基于并行挖掘大数据的变电站作业风险感知

Risk Perception Method of Substation Operation Based on Parallel Mining Big Data

为提高变电站安全作业风险感知精度,缩短变电站安全作业风险感知时间,提出基于并行挖掘大数据的变电站作业风险感知方法。在分析了变电站安全运行面临的关键问题基础上,以变电站故障大数据为依据,利用Pearson相关系数对影响变电站安全作业的关键要素进行并行挖掘,分析不同风险影响因素与变电站故障之间的联系,并建立故障模型。以上述分析结果为依据,采用状态枚举法对变电站风险状态进行分析,并对风险后果进行计算。试验测试结果表明,在单一风险影响因素干扰下,所提方法可在1s内做出准确的风险感知,复合影响因素干扰下,也可准确判断风险值,且误差在1%以内,具有较高的可靠性。

In order to improve the accuracy of risk perception of substation safety operation and shorten the time of risk perception of substation safety operation,a risk perception method of substation operation based on Parallel Mining big data is proposed.Based on the analysis of the key problems in the safe operation of substation,based on the big data of substation fault,the paper uses Pearson correlation coefficient to excavate the key elements that affect the safety operation of substation in parallel,analyzes the relationship between different risk influencing factors and substation fault,and establishes the fault model.Based on the above analysis results,the risk state of substation is analyzed by state enumeration method,and the risk consequences are calculated.The test results show that the proposed method can make accurate risk perception in 1s under the interference of single risk influencing factors,and can accurately judge the risk value under the interference of composite influencing factors,and the error is less than 1%.It has high reliability,and can effectively improve the accuracy of substation safety operation risk perception and shorten the time of substation safety operation risk perception.