CAJ | 학술논문

传感器节点通常被随机布撒于环境恶劣甚至无人能及的区域，容易发生各类故障。为了解决此问题，研究了基于K-Means算法和粗糙集神经网络的节点故障诊断方法。首先，采用改进的K-Means算法离散化数据连续属性值；然后，通过粗糙集互信息法对数据属性进行约简，以提高诊断效率；最后，建立三层的BP神经网络故障诊断模型，通过蛙跳算法对权值优化得到最终的故障诊断模型。仿真实验证明文中方法能实现传感器节点故障诊断，且与其他方法相比，具有较高的故障诊断精度和较少的诊断时间。
전감기절점통상피수궤포살우배경악렬심지무인능급적구역，용역발생각류고장。위료해결차문제，연구료기우K-Means산법화조조집신경망락적절점고장진단방법。수선，채용개진적K-Means산법리산화수거련속속성치；연후，통과조조집호신식법대수거속성진행약간，이제고진단효솔；최후，건립삼층적BP신경망락고장진단모형，통과와도산법대권치우화득도최종적고장진단모형。방진실험증명문중방법능실현전감기절점고장진단，차여기타방법상비，구유교고적고장진단정도화교소적진단시간。
The sensor node usually randomly locating in the harsh environment or the area no one can touch, with the nodes easily having fault. Therefore, the sensor node diagnosis method based on K-Means and rough set neural net-work was researched. Firstly, the improved K-Means algorithm was used to get the discrete data of the continuous at-tributes, then the rough set mutual information method was used to realize attribute reduction to improve diagnosis effi-ciency. Finally, the three-layer network fault diagnosis model was established, and the leapfrog algorithm was used to further optimize the weights to get the final fault diagnosis model. The simulation results showed that the proposed method can achieve fault diagnosis for sensor nodes, and compared with the other methods, it has the higher diagnosis precision and less diagnosis time.