基于混合高斯隐马尔科夫模型的滑坡发生时间预报∗

李丽敏

您当前的位置：

首页 >

文章列表页 >

基于混合高斯隐马尔科夫模型的滑坡发生时间预报∗

“城市综合防灾与抗灾韧性”专题二:生命线工程防灾减灾论文 | 更新时间：2026-01-04

- 基于混合高斯隐马尔科夫模型的滑坡发生时间预报∗
- Landslide Disaster Occurrence Time Prediction Algorithm Based on MOG-HMM
- 防灾减灾工程学报 2023年43卷第2期页码：301-307
- 作者机构：
  
  西安理工大学自动化与信息工程学院,陕西,西安,710048
- 作者简介：
- 基金信息：
  
  国家自然科学基金面上项目(61773016)、国家自然科学基金青年项目(62203344)、陕西省技术创新引导专项(2020CGXNG-009,2020CGXNG-009)、陕西省自然科学基础研究计划(2022JM-322)、陕西省教育厅服务地方专项(22JC036)资助
- DOI：
  中图分类号： X43
- 纸质出版：2023
- 稿件说明：
移动端阅览
李丽敏. 基于混合高斯隐马尔科夫模型的滑坡发生时间预报∗[J]. 防灾减灾工程学报, 2023,43(2):301-307.

李丽敏,夏梦凡,魏雄伟.基于混合高斯隐马尔科夫模型的滑坡发生时间预报∗[J].防灾减灾工程学报,2023,43(2):301-307
李丽敏. 基于混合高斯隐马尔科夫模型的滑坡发生时间预报∗[J]. 防灾减灾工程学报, 2023,43(2):301-307. DOI：

李丽敏,夏梦凡,魏雄伟.基于混合高斯隐马尔科夫模型的滑坡发生时间预报∗[J].防灾减灾工程学报,2023,43(2):301-307 DOI：

摘要

滑坡发生时间预报在防灾减灾工作中非常重要，准确的预报能够有效预防灾害发生可能造成的灾难性结果。为解决当前滑坡预报中仅仅实现对滑坡位移等相关参数的预测和估计，而未最终计算出滑坡发生时间的问题，提出采用混合高斯隐马尔科夫模型(MOG?HMM)建立滑坡发生时间预报模型，即对滑坡灾害演化过程全周期数据利用混合高斯算法计算出宏观信息预报判据，与隐马尔科夫模型中的状态相匹配，建立滑坡演化状态模型，该模型能够反映全周期数据的多个状态，当需要对实时采集的位移数据进行时间预报时，首先利用解码算法对当前数据解码，即计算出其属于滑坡的哪个状态，然后利用 Dijkstra 最优路径规划算法，计算出从当前状态到达滑坡发生状态的时间，实现滑坡发生时间预报。通过对新滩滑坡和卧龙寺滑坡灾害全周期数据进行仿真验证，结果表明，本文方法能够比较准确地计算出滑坡发生的时间，同时利用评价指标对预报的结果进行测试，符合预报指标精度要求。

Abstract

The forecast of landslide occurrence time is very important in disaster prevention and mitigation. Accurate forecasting can effectively prevent the catastrophic consequences of disasters. In order to solve the problem that only the landslide displacement and other related parameters instead of the landslide occurrence time are predicted and estimated in the current landslide forecast method， a mixed Gaussian hidden Markov model (MOG-HMM) is proposed to establish the landslide occurrence time calculation model. The macro-information prediction criterion is calculated by the mixed Gaussian algorithm based on the full-cycle data of the landslide hazard evolution process and matched with the state in the hidden Markov model to establish the landslide evolution state model， which can reflect multiple states of the full-cycle data. When the displacement data collected in real time is needed for time forecasting， the current data is first decoded using the decoding algorithm， that is， to calculate which state the landslide belongs to， then the time from the current state to the occurrence of the landslide is predicted using Dijkstra optimal path planning algorithm， achieving the prediction of the occurrence time of the landslide. The simulation results of the Xintan landslide and the Wolongsi landslide show that the presented method can accurately calculate the landslide occurrence time. At the same time， the validation of the prediction results by using prediction indicators indicates that the results meet the accuracy requirement of the forecast indicators.

关键词

Keywords

references

Saito M.Forecasting time of slope failure by tertiarycreep[C]∥Proceeding of 7th Int.Conf.on Soil Mechan?ics and Foundation Engineering.Mexico City:[s.n.],1969:677?683.

王延平,许强,郑光,等.速度倒数法滑坡预警模型流变试验研究[J].岩土力学,2015,36(6):1606-1614.Wang Y P,Xu Q,Zhang G,et al.A rheology experi?mental investigation on early warning model for land?slide based on inverse-velocity method[J].Rock andSoil Mechanics,2015,36(6):1606-1614(.in Chinese)

安北,蒋亚楠,曾启菲.基于灰色关联分析联合 VMDSES-BP 模型的滑坡位移预测[J].人民珠江,2021,42(1):34-40.An B,Jiang Y N,Zeng Q F.Prediction of landslide dis?placement based on grey relational analysis and VMDSES-BP model[J].Pearl River,2021,42(1):34-40.(in Chinese)

邓洪高,姚鹏远,孙希延,等.灰色马尔科夫Verhulst动态模型在滑坡形变预测中的应用[J].科学技术与工程,2019,19(13):50-55.Deng H G,Yao P Y,Sun X Y,et al.Application ofgrey Markov Verhulst dynamic model in prediction oflandslide deformation[J].Science Technology and En?gineering,2019,19(13):50-55(.in Chinese)

