摘要
悬移质粒径分布作为研究水体运动规律和水利建设中的关键参数,通过对Epstein-Carhart-Allegra-Hawley(ECAH)模型和超声衰减实验这类先验信息的研究,结合机器学习算法对悬移质颗粒粒径进行预测。根据超声衰减实验和其他相关物性参数提取特征,结合筛分法确定的粒径分布种类制作训练数据集和验证数据集,通过对单种粒径预测的梯度提升决策树(Gradient Boosting Decision Tree,GBDT)算法进行组合构建多输出回归算法对粒径分布进行预测。结果表明:三种样品单种粒径的最大相对误差在±10%以内,中位径误差分别为0.07%、−0.10%和−2.20%;在实验范围内,预测分布结果与筛分法结果一致,有较高的可行性和准确度,可为粒径分布测量提供一种新的思路。
The particle size distribution of suspended sediment is a key parameter in the study of water movement regulation and water conservancy construction.By combing the study of prior information such as Epstein-CarhartAllegra-Hawley(ECAH)model and ultrasonic attenuation experiment with the machine learning algorithms,the particle size of suspended sediment can be predicted.Features are extracted from the ultrasonic attenuation experiments and other related physical parameters,and labels are the particle size distributions determined by the sieving method.The training data sets and the verification data sets are made by the features and labels.The multi-output regression algorithm is constructed by combining the gradient boosting decision tree(GBDT)algorithm of single particle size prediction to predict the particle size distribution.The results show that the maximum relative errors of the single particle size of three samples are within±10%,and the median diameter errors are 0.07%,−0.10%and−2.20%respectively.The predicted distributions are consistent with the results of the sieving method in the experimental range,which shows that the method has high feasibility and accuracy and can provide a new idea for particle size distribution measurement.
作者
应启帆
谢代梁
徐志鹏
徐雅
刘铁军
黄震威
YING Qifan;XIE Dailiang;XU Zhipeng;XU Ya;LIU Tiejun;HUANG Zhenwei(Key Lab.of Flow Meas.Tech.of Zhejiang Province,China Jiliang University,Hangzhou 310018,Zhejiang,China)
出处
《声学技术》
CSCD
北大核心
2022年第1期137-143,共7页
Technical Acoustics
基金
国家重点研发计划(2018YFF0216001)、浙江省自然科学基金(#LY17F030013
#LQ19E060005)资助项目。
关键词
多输出回归
超声衰减
粒径分布
特征选择
multiple output regression
ultrasonic attenuation
particle size distribution
feature selection
