZHONG D H,BIN-PING W U,et al.Construction simulation approach of roller-compacted concrete dam based on real-time monitoring[J].Journal of Zhejiang University:Science A(Applied Physics&Engineering),2018,19(5):367-383.
[6]刘东海,连振宏,李子龙.土石坝填筑碾压机械激振性态实时监控系统[J].水电能源科学,2015(10):68-71.(LIU Donghai,LIAN Zhenhong,LI Zilong.Real-time roller exciting behaviors monitoring system of earth-rock dam compaction[J].Water Resources and Power,2015(10):68-71.(in Chinese))
[7]LUDWIG D,NANNI A.Application of roller-compacted concrete(RCC)technology to roadway paving[R].Washingten D.C.:US Army Engineer Waterways Experiment Station,1994.
[8]裴亮,代萍,何坤,等.高碾压混凝土拱坝温控可靠性分析[J].水利水电科技进展,2016,36(1):90-94.(PEILiang,DAI Ping,HE Kun,et al.Reliability analysis of temperature control of high RCC arch dam[J].Advances in Science and Technology of Water Resources,2016,36(1):90-94.(in Chinese))
[9]赵春菊,胡超,周宜红.基于OGRE的碾压混凝土坝施工过程可视化仿真系统[J].水利水电科技进展,2013,33(4):41-45.(ZHAO Chunju,HU Chao,ZHOU Yihong.Visual simulation system of RCC dam construction process based on OGRE[J].Advances in Science and Technology of Water Resources,2013,33(4):41-45.(in Chinese))
[10]胡利平,刘鑫,曾国东.压实度和含水率对高液限土宏微观力学特性的影响[J].水利水电科技进展,2014,34(2):4-6.(HU Liping,LIU Xin,ZENG Guodong.Effect of compaction and moisture content on macro-micro mechanical properties of high liquid limit soil[J].Advances in Science and Technology of Water Resources,2014,34(2):4-6.(in Chinese))
[11]刘英,唐杰伟,刘剑波,等.碾压混凝土含湿率快速检测新方法与应用[J].水利水电施工,2015(6):80-83.(LIU Ying,TANG Jiewei,LIU Jianbo,et al.New method and application of rapid detection of moisture content of RCC[J].Construction of Water Resources and Hydropower,2015(6):80-83.(in Chinese))
[12]刘建波.碾压混凝土可碾性和层间结合质量检测研究[D].南京:河海大学,2017.
[13]李青山,张献民,李红英.路基压实度的瞬态瑞雷波检测法[J].河北工业大学学报,2003,32(5):27-30.(LIQingshan,ZHANG Xianmin,LI Hongying.The method of transient reyleigh wave applied in roadbed compaction degree test[J].Journal of Hebei University of Technology,2003,32(5):27-30.(in Chinese))
[2]林达.碾压混凝土坝施工压实质量预测模型研究[D].天津:天津大学,2012.
[3]刘东海,李丙扬,崔博.高碾压混凝土坝智能碾压理论研究[J].中国工程科学,2011,13(12):74-79.(LIUDonghai,LI Bingyang,CUI Bo.Intelligent compaction theory of high roller compacted concrete dam[J].Engineering Sciences,2011,13(12):74-79.(in Chinese))
[4]杨斌.高填方渠道填筑碾压质量实时监控与压实度预测模型研究[D].天津:天津大学,2012.
[5]WANG Q W,ZHONG D H,BIN-PING W U,et al.Construction simulation approach of roller-compacted concrete dam based on real-time monitoring[J].Journal of Zhejiang University:Science A(Applied Physics&Engineering),2018,19(5):367-383.
[6]刘东海,连振宏,李子龙.土石坝填筑碾压机械激振性态实时监控系统[J].水电能源科学,2015(10):68-71.(LIU Donghai,LIAN Zhenhong,LI Zilong.Real-time roller exciting behaviors monitoring system of earth-rock dam compaction[J].Water Resources and Power,2015(10):68-71.(in Chinese))
[7]LUDWIG D,NANNI A.Application of roller-compacted concrete(RCC)technology to roadway paving[R].Washingten D.C.:US Army Engineer Waterways Experiment Station,1994.
[8]裴亮,代萍,何坤,等.高碾压混凝土拱坝温控可靠性分析[J].水利水电科技进展,2016,36(1):90-94.(PEILiang,DAI Ping,HE Kun,et al.Reliability analysis of temperature control of high RCC arch dam[J].Advances in Science and Technology of Water Resources,2016,36(1):90-94.(in Chinese))
[9]赵春菊,胡超,周宜红.基于OGRE的碾压混凝土坝施工过程可视化仿真系统[J].水利水电科技进展,2013,33(4):41-45.(ZHAO Chunju,HU Chao,ZHOU Yihong.Visual simulation system of RCC dam construction process based on OGRE[J].Advances in Science and Technology of Water Resources,2013,33(4):41-45.(in Chinese))
[10]胡利平,刘鑫,曾国东.压实度和含水率对高液限土宏微观力学特性的影响[J].水利水电科技进展,2014,34(2):4-6.(HU Liping,LIU Xin,ZENG Guodong.Effect of compaction and moisture content on macro-micro mechanical properties of high liquid limit soil[J].Advances in Science and Technology of Water Resources,2014,34(2):4-6.(in Chinese))
[11]刘英,唐杰伟,刘剑波,等.碾压混凝土含湿率快速检测新方法与应用[J].水利水电施工,2015(6):80-83.(LIU Ying,TANG Jiewei,LIU Jianbo,et al.New method and application of rapid detection of moisture content of RCC[J].Construction of Water Resources and Hydropower,2015(6):80-83.(in Chinese))
[12]刘建波.碾压混凝土可碾性和层间结合质量检测研究[D].南京:河海大学,2017.
[13]李青山,张献民,李红英.路基压实度的瞬态瑞雷波检测法[J].河北工业大学学报,2003,32(5):27-30.(LIQingshan,ZHANG Xianmin,LI Hongying.The method of transient reyleigh wave applied in roadbed compaction degree test[J].Journal of Hebei University of Technology,2003,32(5):27-30.(in Chinese))