基于改进粒子群算法的平房仓粮温BP神经网络预测模型建立

Prediction Model of Grain Temperature in Warehouse Based on Improved Particle Swarm Optimization BP Neural Network

在传统的BP神经网络预测模型的基础上引入改进的粒子群算法对神经网络中的权值和阈值进行不断优化,针对平房仓内部不同温度监测点处的粮食温度建立预测模型,改进后的粒子群算法拥有更好的局部寻优能力和全局寻优能力,较传统的BP神经网络预测拥有更精确的预测精度,更小的预测误差,使优化后的BP神经网络能快速的从历史粮温中总结平方仓粮温变化规律,实现平房仓粮温的预测。

In this study,on the basis of the traditional BP neural network prediction model,the improved particle swarm algorithm was introduced to optimize the weights and thresholds of the neural network.The prediction model was established for the grain temperature at different temperature monitoring points in the warehouse.The improved particle swarm algorithm had better local optimization ability and global optimization ability.Compared with the traditional BP neural network prediction,the improved particle swarm algorithm had more accurate prediction accuracy and smaller prediction error.The optimized BP neural network could quickly summarize the grain temperature variation of the square warehouse from the historical grain temperature,and realize the prediction of the grain temperature of the warehouse.