摘要
研究冰箱订单需求准确预测问题,由于冰箱需求具有季节性和随机性,传统的数据模型无法准确描述订单变化规律,预测精度较低。为了提高冰箱订单需求预测精度,将神经网络和灰色理论相结合,构建一种改进灰色神经网络的冰箱订单预测方法。利用灰色系统理论处理订单产生中的随机性,BP神经网络预测其非线性变化规律,并利用遗传算法对神经网络参数进行优化,实现对冰箱订单的准确预测。仿真试验表明,相对于传统预测方法,改进灰色神经网络提高了订单需求的预测精度,可为冰箱需求的预测提供依据。
Refrigerator orders are of the characteristics of random, discrete and nonlinear, the traditional model cannot accurately describe the regularity, and the forecasting precision is quite low. In order to improve the forecast accuracy of refrigerators orders demand, neural network and the grey theory was combined to construct a kind of improved grey neural network forecasting method of refrigerator orders. By using the theory of gray system, the random- ness of refrigerator orders was processed, BP neural network was used to predict the nonlinear variation, and the genetic algorithm was used to optimize the neural network＇ s parameters. Simulation results show that, compared with the traditional forecasting methods, the proposed method improves the forecasting accuracy of order demand and is efficient in refrigerators orders forecasting.
出处
《计算机仿真》
CSCD
北大核心
2012年第5期219-222,共4页
Computer Simulation
基金
国家自然基金"甲骨文编辑与编码技术研究"(60973051)
河南省科技厅科技计划项目"面向旅游资源管理的数字化与可视化技术研究"(112400450215)
关键词
冰箱订单
需求预测
灰色神经网络
遗传算法
Refrigerator orders
Demand forecasting
Grey neural network
Genetic algorithm
