基于随机截尾数据及极大似然估计的继电保护可靠性分布

Reliability distribution of relay protection based on random truncation data and maximum likelihood estimation

保护装置缺陷严重影响装置运行可靠性。装置缺陷分布是评估装置可靠性的重要依据。受制于装置运行时间长,缺陷发生率低,无法获取完整的缺陷数据,缺陷数据存在随机截尾特征。采用极大似然估计法,基于两参数的威布尔分布模型,实现对继电保护装置缺陷分布的参数估计。基于保护装置的电源模块、CPU模块、交流采样模块及液晶显示模块存在独立分布的假设,建立装置整体缺陷分布的联合分布模型,实现对装置各模块及整体缺陷概率分布模型的参数估计。所提出的方法能够有效指导装置缺陷分布分析,并指导装置检修。

Defects of protective device seriously affect its operation reliability.Device defect distribution is an important basis for evaluating device reliability.Due to the long running time of the device,the defect occurrence rate is low,it is unable to obtain complete defect data,and the defect data has a random truncation feature.The maximum likelihood estimation method is used,and the distributed parameter estimation of protection devices is realized based on Weibull distribution model with two parameters.Based on the assumption that the power module,CPU module,AC sampling module and LCD module of the protection device have independent distribution characteristics,it builds joint distribution model,which realizes the parameter estimation of each module and the overall defect probability distribution model.The proposed method can effectively guide the device defect distribution analysis and the device maintenance.