基于支持向量机-小波神经网络的边坡位移时序预测模型

发布时间：2018-06-04 05:17

本文选题：支持向量机 + 遗传算法参数寻优　；参考：《武汉大学学报(工学版)》2017年02期

【摘要】：针对岩体边坡位移预测难度大的问题,结合支持向量机-小波神经网络,提出了一种新的岩体边坡位移时序预测模型——支持向量机-小波神经网络预测模型.通过对实测位移值的学习,并借助遗传算法参数寻优的支持向量机对位移时间序列的宏观发展趋势进行滚动预测;在此基础上利用小波基函数变换分析序列的局部特征,通过2维情况下的序列局部走势方向的选择、实测值与支持向量机拟合值的相对误差与绝对误差等指标的分析,达到对预测值优化改进的目的.将该模型应用到某工程面板堆石坝坝肩强卸荷岩体边坡位移的时序预测中,结果表明,该模型具有可靠度和精度高的优点,可应用于岩体边坡位移预测分析.
[Abstract]:Aiming at the difficult problem of rock slope displacement prediction, a new prediction model of rock slope displacement time series-support vector machine-wavelet neural network is proposed. The model is based on support vector machine (SVM) and wavelet neural network (WNN). Based on the study of the measured displacement value and the support vector machine (SVM), which is optimized by genetic algorithm parameters, the macroscopic development trend of displacement time series is predicted by rolling, and the local characteristics of the sequence are analyzed by wavelet basis function transformation. Through the analysis of the local direction of the sequence, the relative error and the absolute error between the measured value and the fitting value of support vector machine, the purpose of optimizing and improving the prediction value is achieved. The model is applied to the time series prediction of the displacement of the strong unloading rock slope at the abutment of a face rockfill dam. The results show that the model has the advantages of high reliability and precision, and can be applied to the prediction and analysis of the displacement of the rock slope.
【作者单位】：河海大学水文水资源与水利工程科学国家重点实验室;河海大学水利水电学院;
【基金】：2016年度江苏省普通高校学术学位研究生科研创新计划项目(编号:KYZZ16_0284) 江苏省自然科学基金青年基金(编号:BK2012410) 国家自然科学基金项目(编号:51179062) 江苏高校优势学科建设工程资助项目中央高校基本业务费项目(编号:2014B11914)
【分类号】：TU433;TP18

【相似文献】