周美玲,高春艳.山区灾害滑坡风险非线性预测研究[J].灾害学,2018,33(4):23-27.Zhou M L,Gao C Y.Study on the nonlinear predictionof landslide risk in mountainous area[J].Journal ofCatastrophology,2018,33(4):23-27(.in Chinese)

王智伟,王利,黄观文,等.基于BP神经网络的滑坡监测多源异构数据融合算法研究[J].地质力学学报,2020,26(4):575-582.Wang Z W,Wang L,Huang G W,et al.Research onmulti-source heterogeneous data fusion algorithm of land?slide monitoring based on BP neural network[J].Jounalof Geomechanics,2020,26(4):575-582(.in Chinese)

何健保.堆积层滑坡临界位移预警判据研究[D].成都:成都理工大学,2016.He J B.Warning on critical displacement of accumula?tion landslide[D].Chengdu:Chengdu University ofTechnology,2016(.in Chinese)

解明礼,赵建军,巨能攀,等.多源数据滑坡时空演化规律研究——以黄泥坝子滑坡为例[J].武汉大学学报(信息科学版),2020,45(6):923-932.Xie M L,Zhao J J,Ju N P,et al.Research on tempo?ral and spatial evolution of landslide based on multi?source data:a case study of Huangnibazi Landslide[J].Geomatics and Information Science of Wuhan Universi?ty,2020,45(6):923-932.(in Chinese)

董秀军,许强,唐川,等.滑坡位移-时间曲线特征的物理模拟试验研究[J].工程地质学报,2015,23(3):401-407.Dong X J,Xu Q,Tang C,et al.Characteristics of land?slide displacement-time curve by physical simulation ex?periment[J].Journal of Engineering Geology,2015,23(3):401-407(.in Chinese)

王珊珊.滑坡位移预测中的时序数据挖掘研究[D].宜昌:三峡大学,2015.Wang S S.The Research of time series data mining forlandslide prediction[D].Yichang:China Three GorgesUniversity,2015(.in Chinese)

王卫东,瞿霞,刘攀,等.基于最优权重联合模型的滑坡位移预测研究[J].灾害学,2018,33(1):59-64.Wang W D,Qu X,Liu P,et al.Prediction on land?slide displacement using a combination model with opti?mal weight[J].Journal of Catastrophology,2018,33(1):59-64.(in Chinese)

蔡泽宏,简文彬,李宏达,等.基于滑坡监测数据的时间序列位移预测[J].水利与建筑工程学报,2016,14(1):236-242.Cai Z H,Jian W B,L H D,et al.Displacement predic?tion by using time series analysis method based on themonitoring data[J].Journal of Water Resources and Ar?chitectural Engineeringal 2016,14(1):236-242.(inChinese)

Zhu X,Xu Q,Tang M,et al.A hybrid machine learn?ing and computing model for forecasting displacement ofmultifactor-induced landslides[J].Neural Computing &Applications,2018,30(12):3825-3835.

Zhu X,Xu Q,Tang M,et al.Comparison of two opti?mized machine learning models for redicting displace?ment of rainfall-induced landslide:a case study in Sich?uan province,China[J].Engineering Geology,2017,218:213-222.

李丽敏.统计聚类和粒子滤波在故障诊断中的应用研究[D].西安:西北工业大学,2014.Li L M.Application research for fault diagnosis based onstatistical clustering and particle filter [D].Xi'an:North?we-stern Polytechnical University,2014.(in Chinese)

Baruah P,Chinnam R B.HMMs for diagnostics andprognostics in machining processes[J].International Jour?nal of Production Research,2005,43(6):1275?1293.

Tobon-Mejia D A,Medjaher K,Zerhouni N,et al.Adata-driven failure prognostics method based on mixtureof gaussias hidden markov models[J].IEEE Transac?tions on Reliability,2012,61(2):491?503.

Dijkstra E W.A note on two problems in connexionwith graphs[J].Mumerische Mathematik,1959,1(1):269?271.

周亚同,赵翔宇,何峰,等.基于高斯过程混合模型的大气温湿度预测[J].农业工程学报,2018,34(5):219-226.Zhou Y T,Zhao X Y,He F,et al.Atmospheric tem?perature and humidity prediction of Gaussian processmixed model[J].Transactions of the Chinese Society ofAgricultural Engineering,2018,34(5):219-226.(inChinese)

刘畅,魏忠诚,张春华,等.基于隐马尔可夫模型的步态识别算法[J].计算机工程与设计,2019,40(12):3487-3493.Liu C,Wei Z C,Zhang C H,et al.Gait recognition al?gorithm based on hidden markov model[J].ComputerEngineering and Design,2019,40(12):3487-3493(.inChinese)

Baum L E,Petrie T,Soules G,et al,A maximizationtechnique occurring in the statistical analysis of probabillistic functions pf Markov chains[J].Ann Math Statist,1970,41(1):164?171.

蔡嘉伦.基于表面位移的滑坡稳定性评价及预警阈值探讨[D].绵阳:西南科技大学,2016.Cai J L.Based on the surface displacement of landslidestability evaluation and early warning[D].Mianyang:Southwest University of Science and Technology,2016(.in Chinese)

李德营.三峡库区具台阶状位移特征的滑坡预测预报研究[D].武汉:中国地质大学,2010.Li D Y.Predietion study of landslides with step-like de?for-mation in the Three Gorges Reservior[D].Wuhan:China University of Geosciences,2010(.in Chinese)

Saxena A,Celaya J,Balaban E,et al.Metrics for eval?uating performance of prognostic techniques[C]∥Inter?national Conference on Prognostics & Health Manage?ment.[S.l.]:IEEE,2008:1-18.

浏览量

450

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

山地城镇洪涝滑坡灾害韧性评估研究