﻿ 融合混沌残差的BP强预测器的地表下沉预测模型
 文章快速检索 高级检索
 大地测量与地球动力学  2020, Vol. 40 Issue (9): 913-917  DOI: 10.14075/j.jgg.2020.09.007

### 引用本文

CHEN Xingda, YU Xuexiang, CHI Shengsheng, et al. Surface Subsidence Prediction Model of BP Strong Predictor Fusing Chaos Residuals[J]. Journal of Geodesy and Geodynamics, 2020, 40(9): 913-917.

### Foundation support

Foundation of Huainan Mining (Group) Co Ltd, No.HZMDGB-JF2013-14;Foundation of Huaizhe Coal Power Co Ltd, No.HZMDGB-JF2019-0501.

### Corresponding author

YU Xuexiang, PhD, professor, majors in GNSS mine deformation monitoring automation, E-mail:1064365177@qq.com.

### 第一作者简介

CHEN Xingda, postgraduate, majors in geodesy and survey engineering, E-mail:2576082434@qq.com.

### 文章历史

1. 安徽理工大学测绘学院，安徽省淮南市泰丰大街168号，232001;
2. 安徽理工大学矿山采动灾害空天地协同监测与预警安徽普通高校重点实验室，安徽省淮南市泰丰大街168号，232001;
3. 安徽理工大学矿区环境与灾害协同监测煤炭行业工程研究中心，安徽省淮南市泰丰大街168号，232001

1.1 混沌残差序列的预测

1.1.1 残差序列的相空间重构

 $\begin{array}{c} \left[ {\begin{array}{*{20}{c}} {{\mathit{\boldsymbol{X}}_1}}&{{\mathit{\boldsymbol{X}}_2}}& \cdots &{{\mathit{\boldsymbol{X}}_K}} \end{array}} \right] = \\ \left[ {\begin{array}{*{20}{c}} {{d_1}}&{{d_2}}& \cdots &{{d_K}}\\ {{d_{1 + \tau }}}&{{d_{2 + \tau }}}& \cdots &{{d_{K + \tau }}}\\ {{d_{1 + 2\tau }}}&{{d_{2 + 2\tau }}}& \cdots &{{d_{K + 2\tau }}}\\ {}& \vdots & \vdots & \vdots \\ {{d_{1 + \left( {m - 1} \right)\tau }}}&{{d_{2 + \left( {m - 1} \right)\tau }}}& \cdots &{{d_{K + \left( {m - 1} \right)\tau }}} \end{array}} \right] \end{array}$ (1)

1.1.2 残差序列混沌特性的识别

1.1.3 一阶加权局域预测法

 ${\rm{p}}{{\rm{d}}_i} = \frac{{{\rm{exp}}( - c({\rm{di}}{{\rm{s}}_i} - {\rm{di}}{{\rm{s}}_{{\rm{min}}}}))}}{{\sum\limits_{i = 1}^q {{\rm{exp}}( - c({\rm{di}}{{\rm{s}}_i} - {\rm{di}}{{\rm{s}}_{{\rm{min}}}}))} }}$ (2)

 $\mathit{\boldsymbol{X}}{_{mi + 1}} = \alpha \mathit{\boldsymbol{e}} + b{\mathit{\boldsymbol{X}}_{mi}}$ (3)

 $\sum\limits_{i = 1}^q {{\rm{p}}{{\rm{d}}_i}{{({\mathit{\boldsymbol{X}}_{mi + 1}} - \alpha \mathit{\boldsymbol{e}} + b{\mathit{\boldsymbol{X}}_{mi}})}^2} = {\rm{min}}}$ (4)

 图 1 融合混沌残差的BP-Adaboost预测算法流程 Fig. 1 Flow chart of BP-Adaboost algorithm fused with chaotic residuals

 $y = {\rm{pre}} + \varepsilon$ (5)

