当前位置:主页 > 科技论文 > 地质论文 >

ELMD并联式组合模型在沉降分析中的可行性研究

发布时间:2018-06-13 08:53

  本文选题:精密工程测量 + 总体局部均值分解 ; 参考:《武汉大学学报(信息科学版)》2017年10期


【摘要】:时频分解方法局部均值分解(local mean decomposition,LMD)在沉降监测中已经得到了应用,但在使用中会出现模态混叠现象。总体局部均值分解(ensemble local mean decomposition,ELMD)通过添加辅助噪声可以抑制局部均值分解过程中出现的模态混叠现象。提出了一种基于ELMD的并联式组合沉降预测方法,结合高速铁路某桥梁实际监测数据,在对ELMD模型进行仿真分析的基础上,分别使用ELMD和LMD将一组离散非线性信号分解为3个PF分量和1个剩余分量,并利用支持向量机和卡尔曼滤波进行预测验证。结果表明:使用ELMD进行分解的过程中能够很好地抑制LMD方法中出现的模态混叠问题。在预报精度方面,基于ELMD的并联式组合模型的平均相对误差可以达到8.3%,可为沉降监测的预报工作提供参考和借鉴。
[Abstract]:Local mean decompositionLMD (local mean decomposition method) has been applied in settlement monitoring, but modal aliasing will occur in use. Total local mean decomposition (LMS) can suppress modal aliasing in the process of local mean decomposition by adding auxiliary noise. A parallel combined settlement prediction method based on ELMD is proposed. Based on the actual monitoring data of a bridge in high-speed railway, the ELMD model is simulated and analyzed. A set of discrete nonlinear signals are decomposed into three PF components and one residual component using ELMD and LMD respectively. The prediction is verified by support vector machine and Kalman filter. The results show that the modal aliasing problem in LMD method can be well suppressed by using ELMD in the process of decomposition. In the aspect of prediction accuracy, the average relative error of parallel combined model based on ELMD can reach 8.3, which can provide reference and reference for the prediction of settlement monitoring.
【作者单位】: 四川省第三测绘工程院;西南交通大学地球科学与环境工程学院;四川隧唐科技股份有限公司;株洲中车时代电气股份有限公司;
【基金】:国家自然科学基金(41374002) 四川省科技计划项目(2015JQ0046) 长江学者和创新团队发展计划项目(IRT13092)~~
【分类号】:TU433


本文编号:2013442

资料下载
论文发表

本文链接:https://www.wllwen.com/kejilunwen/diqiudizhi/2013442.html


Copyright(c)文论论文网All Rights Reserved | 网站地图 |

版权申明:资料由用户af202***提供,本站仅收录摘要或目录,作者需要删除请E-mail邮箱bigeng88@qq.com