多传感器信息融合测控体系在温室测控中的应用研究  

Research on the Application of Sensors Information Fusion Control System in the Conservatory Monitor

作　　者：杨帆[1,2] 程雯[1] 夏亦冰[3] 杜四平[1] 肖贝[1] 

机构地区：[1]武汉工程大学电气信息学院,武汉430073 [2]湖北省智能机器人重点实验室,武汉430073 [3]武汉纺织大学机电工程学院,武汉430073

出　　处：《武汉理工大学学报》2011年第9期156-159,共4页Journal of Wuhan University of Technology

基　　金：湖北省自然科学基金(D2010CDB11101)

摘　　要：对农作物生长环境的温度、湿度和光照等参数的实时监测和远程控制是农业生产现代化的重要手段,为此设计了一种以ARM嵌入式微处理器2410为硬件平台,结合Linux操作系统和ADS1.2集成开发环境,同时采用D-S证据理论和BP神经网络相结合算法的多传感器信息融合测控系统。BP神经网络提供一定数量的证据,D-S证据理论降低证据的不确定性,将这种基于二者的多传感器信息融合算法应用于农作物生长环境监控中,最终得到了在S1(T>30°)温度区间内93.47%的可信度,可见设计的基于多传感器信息融合的测控体系具有良好的应用前景。The real-time monitoring and remote controlling to growing environmental parameters of crops,such as temperature,humidity and illumination,which is a significant method in agricultural modernization.The system takes the ARM embedded microprocessor 2410 as the hardware platform,combines with Linux operating system and ARM Developer Suite（ADS） 1.2 integrated development environments.Moreover,it forms a measurement and control system of multisensor information fusion,which based on the D-S evidence theory and the BP neural network algorithm.The BP neural network provides some pieces of evidence;while D-S evidence theory could reduce the nondeterminacy.With the application of both multisensor information fusion algorithms,finally,the reliability is 93.47% of section,with the basic probability fusion of three sensors in three different moments.Through the simulation result of the experiment,we can see a higher recognition rate and good application prospect of the system.

关 键 词：多传感器融合 D-S证据理论 BP神经网络 测控 农作物生长 

分 类 号：TP29[自动化与计算机技术—检测技术与自动化装置]