基于灰色关联和相关向量机的隧道地表沉降预测  

Prediction of Tunnel Surface Subsidence:Based on Gray Relational-Relevance Vector Machine

作　　者：张立亭[1] 徐志宽[1] 罗亦泳[2] ZHANG Liting XU Zhikuan LUO Yiyong(Faculty of Geomatics, East China University of Technology, 418 Guanglan Road, Nanchang 330013, China School of Geodesy and Geomatics, Wuhan University, 129 Luoyu Road, Wuhan 430079, China)

机构地区：[1]东华理工大学测绘工程学院,南昌市广兰大道418号330013 [2]武汉大学测绘学院,武汉市珞喻路129号430079

出　　处：《大地测量与地球动力学》2017年第10期1033-1037,共5页Journal of Geodesy and Geodynamics

基　　金：国家自然科学基金(41374007);江西省自然科学基金(20132BAB201049;20161BAB203102);江西省教育厅科学技术研究项目(GJJ150555)~~

摘　　要：基于灰色关联算法确定与地表沉降有直接重要关联的主要影响因子,构建高斯核函数和多项式核函数的加权核函数,利用遗传算法优化模型参数,建立相关向量机地表沉降预测模型。实验结果表明,灰色关联算法能定量地反映系统影响因子与地表沉降变化的关联程度,有效处理不是完全明确的灰色系统信息;加权核函数的合理组合可较好地通过低维空间线性不可分映射变换到高维特征空间线性可分;遗传算法具有计算过程简单和自适应迭代寻优特点;相关向量机模型可极大地减少核函数的计算量,计算过程和结果均具有概率解释。该模型预测结果的多项精度指标值均优于BP神经网络和GR-SVM方法。We apply the gray relational algorithm to determine the major factors directly influencing surface subsidence. The Gaussian kernel function and the polynomial kernel function are constructed, we determine an optimization of model parameters by genetic algorithm, and a prediction model of ground surface subsidence is established. The experimental data shows that. the gray relational algorithm can quantitatively reflect the degree of correlation between many factors of the system and the change of surface subsidence predictiom fur- thermore, the information of the gray system can be processed effectively. The reasonable combination of the weighted kernel functions can be transformed into a linearly separable map of the high-dimensional feature space by the low-dimensional linearly separable map; the genetic algorithm is simple to calculate and shows a- daptive iterative optimization; the relevance vector machine model can greatly reduce the computational burden of the kernel function and the probabilistic interpretation of the process and results. The model based on rele- vance vector machine has good predictive effects. In addition, the accuracy of this method is better than that the precision of BP neural network, GR-SVM method.

关 键 词：灰色关联 相关向量机 地表沉降 

分 类 号：P258[天文地球—测绘科学与技术]