【摘要】 准确的铁路货运量预测关系到铁路运输的发展,为此提出模糊神经网络非线性组合预测模型,应用三次指数预测模型、灰色理论预测模型、多元回归预测模型的预测值作为模糊神经网络的测试样本数据库,输出样本为铁路货运量,并采用全局优化的粒子群算法优化模糊神经网络的参数。仿真结果表明该模型能够取得比单项预测模型更高的精度。更多还原

【Abstract】 Accurate forecasting for railway freight volumeis important to the development of railway transportation.This paper presents nonlinear combination forecast modelof fuzzy neural network,uses the results of three-timeexponential forecast model,grey theory forecast modeland multiple regression forecast model as the test sampledatabase of fuzzy neural network,thereinto the outputsample is the railway freight volume,and also uses thewhole optimized particle swarm algorithm to optimize theparameters of fuzzy neural network.The simulation resultsdemonstrate the proposed model can improve theaccuracy compared with individual forecasting model.更多还原