基于深度学习的农业装备库存预测研究

Research on Agricultural Equipment Inventory Prediction Based on Deep Learning

为解决农业装备制造企业供应链峰谷生产下因库存需求预测不准造成的“断供”或库存冗余问题,且传统的预测模型不能够考虑影响库存的多重因素,预测结果往往不够准确,因此决定建立一个可以精准预测的模型。提出一种基于LSTM算法的农业装备库存预测模型,可根据影响库存的主要影响因素等数据实现精准预测,能够最大程度地节约成本,提高效率。实验结果表明:LSTM模型的预测数据集和真实数据集的拟合度较高,这说明LSTM模型预测结果具有更高的预测精度,有很强的泛化能力。

In order to solve the problem of"supply cut"or inventory redundancy caused by inaccurate inventory demand prediction in the peak and valley production of supply chain of agricultural equipment manufacturing enterprises,and the traditional forecasting model can not take into account the multiple factors affecting inventory,so the prediction results are often not accurate,so it is decided to establish a model that can accurately predict.A prediction model of agricultural equipment inventory based on LSTM algorithm is proposed,which can realize accurate prediction according to the main influencing factors of inventory and other data,and can save cost and improve efficiency to the greatest extent.The experimental results show that the prediction data set of LSTM model has a high degree of fitting with the real data set,which indicates that the prediction results of LSTM model have higher prediction accuracy and strong generalization ability.