基于关联监测点数据的非线性变形预测模型

PDF(1889 KB)

振动与冲击 ›› 2021, Vol. 40 ›› Issue (8) : 124-130.

论文

基于关联监测点数据的非线性变形预测模型

李柏佚1,王桂林1, 2,袁军3

作者信息 +

A nonlinear deformation prediction model based on associated monitoring point data

LI Baiyi1,WANG Guilin1,2,YUAN Jun3

Author information +

文章历史 +

摘要

基坑边坡变形具有非平稳性、非线性等特点，且现有的变形预测模型常用单个监测点或整体监测点的数据进行预测，忽略了不同监测点之间的关联性。以重庆某深基坑边坡为例，分别研究基于单个监测点数据和基于关联监测点数据的经验模态分解-粒子群优化算法-BP神经网络（EMD-PSO-BPNN）模型、PSO-BPNN模型、BP神经网络模型的预测结果，并对比了基于整体监测点中非关联多点数据的预测结果。结果表明：EMD模型降低了基坑边坡变形数据非平稳性，使得各分量变化曲线比原监测数据的曲线更光滑和平稳，提高了预测精度；EMD-PSO-BPNN模型具有较好的非线性映射能力、学习能力和自适应能力，预测精度优于其他模型；同种模型下，基于关联点的预测模型预测精度明显高于单个监测点的预测模型。

Abstract

The deformation of foundation pit slope has the characteristics of non-stationarity and non-linearity. Currently, prediction models for foundation pit slope deformation usually use the data of a single monitoring point or overall monitoring points to predict, ignoring the correlation between different monitoring points. Three models, empirical mode decomposition-particle swarm optimization-back propagation neural network(EMD-PSO-BPNN) model, PSO-BPNN model, and BPNN model were built. Those models are based on single monitoring point data and related monitoring point data. Finally, a deep foundation pit slope in Chongqing was used to verify the correctness of those models. The following conclusions can be obtained. In the first place, The EMD model reduces the non-stationarity of the deformation data of the foundation pit slope, and makes the curve of each component smooth and stable, which improves the prediction accuracy. In the second place, the EMD-PSO-BPNN model has better ability of non-linear mapping, learning and self-adaptation. The prediction accuracy of the EMD-PSO-BPNN model is better than that of other models. In the last place, under the same model, the prediction accuracy of the prediction model based on correlation points is significantly higher than that of the prediction model based on single monitoring point.

导出引用

李柏佚1,王桂林1, 2,袁军3. 基于关联监测点数据的非线性变形预测模型[J]. 振动与冲击, 2021, 40(8): 124-130

LI Baiyi1,WANG Guilin1,2,YUAN Jun3. A nonlinear deformation prediction model based on associated monitoring point data[J]. Journal of Vibration and Shock, 2021, 40(8): 124-130

参考文献

［1］罗飞雪, 戴吾蛟. 小波分解与EMD在变形检测应用中的比较［J］. 大地测量与地球动力学,2010, 30(3) : 137-141.
LUO Feixue, DAI Wujiao. Comparison of wavelet decomposition and EMD in deformation detection applications［J］. Journal of Geodesy and Geodynamics, 2010, 30(3) : 137-141.
［2］吴杰, 胡夏闽, 乔燕,等. 基于交叉证认的EMD小波滤波在大桥动态监测去噪中的应用［J］. 振动与冲击, 2017, 36(22):212-217.
WU Jie, HU Xiamin, QIAO Yan, et al. Application of EMD wavelet filtering based on cross-validation in dynamic monitoring and denoising of bridge ［J］. Journal of Vibration and Shock, 2017, 36(22):212-217.
［3］邵东辉. 基于CEEMD低通的隧道爆破振动信号去噪［J］. 工程爆破, 2017, 23(6): 5-10.
SHAO Donghui. Denoising of tunnel blasting vibration signal based on CEEMD low pass［J］. Engineering Blasting,2017,23(6):5-10.
［4］谢世成,黄定川,张逸仙. 顾及点位关联的变形体空间多点预测模型效果分析［J］.勘察科学技术, 2016(3):28-31.
XIE Shicheng, HUANG Dingchuan, ZHANG Yixian. Effect analysis of multi-point prediction model for deformed space considering point correlation［J］. Chinese Journal of Survey Science and Technology, 2016(3):28-31.
［5］周昀琦,王奉伟,周世健,等.顾及邻近点变形因素的高斯过程建模及预测［J］.测绘科学,2018,43(4):114-121.
ZHOU Yunqi, WANG Fengwei, ZHOU Shijian, et al. Modeling and prediction of gaussian process with adjacent deformation factors ［J］. Science of Surveying and Mapping, 2008,43(4):114-121.
［6］HUANG N E , SHEN Z , LONG S R , et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis［J］. Proceedings A, 1998, 454(1971):903-995.
［7］SHEN S S P , SHU T , HUANG N E , et al. HHT analysis of the nonlinear and non-stationnary annual cycle of daily surface air temperature data［M］// 2nd ed. Hilbert-Huang Transform and its Applications. Hackensack :World Science Publishing ,2005.
［8］KENNEDY J. Particle swarm optimization［C］//Proceedings of 1995 IEEE International Conference on Neural Networks.Perth: IEEE, 2011.
［9］YUTTHAPONG T, KURUTACH W. Comparing nonlinear inertia weights and constriction factors in particle swarm optimization［J］. International Journal of Knowledge-based and Intelligent Engineering Systems, 2011, 15(2):65-70.
［10］SHA F , ZHU F , GUO S N , et al. Based on the EMD and PSO-BP neural network of short-term load forecasting［J］. Advanced Materials Research, 2012, 614/615:1872-1875.
［11］金盛杰, 包腾飞, 陈迪辉. 基于EMD分解法的大坝变形预测模型及应用［J］. 水利水电技术, 2017, 48(62): 41-44.
JIN Shengjie, BAO Tengfei, CHEN Dihui. Dam deformation prediction model based on EMD decomposition method and its application ［J］. Water Resources and Hydropower Engineering, 2017, 48(62): 41-44.
［12］李思慧, 刘海卿. 基于LMD-PSO-LSSVM组合模型的深基坑变形预测［J］. 地下空间与工程学报, 2018, 14(2): 483-489.
LI Sihui, LIU Haiqing. Deformation prediction of deep foundation pit based on LMD-PSO-LSSVM combined model［J］. Chinese Journal of Underground Space and Engineering, 2018, 14(2): 483-489.
［13］刘吉超,陈阳舟.基于GA-PSO混合优化的BPNN车速预测方法［J］.交通运输系统工程与信息,2017,17(6):40-47.
LIU Jichao, CHEN Yangzhou. BPNN speed prediction method based on GA-PSO hybrid optimization ［J］. Transportation Systems Engineering and Information,2017,17(6): 40-47.
［14］郭彩杏,郭晓金,柏林江.改进遗传模拟退火算法优化BP算法研究［J］.小型微型计算机系统,2019,40(10):2063-2067.
GUO Caixing, GUO Xiaojin, BAI Linjiang. Study on BP algorithm optimization based on modified genetic simulated annealing algorithm ［J］. Miniature Microcomputer Systems, 2019, 40(10): 2063-2067.
［15］PANKRATZ A. Forecasting with univariate Box-Jenkins models: concepts and cases［M］. Hoboken: Wiley, 2008.