研究并应用径向基函数神经网络(RBF-network)对稀土卤化物标准生成焓进行定量建模,相关系数r达到0.9985,样本误差较小,显现了神经网络方法在该领域的优势.交互预测结果证明模型具有好的稳定性和泛化性能,对7个未知样本所作的预测有一定参考价值. The standard enthalpies of formation of rare earth halides were quantitatively modeled using radial basis function neural network (RBF-network), the correlation coefficient r was 0.9985, the sample error was small, which showed the advantages of neural network method in this field. The results show that the model has good stability and generalization performance, and has certain reference value for the prediction of seven unknown samples.