多元地学信息挖掘中分层动量增项自适应BP算法应用研究  

Study and Application on Stratified Momentum Term Adaptive BP Algorithm in Multi-geoobject Information Mining

作　　者：刘伟[1] 

机构地区：[1]吉林建筑工程学院基础科学部,吉林长春130021

出　　处：《数学的实践与认识》2011年第2期85-89,共5页Mathematics in Practice and Theory

基　　金：国家高技术研究发展计划(863计划)(2006AA06Z114)

摘　　要：地球化学元素分布规律的研究是揭示元素矿化富集及空间变化规律的重要途径之一,采用人工神经网络方法对东天山地区地球化学信息进行了研究,为矿区靶区预测提供支持.对传统BP算法进行了改进,采用分层动量增项自适应BP算法设计,并完成了样本区数据的预测分析,效果较好.The investigation on the geochemical elements＇ distributions can serve as an important way to diclose the mineralized enrichment and spatial distributions of geochemical elements.The artificial neural network method was used to investigate on the geochemical information and the study can serve as the support of the target forecast of the mining areas. Based on a layered design of adaptive algorithm,a platform was developed by improving the algorithm to achieve the sample area forecast data analysis with excellent effiency.

关 键 词：分层增量自适应 地学信息挖掘 BP算法 预测分析 

分 类 号：P595[天文地球—地球化学] TP183[天文地球—地质学]