基于并行计算的电能计量装置故障诊断技术研究

Research on fault diagnosis technology of electric energy metering device based on parallel computing

针对当前电能计量装置故障诊断技术的计算量较大,导致电能计量装置故障诊断效率与诊断准确率较低,提出一种基于并行计算的电能计量装置故障诊断技术。利用信息聚类技术对电能计量装置信息采样,通过阈值法对数据预处理,去除冗余数据,并建立判别函数,采用并行计算方法处理故障数据,同时执行多个故障数据处理指令,通过判别函数判断故障发生概率并将同类故障数据聚集到一起,以此实现电能计量装置故障诊断。实验结果表明,文中方法使电能计量装置故障诊断效率与准确率较大提升,并在17 MB与1024 MB数据量下,文章所提技术方法均能够在较短时间内完成故障诊断。

The current fault diagnosis technology of electric energy metering device has a large amount of calculation,which leads to the low efficiency and low accuracy of the electric energy metering device fault diagnosis.For this reason,the fault diagnosis technology of electric energy metering device based on parallel computing is proposed.The information clustering technology is used to sample the information of electric energy metering devices,preprocess data through threshold method,remove redundant data,and establish the discriminant function.The parallel computing method is used to process fault data,execute multiple fault data processing instructions at the same time,and the discriminant function is used to judge the probability of failure and gather the same kind of failure data together to realize the fault diagnosis of the electric energy metering device.The experimental results show that the proposed method greatly improves the efficiency and accuracy of fault diagnosis for electric energy metering device,and under the data volume of 17 MB and 1024 MB,the researched technology can complete the fault diagnosis in a relatively short time.