1. 上海交通大学 电子信息与电气工程学院， 上海 200240；2. 国网湖南省电力公司 防灾减灾中心， 长沙 410007；3. 华东师范大学 统计学院， 上海 200241
通讯作者:范春菊，女，副教授，电话(Tel.): 021-34204290；E-mail：fanchunju@sjtu.edu.cn.作者简介:徐峰(1992-)，男，安徽省六安市人，硕士生，主要从事电力系统保护与控制研究. E-MAIL: fengxu0520@163.com基金资助:国家电网公司科技项目(5216A01600VX)Displacement Prediction of Landslide Based on Variational Mode Decomposition and AMPSO-SVM Coupling Model
U Feng,FAN Chunju,XU Xunjian,LI Li,NI Jiayun1. School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China; 2. Disaster Prevention and Reduction Center, State Grid Hunan Electric Company, Changsha 410007, China; 3. School of Statistics, East China Normal University, Shanghai 200241, China
摘要/Abstract
摘要： 滑坡是一种严重威胁危害居民生命财产安全的自然灾害，滑坡位移预测有助于预测滑坡等自然灾害.滑坡体监测数据的处理和预测模型的建立是滑坡位移预测的基础.针对当前时间序列分析中应用广泛的EMD、EEMD分解算法的缺陷，将具有严格数学理论支撑且分解个数可控的变分模态分解算法应用于位移时间序列分解，以获得滑坡位移子序列.将自适应变异粒子群优化算法(AMPSO)和支持向量机(SVM)相结合，构建AMPSO-SVM位移预测耦合模型.运用耦合模型对分解所得位移子序列分别进行预测，然后重构子序列预测结果得到总位移预测值.以三峡库区白水河滑坡XD1监测点为例，针对2007～2012年监测数据，设置不同情景以验证所提出预测模型的有效性及稳定性.实例分析表明，基于变分模态分解和AMPSO-SVM耦合模型对于滑坡位移的预测性能优于BP神经网络预测模型和网格搜索优化的SVM模型，在滑坡位移预测中有良好的理论基础及工程应用价值.
关键词: 变分模态分解, 滑坡, 位移预测, 自适应变异粒子群算法(AMPSO), 支持向量机(SVM)
Abstract: Landslide is a natural disaster that seriously threatens and endangers the safety of life and property of residents. Landslide displacement prediction is helpful to predict natural disasters such as landslide. Monitoring data processing and the establishment of prediction model are the basis of landslide displacement prediction. According to the shortcomings of the EMD and EEMD decomposition algorithms which are applied widely in present analysis of time series，the variational mode decomposition algorithm is applied in signal processing to the landslide displacement sequences decomposition to obtain the subsequences. The AMPSO-SVM displacement prediction coupling model is constructed by combining adaptive mutation particle swarm optimization (AMPSO) and support vector machine (SVM). Apply the coupling model to predict displacement subsequences separately， then reconstruct all the sub-sequences prediction results and the total displacement prediction value is acquired. Taking the monitoring point XD1 in the Baishuihe landslide in the Three Gorges Reservoir area as an example, different scenarios are set to clarify the validity and stability of the proposed model. The case studies show that the prediction performance of landslide displacement based on variational mode decomposition and AMPSO-SVM coupling model is superior to BP neural network prediction model and SVM model optimized by the grid search algorithm, and it has a good theoretical basis and engineering application value.
Key words: varitional mode decomposition, landslide, displacement prediction, auto mutation particle swarm algorithm (AMPSO), support vector machine (SVM)
PDF全文下载地址:
点我下载PDF
