基于贝叶斯理论的传感器网络节点故障检测方法  

Fault detection for sensor networks nodes based on Bayesian method

作　　者：何永强[1] 张文欣[2] 李可[1] 

机构地区：[1]河南工程学院计算机学院,河南郑州451191 [2]西安电子科技大学通信工程学院,陕西西安710126

出　　处：《河南工程学院学报（自然科学版）》2014年第4期65-68,共4页Journal of Henan University of Engineering：Natural Science Edition

基　　金：河南省科技厅科技计划课题(112102310550)

摘　　要：提出了运用贝叶斯理论进行传感器网络节点故障检测的方法,通过分析传感器网络中各节点的影响关系,利用贝叶斯理论对各节点的正常率进行估值计算,给出正常率计算的推导过程,通过实例验证了计算过程并与其他检测方法进行了比较分析.该方法计算简单、方便、快速,能估算检测用例数目、降低检测成本,为传感器网络节点故障的检测提供了支持.This paper proposes a fault detection method for sensor networks nodes based on Bayesian method. A estimation and calculation method is given through analyzing the influence relationship between sensor networks nodes,valuation of normal rate for each node based on Bayesian theory. The derivation of calculation is given for normal rate. Through the application examples demonstrate the calculation process,and compared with other detection methods. The method is simple,convenient,fast,and can estimate the number of cases detected using,reduce testing costs,provide support for failure detection.

关 键 词：贝叶斯理论 传感器网络 节点故障检测 正常率 节点影响关系 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]