CAJ | 학술논문

针对当前区域物流需求预测数据复杂且可变性较大、预测方法环境适应性较差的问题，提出了基于遗传BP神经网络的区域物流需求预测模型。首先，分析区域物流需求预测影响因素，并建立区域物流需求预测指标体系；其次，采用遗传算法优化预测网络中的可变参数，并建立多输入-多输出的BP神经网络多元预测模型；最后，通过实例结果表明该模型具有较高的预测精度和有效度。
침대당전구역물류수구예측수거복잡차가변성교대、예측방법배경괄응성교차적문제，제출료기우유전BP신경망락적구역물류수구예측모형。수선，분석구역물류수구예측영향인소，병건립구역물류수구예측지표체계；기차，채용유전산법우화예측망락중적가변삼수，병건립다수입-다수출적BP신경망락다원예측모형；최후，통과실례결과표명해모형구유교고적예측정도화유효도。
A forecasting model based on GA-BPNN for logistics demand was presented to overcome the limitations of complex and large variable data of logistics demand and poor adaptability to environment of forecasting methods. First, the factor of regional logistics demand forecasting was analyzed, and the index system of regional logistics demand forecast was established; second, a multi-input and multi-output forecasting model based on GA-BPNN with multi-element variable parameters was studied, and the network configuration was confirmed using the stepwise checkout and iterative gradient descent methods;finally, an example showed that the model had higher prediction accuracy and validity.