论文部分内容阅读
应用灰色系统中的GM(1,1)模型预测蚕茧价格趋势,应用BP人工神经网络模型基于蚕茧产量波动预测蚕茧价格波动,建立组合2种模型预测蚕茧价格的方法,为蚕桑生产计划及蚕茧收售提供参考。应用该方法分别对2011—2014年各年度的蚕茧价格进行预测与检验,预测价格与实际价格的相对误差分别为4.17%、5.01%、2.84%和1.25%;应用该方法预测2015年的全国家蚕鲜茧销售均价为38.21元/kg,比上年度小幅增长。预测及检验结果表明,组合2种模型的蚕茧价格预测方法具有较高的准确度,适用于市场经济规律调控下的蚕茧价格预测。
The GM (1,1) model in gray system was used to predict the price trend of silkworm cocoon. BP artificial neural network model was used to predict the price fluctuation of silkworm cocoon based on the fluctuation of cocoon production. The method of combining two models to predict the price of silkworm cocoon was established. For sale reference. The method was used to predict and test the cocoon price in each year from 2011 to 2014. The relative error between forecast price and actual price were 4.17%, 5.01%, 2.84% and 1.25% respectively. Using this method to predict the 2015 domestic silkworm cocoon, Fresh cocoon sales price was 38.21 yuan / kg, a slight increase over the previous year. Prediction and test results show that the method of combining two models of cocoon price forecasting has high accuracy and is suitable for forecasting cocoon price under the regulation of market economy.