中文摘要：

人工神经网络具有自组织、自学习、非线性逼近能力，其中的径向基函数（RBF）网络是以函数逼近理论为基础而构造的一类前向网络，这类网络的学习等价于在高维空间中寻找训练数据的最佳拟合平面。对攀枝花已知地质样品的X射线荧光计数数据进行归一化，并用自组织神经网络进行分类后，采用RBF网络的OLS算法预测攀枝花未知地质样品的Ti元素含量，预测数据与化学分析数据的相对误差均小于0．5％，结果比较理想。

英文摘要：

Artificial neural network has self-organization, self-study and non-linear approaching ability, of which RBF （Radial Basis Function） network is a kind of forward network constructed on the basis of function approximation theory. The study of this kind of network equals searching for the optimal fit plane for the training data in high dimensional space. The X ray florescent counting data of Panzhihua certified geological samples are normalized and classified by suing self-organization neural network. OLS algorithm of RBF network is adopted to forecast the Ti element content in the Panzhihua uncertified geological samples and the relative error between the forecast data and those of the chemical analysis is all smaller than 0.5% , an ideal result.