基于随机森林的无线传感器通信网络阻塞故障检测

Blockage fault detection of wireless sensor communication network based on random forest

针对无线传感器通信网络信道分布复杂,受外界因素影响大,导致故障检测精准度低的问题,提出一种基于随机森林的无线传感器通信网络阻塞故障检测方法。通过预设随机变量模拟存在阻塞故障、不存在阻塞故障两种状态下,样本集属性向量变化,设立判定阈值。考虑到外界因素影响,建立随机森林决策规则,输入样本数据,通过预设变量模拟外界干预因子,让检测结果逼近真实值,不断迭代直至基于判定阈值的检测结果符合规则。仿真实验证明:本文方法的检测结果与实测值吻合度高,在存在干扰环境下也能保证检测准确率,耗用时间短。

The channel distribution of wireless sensor communication network is complex,and it is greatly affected by external factors,resulting in low accuracy of fault detection.Therefore,a method of wireless sensor communication network blocking fault detection based on random forest is proposed.The change of attribute vector of sample set is simulated by preset random variables under the two states of blocking fault and non-blocking fault,and the decision threshold is set.Considering the influence of external factors,random forest decision rules are established,sample datas are input,external intervention factors through preset variables simulated,make the detection results approach the true value,and iterated until the detection results based on the decision threshold meet the rules.The simulation results show that the detection results of the proposed method are in good agreement with the measured values,and can also ensure the detection accuracy in the presence of interference environment,with short time consumption.