禽蛋孵化过程组合预测研究

Combination Prediction of Incubator for Eggs

针对孵化过程是一个具有高度非线性、大滞后、时变特性且强耦合性的农业生产过程,提出了一种基于灰色预测和联想记忆神经网络的组合预测方法。该模型首先利用灰色预测模型和联想记忆神经网络分别对焦炉禽蛋孵化过程温、湿度进行预测,然后采用方差-协方差优选组合预测法对2种单一模型的预测结果进行加权集成,以获得较为准确的预测精度,实现孵化过程温度和湿度的有效预测。运行结果表明,组合预测模型均方根相对偏差为0.9%。

In view of the incubation process which is highly nonlinear, large delay and time-varying and strong coupling, a combination forecasting method based on gray prediction and associative memory neural networks was proposed. Firstly, the gray prediction model and associative memory neural networks were respectively used on prediction for incubator. Then the two sub-models with weighted integration by using the variance-covariance combination forecasting method was combined. The value of the temperature and humidity of incubator could be more accurate and effective. Finally, the results showed the mean square deviation of combination forecasting model was 0.9%.