基于BP神经网络的仓内稻谷温度预测模型  

Granary rice temperature prediction model based on BP neural network

作　　者：程嘉蔚 徐佳[1] 王艺玲 张红伟[1] 李晓辉[1] CHENG Jiawei;XU Jia;WANG Yiling;ZHANG Hongwei;LI Xiaohui(School of Electronics and Information Engineering,Anhui University,Hefei 230601,China)

机构地区：[1]安徽大学电子信息工程学院,安徽合肥230601

出　　处：《现代电子技术》2021年第19期178-182,共5页Modern Electronics Technique

基　　金：教育部高等学校博士点专项基金(20133401110003);安徽省高校省级优秀青年人才基金重点项目(2013SQRL008ZD)。

摘　　要：传统的BP神经网络模型在预测仓内稻谷温度的过程中存在易陷入局部最优值及收敛速度慢的问题,为了提高预测准确性,文中采用自适应变异的粒子群算法优化BP神经网络模型对温度进行预测。在标准粒子群算法优化BP神经网络的基础上,引入一种自适应变异的粒子群算法对BP神经网络进行优化,加强算法跳出局部最优的能力。对温度数据进行归一化处理后,建立自适应变异的粒子群算法优化BP神经网络预测模型,对仓内稻谷的最高温度进行预测,将预测结果与BP神经网络模型和粒子群优化的BP神经网络模型进行对比分析。仿真结果表明,与传统的BP神经网络模型和粒子群优化的BP神经网络模型相比,采用自适应变异的粒子群算法的BP神经网络优化模型对稻谷最高温度的预测具有更高的准确性。The traditional BP neural network model is easy to fall into the local optimal value and its convergence speed is slow in the process of predicting the temperature of the rice in the granary.In order to improve the prediction accuracy,an adaptive mutation particle swarm optimization(AMPSO)algorithm is adopted to optimize the BP neural network model to predict the temperature.The BP neural network is optimized by the standard PSO algorithm.On the basis of this,the AMPSO algorithm is introduced to optimize the BP neural network for fear of the local optimum.After normalizing the temperature data,a BP neural network prediction model optimized by the AMPSO algorithm is established to predict the maximum temperature of the rice in the granary.The prediction results are compared with the results of the traditional BP neural network model and the BP neural network model optimized by PSO algorithm respectively.The simulation results show that the BP neural network model optimized by AMPSO algorithm has higher accuracy in predicting the maximum temperature of rice.

关 键 词：稻谷温度 粮食储藏 自适应变异 粒子群算法 BP神经网络 预测模型 预测准确性 

分 类 号：TN711-34[电子电信—电路与系统] TP301[自动化与计算机技术—计算机系统结构]