混合粒子群算法在储粮环境中的应用  

APPLICATION OF HYBRID PARTICLE SWARM ALGORITHM IN GRAIN STORAGE ENVIRONMENT

作　　者：王婧[1] 甄彤[1] 吴建军[1] 丁伟[1] 

机构地区：[1]河南工业大学信息科学与工程学院,河南郑州450001

出　　处：《河南工业大学学报（自然科学版）》2010年第4期76-79,共4页Journal of Henan University of Technology：Natural Science Edition

基　　金：国家"十一五"科技支撑计划项目(2006BAD08B01);郑州市科技攻关项目(083SGXG25121-19);河南工业大学校科研基金项目(08XPT003)

摘　　要：为了保证储粮环境安全,需要严格控制湿度、温度等内部与外部因素.将粒子群-BP神经网络技术应用于粮情测控系统,把同一粮仓的不同位置提供的温度、湿度数据进行融合处理,以提高目标参量测量的准确度和稳定性.首先,通过BP神经网络对粮情数据进行初次融合;然后,通过粒子群对其融合结果进行处理.该方法能够实现对同质数据的优化处理,并从整体上考虑了数据的互补性,提高了测控系统的可靠性.In order to ensure safety of grain storage environmen ternal factors, such as humidity and temperature. We applied t, th we need to strictly control the internal and exe PSO-BP neural network technology to a grain measurement and control system to achieve fusion processing of temperature and humidity data in different positions of the same granary so as to enhance the accuracy and stability of target parameter measurement. Firstly, the grain storage data were fused for the first time by the BP neural network ; secondly, we applied PSO to process the fusion result. The method can achieve optimization of homogeneous data while generally considering the data complementary, thereby improving the reliability of the measurement and control system.

关 键 词：粒子群 BP神经网络 粮情测控系统 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]