QPSO优化BP网络预测烟蚜发生量

QPSO Optimization BPNN to Predict the Occurrence Quantity of Myzus persicae

为有效地预测烟蚜发生量,利用BP神经网络理论和方法建立了烟蚜发生量预测模型,并运用QPSO算法优化BP神经网络的连接权值和阈值,以此确定最优连接权值和阈值。应用该模型以云南省玉溪市红塔区2003—2006年的烟蚜发生量历史数据为训练样本,对2007—2009年烟蚜发生量进行预测,其预测精度为99.35%,最小完成时间30 s,平均完成时间34.5 s,运行次数19次,预测效果明显优于其他预测模型。实验表明:该模型比其他预测模型预测结果更有效可行,收敛速度更快,稳定性更强,能解决预测、聚类方面的类似问题,为烟蚜的综合防治提供了理论依据。

In order to foresee the occurrence quantity of M.persicae efficiently,BP neural network theory and method were used to establish model of the occurrence quantity of Myzus persicae,and at the same time,QPSO algorithm was used to optimize the BP neural network connection weights and threshold value,so as to determine the optimal connection weights and threshold value.The 2003—2006 historical data of M.persica quantity in Hongta County,Yuxi City of Yunnan Province was applied as samples.The 2007—2009 data of M.persica quantity was used to forecast for the sample.The model prediction accuracy rate was 99.35%,the minimum completion time was 30 s,average completion time was 34.5 s,and the number of runs was 19 times.The prediction effect were obviously superior to the other prediction models.The experiment showed that this model was better than other prediction.The prediction results were more effective,feasible,and faster convergence speed,and stronger stability,and could solve the similar problems forecast and clustering to provide a theoretical basis for M.persicae comprehensive prevention and control.