基于粒子群的神经网络改进算法在粮情测控中的研究  

APPLICATION OF IMPROVED NEURAL NETWORK ALGORITHM BASED ON PARTICLE SWARM IN GRAIN MONITORING

作　　者：吴建军[1,2] 张强[1,2] 邹东尧[3] 

机构地区：[1]武汉理工大学计算机学院,湖北武汉430070 [2]河南工业大学信息科学与工程学院,河南郑州450052 [3]郑州轻工业学院计算机与通信工程学院,河南郑州450002

出　　处：《河南工业大学学报（自然科学版）》2009年第4期68-71,共4页Journal of Henan University of Technology：Natural Science Edition

基　　金："十一五"国家科技支撑计划项目(2006BAD08B01);郑州市科技攻关项目(083SGXG25121-19)

摘　　要：结合粮情测控中粮情数据分析的特点,利用粒子群算法对基于BP神经网络的模糊控制算法进行了改进,将该算法引入到粮情测控系统的数据分析中,对温度、湿度数据进行信息融合,判断粮堆内部是否处于安全状况.该系统在中央储备粮库中的应用表明,改进的算法能够正确实现粮情安全等级智能分析.In combination with the characteristics of grain data analysis for grain monitoring, the particle swarm algorithm was used to improve the fuzzy control algorithm based on BP neural network, and the algorithm was introduced to data analysis of the grain monitoring system to carry out information fusion of temperature and humidity data so as to determine whether the interior of the grain bulk is in the safe condition. The application of the system in the state grain reserve depots shows that the improved algorithm can accurately achieve grain security level intelligent analysis.

关 键 词：粒子群 BP神经网络算法 粮情测控系统 模糊控制 

分 类 号：TS210[轻工技术与工程—粮食、油脂及植物蛋白工程] TP39[轻工技术与工程—食品科学与工程]