摘要
为了提高ENN(Elman neural network)神经网络获取概率积分预计参数的准确性,以我国30个地表移动观测站的实测数据作为学习训练和测试的样本数据,采用强稳健局部加权回归法(Rlowess,RW)对30个地表移动观测站数据进行降噪处理,采用蚁群算法(Ant Colony Optimization,ACO)对ENN神经网络的权值和阈值进行优化,构建了ACO-ENN概率积分预计参数解算模型。结果表明:对比分析ACO-ENN模型解算RW降噪处理前后的实测数据,发现RW降噪处理显著提高了数据质量,提高了解算模型的预测精度;利用ACO-ENN模型解算下沉系数、水平移动系数、主要影响角正切及拐点偏移距的平均相对误差分别为2.41%、3.48%、6.11%和1.67%,ACO-ENN模型对于概率积分预计参数的解算精度优于传统ENN算法,为精确获取概率积分预计参数提供了新思路。
In order to improve the accuracy of the Elman neural network(ENN)to obtain probability integral prediction parameters.Taking the measured data of 30 surface observation stations in China as the sample data for learning training and testing,and the strong robust local weighted regression method(rlowess,RW)for noise reduction of the 30 surface observation stations data was adopted.Ant colony optimization(ACO)was used to optimize the weights and thresholds of the ENN neural network to construct the ACO-ENN probability integral prediction parameters solving method.The results show that comparing the measured data before and after the ACO-ENN model solved RW noise reduction treatment found that the RW noise reduction treatment significantly improved the data quality and the prediction accuracy of the solved model.The average relative errors of the subsidence coefficient,horizontal movement coefficient,main influence angle tangent and inflection point offset distance solved by using ACO-ENN were 2.41%,3.48%,6.11%,and 1.67%,respectively.The probability integral prediction parameters solved by the ACO-ENN model are better than those solved by the traditional ENN algorithm in terms of accuracy,which provides a new idea to obtain probability integral prediction parameters with higher accuracy.
作者
张劲满
阎跃观
李杰卫
徐瑞瑞
王芷馨
张坤
岳彩亚
ZHANG Jinman;YAN Yueguan;LI Jiewei;XU Ruirui;WANG Zhixin;ZHANG Kun;YUE Caiya(School of Earth Sciences and Surveying Engineering,China University of Mining and Technology-Beijing,Beijing 100083,China;Zhejiang Geology and Mineral Construction Co.,Ltd.,Geological Exploration Bureau of Zhejiang Province,Hangzhou 310052,China;Anhui Provincial Bureau of Coal Geology,Hefei 230088,China;School of Spatial Information and Geomatics Engineering,Anhui University of Science and Technology,Huainan 232001,China;School of Environment and Planning,Liaocheng University,Liaocheng 252000,China)
出处
《金属矿山》
CAS
北大核心
2022年第5期170-176,共7页
Metal Mine
基金
国家自然科学基金项目(编号:41930650)
中央高校基本科研业务费专项(编号:2020XJDC03,2021YQDC09)
中国矿业大学(北京)大学生创新训练项目(编号:202102022)。
关键词
开采沉陷
概率积分法
RW
降噪
蚁群算法
ENN
神经网络
mining subsidence
probability integral method
RW noise reduction
ant colony algorithm
ENN neural network
作者简介
张劲满(1992-),男,博士研究生;通信作者:阎跃观(1981-),男,副教授,博士,硕士研究生导师。
