一种基于GA-BP-MC神经网络的高铁桥墩沉降预测模型  

A settlement prediction model of high-speed railway pier based on GA-BP-MC neural network

作　　者：冯绍权 花向红[1,2] 陶武勇 宣伟 吴伟 续东[1,2] FENG Shaoquan;HUA Xianghong;TAO Wuyong;XUAN Wei;WU Wei;XU Dong(School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, China;Hazard monitoring & prevention Research Center, Wuhan University, Wuhan 430079, China;School of Civil Engineering and Architecture, Wuhan University of Technology, Wuhan 430070, China)

机构地区：[1]武汉大学测绘学院,湖北武汉430079 [2]武汉大学灾害监测和防治研究中心,湖北武汉430079 [3]武汉理工大学土木工程与建筑学院,湖北武汉430070

出　　处：《测绘通报》2019年第7期50-53,82,共5页Bulletin of Surveying and Mapping

基　　金：国家自然科学基金(41674005;41374011);东华理工大学江西省数字国土重点实验室开放研究基金资助项目(DLLJ201801)

摘　　要：提出一种基于马尔科夫链修正的遗传BP神经网络预测模型(GA-BP-MC),利用遗传算法的全局寻优能力初始化BP神经网络权值和阈值,初步建立GA-BP神经网络预测模型,结合马尔科夫链的无后效性修正模型预测值,形成高精度GA-BP-MC神经网络变形预测模型。结合高铁桥墩沉降数据,分别与BP神经网络、GA-BP神经网络预测模型进行对比,结果表明,该预测模型精度最高。A genetic BP neural network prediction model (GA-BP-MC) based on Markov chain modification is proposed. The weights and thresholds of BP neural network are initialized by the global optimization ability of genetic algorithm, and the prediction model of GA-BP neural network is established preliminarily. The predictive value of model is modified by the invalidity of Markov chain to form a high precision deformation prediction model of GA-BP-MC neural network. Combined with the settlement data of high-speed railway piers, and compared with the BP neural network and GA-BP neural network prediction models respectively, the results show that the accuracy of the prediction model is highest.

关 键 词：马尔科夫链 遗传算法 BP神经网络 高铁桥墩 沉降预测 

分 类 号：P258[天文地球—测绘科学与技术]