目的　探讨人工神经网络在时间序列资料分析中的应用。方法　利用动态学习比率BP算法以双曲正切函数为功能函数的非线性时间序列预测方法。结果　建立HFRS发病率的两种ANN预测模型 ,其预测精度远远高于传统方法。结论　BP人工神经网络可以用于疾病发病率或死亡率的预测。 Objective To investigate the application of artificial neural network in time series analysis. Methods The nonlinear time series prediction method based on hyperbolic tangent function was studied by dynamic learning ratio BP algorithm. Results Two ANN prediction models for the incidence of HFRS were established, and the prediction accuracy was much higher than the traditional method. Conclusion BP artificial neural network can be used to predict disease morbidity or mortality.