Abstract: Train samples usually have inherent characteristic and regularity according to the neural network in practical application.This paper presents a BP neural network predicting model based on samples self-organizing clustering.The effect of samples training on BP neural network performance with the clustering characteristic of self-organizing competitive network is improved.BP neural network using adaptive learning rate momentum algorithm has fast convergence rate and high error precision.And according to the air quality forecast experiment based on this kind of model，the BP neural network predicting model based on samples self-organizing clustering improves convergence rate at first，secondly reduces the possibility of getting into local minimum，and improves the prediction accuracy.

Key words: samples, self-organizing competitive network, BP neural network, air quality

摘要： 根据实际应用中神经网络训练样本通常具有内在特征和规律性，提出一种基于样本自组织聚类的BP神经网络预测模型。通过自组织竞争网络的聚类特征，改善样本训练对BP网络性能的影响。BP神经网络采用收敛速度较快和误差精度较高的动量—自适应学习速率调整算法。并通过基于这种模型的空气质量预测实验，表明基于样本自组织聚类的BP神经网络预测模型首先会提高收敛速度，其次会减少陷入局部最小的可能，提高预测精度。

关键词: 样本, 自组织竞争网络, BP神经网络, 空气质量