2 工程实例 2.1 工程应用

 图 2 最大下沉点MS23下沉图 Fig. 2 MS23 sinking plot
2.2 最大下沉点活跃期的预测

2.3 最大下沉点稳定期的预测

3 结语

 [1] 李培现.深部开采地表沉陷规律及预测方法研究[D].徐州: 中国矿业大学, 2012 (Li Peixian. Study on Regularity and Prediction Method of Surface Subsidence Due to Deep Mining[D]. Xuzhou: China University of Mining and Technology, 2012) http://cdmd.cnki.com.cn/Article/CDMD-10290-1012032583.htm (0) [2] Ding D X, Zhang Z J, Bi Z W. A New Approach to Predicting Mining Induced Surface Subsidence[J]. Journal of Central South University of Technology, 2006, 13(4): 438-444 DOI:10.1007/s11771-006-0064-y (0) [3] 何君, 杨国东. 灰色预测理论在建筑物沉降中的应用研究[J]. 测绘通报, 2012(3): 63-64 (He Jun, Yang Guodong. On the Application of Grey Theory in Building Settlement[J]. Bulletin of Surveying and Mapping, 2012(3): 63-64) (0) [4] Li L, Wu K, Zhou D W. Extraction Algorithm of Mining Subsidence Information on Water Area Based on Support Vector Machine[J]. Environmental Earth Sciences, 2014, 72(10): 3 991-4 000 DOI:10.1007/s12665-014-3288-4 (0) [5] 谭洋, 牛雪峰, 王明常. 径向基神经网络在沉降预测中的应用[J]. 测绘科学, 2016, 41(4): 33-36 (Tan Yang, Niu Xuefeng, Wang Mingchang. Application of Radial Basis Function Neural Networks in Settlement Predictive Model[J]. Science of Surveying and Mapping, 2016, 41(4): 33-36) (0) [6] 魏博文, 熊威, 李火坤, 等. 融合混沌残差的大坝位移蛙跳式组合预报模型[J]. 武汉大学学报:信息科学版, 2016, 41(9): 1 272-1 278 (Wei Bowen, Xiong Wei, Li Huokun, et al. Dam Deformation Forecasting of Leapfrog Combined Model Merging Residual Errors of Chaos[J]. Geomatics and Information Science of Wuhan University, 2016, 41(9): 1 272-1 278) (0) [7] Blekas K, Likas A. Sparse Regression Mixture Modeling with the Multi-Kernel Relevance Vector Machine[J]. Knowledge and Information Systems, 2014, 39(2): 241-264 (0) [8] 罗亦泳, 姚宜斌, 赵庆志, 等. 利用优化的组合核相关向量机算法构建地表下沉预测模型[J]. 武汉大学学报:信息科学版, 2018, 43(9): 1 295-1 301 (Luo Yiyong, Yao Yibin, Zhao Qingzhi, et al. Prediction of Surface Subsidence of Underground Mining Based on HIOA and MK-RVM[J]. Geomatics and Information Science of Wuhan University, 2018, 43(9): 1 295-1 301) (0) [9] 王晶晶, 尹晖. 一种建筑沉降叠加预测方法[J]. 测绘科学, 2019, 44(3): 107-113 (Wang Jingjing, Yin Hui. A Method of Building Settlement Superposition Prediction Based on ARMA Model[J]. Science of Surveying and Mapping, 2019, 44(3): 107-113) (0) [10] 李苋兰, 张顶, 黄晞. 基于BP-AdaBoost神经网络的多参数掌静脉图像质量评价法[J]. 计算机系统应用, 2020, 29(3): 20-28 (Li Xianlan, Zhang Ding, Huang Xi. Multi-Parameter Palm Vein Image Quality Evaluation Method Based on BP-AdaBoost Neural Network[J]. Computer Systems and Applications, 2020, 29(3): 20-28) (0) [11] 刘艳丽, 陈跃东. 基于BP-Adaboost的目标跟踪算法应用研究[J]. 河北工程大学学报:自然科学版, 2012, 29(3): 99-102 (Liu Yanli, Chen Yuedong. The Applied Research of Motive Object Tracking Based on BP[J]. Adaboost Algorithm:Natural Science Edition, 2012, 29(3): 99-102) (0) [12] 董春娇, 邵春福, 张辉, 等. 基于G-P算法的快速路交通流参数相空间重构[J]. 吉林大学学报:工学版, 2012, 42(3): 594-599 (Dong Chunjiao, Shao Chunfu, Zhang Hui, et al. Phase Space Reconstruction of Traffic Flow Parameters on Expressway Based on G-P Algorithm[J]. Journal of Jilin University:Engineering and Technology Edition, 2012, 42(3): 594-599) (0) [13] 张安兵.动态变形监测数据混沌特性分析及预测模型研究[D].徐州: 中国矿业大学2009 (Zhang Anbing. Study on Chaotic Characteristic and Prediction Model of Dynamic Deformation Monitoring Data[D]. Xuzhou: China University of Mining and Technology, 2009) http://cdmd.cnki.com.cn/Article/CDMD-10290-2009222856.htm (0)
Surface Subsidence Prediction Model of BP Strong Predictor Fusing Chaos Residuals
CHEN Xingda1,2,3     YU Xuexiang1,2,3     CHI Shengsheng1,2,3     JIANG Chuang1,2,3     ZHAO Xiangshuo1,2,3
1. School of Geomatics, Anhui University of Science and Technology, 168 Taifeng Street, Huainan 232001, China;
2. Key Laboratory of Aviation-Aerospace-Ground Cooperative Monitoring and Early Warning of Coal Mining-Induced Disasters of Anhui Higher Education Institutes, Anhui University of Science and Technology, 168 Taifeng Street, Huainan 232001, China;
3. Coal Industry Engineering Research Center of Mining Area Environmental and Disaster Cooperative Monitoring, Anhui University of Science and Technology, 168 Taifeng Street, Huainan 232001, China
Abstract: In order to improve the accuracy of the prediction results caused by underground mining, we propose a surface subsidence prediction model of BP-Adaboost, which fuses chaos residuals. Taking the measured value of 1312 (1) of Gubei mine as an example, we use the BP-Adaboost models, the BP neural network model, and BP-Adaboost model fused with chaotic residuals to make one-step and multi-step predictions for the stability and active period of the maximum sinking value point, respectively. The experimental results show that BP-Adaboost model fused with chaotic residuals has the highest accuracy in both one-step prediction and multi-step prediction, especially for one-step prediction.
Key words: chaos sequence; BP strong predictor; BP neural network; surface subsidence prediction; residual