基于BP神经网络的地裂缝活动强度预测——以西安地裂缝为例  

Prediction of Activity Intensity of Ground Fissures Based on BP Neural Network——A Case Study of Xi'an Ground Fissures

作　　者：贺炳彦[1,2] 崔建军[2] 

机构地区：[1]长安大学信息工程学院,陕西西安710064 [2]长安大学地质工程与测绘学院,陕西西安710054

出　　处：《灾害学》2010年第4期38-42,共5页Journal of Catastrophology

基　　金：国家自然科学基金资助项目(40972181)

摘　　要：地裂缝灾害是一个典型灾种,地裂缝给城市建设及地表地下建筑物造成巨大危害。依据西安地裂缝多年监测资料和研究成果,分析西安地裂缝的活动特征和主要影响因素,采用了BP神经网络结合地理信息系统的方法对西安地裂缝活动强度进行预测,在学习过程中结合了聚类,引入了惯性因子,加快了学习时的收敛速度,结果在地理信息系统中以可视化的方式进行显示。经过实际数据验证,取得了良好的效果。Ground fissure is one of the typical disasters. It can do great harm to urban construction, including surface and underground constructions. According to the monitoring data of Xi＇an ground fissures and research results in recent years, features and main influence factors of activity of Xi＇an ground fissures and prediction of activity intensity of ground fissures are analyzed by combining BP neural network with Geographic Information Systems. Cluster analysis is introduced to the BP neural network learning process, and at the same time, inertia factor is used to speed up the convergence rate of learning. The resulting can be shown in geographic information system in a visualized manner. After the actual data validation, it is proved to be an effective method.

关 键 词：地裂缝 神经网络 BP算法 地理信息系统 活动强度 西安 

分 类 号：P642.22[天文地球—工程地质学] TP183[天文地球—地质矿产勘探]