CAJ | 학술논문

文章以全国统计局货运量的历史数据为基本数据，考虑影响货运量的8个因素，采用GRNN模型对货运量（货运总量、铁路货运量和公路货运量）进行预测，并将结果与真实值拟合比较。结果表明：该方法在预测货运量方面能够达到较好的效果，尤其在径向基函数的扩展速度为0.4时，预测结果最好。
문장이전국통계국화운량적역사수거위기본수거，고필영향화운량적8개인소，채용GRNN모형대화운량（화운총량、철로화운량화공로화운량）진행예측，병장결과여진실치의합비교。결과표명：해방법재예측화운량방면능구체도교호적효과，우기재경향기함수적확전속도위0.4시，예측결과최호。
According to the historical data of freight volume as the basic data, considering the eight factors of freight volume, this paper established the general regression neural network (GRNN) model for freight volume forecast, including volume of the total freight, the railway freight and the highway freight. Compared the result of the forecast with real value by curve-fitting. The re-sults show that the method can achieve good results in the prediction of freight volume, especially when the expansion velocity of radial basis function is 0.4, the prediction results is the best.