多数据源信息融合的电网故障诊断新方法

Novel Approach for Fault Diagnosis of the Power Grid With Information Fusion of Multi-data Resources

电网发生故障时,故障信号主要包括开关量和电气量。开关量是继电保护的动作信息,目前的故障诊断方法主要基于开关量;电气量是各种故障暂态信息,它蕴含了故障的特征信息,但很少应用于电网故障诊断。提出一种基于改进D-S证据理论的多数据源信息融合故障诊断方法(information fusion of multi-data resources in fault diagnosis based on improved D-S theory,IMFD),首先对故障信息进行特征提取,通过模糊Petri网将开关量转化为元件的模糊故障度;利用小波变换分析电气量,得到元件的小波故障表征。然后基于改进的D-S证据理论进行信息融合,最后采用C-均值法决策故障元件。仿真计算表明,该方法将电气量和开关量进行信息融合,得到精确的故障诊断结果,在电网故障诊断中有良好的应用前景。

The fault information mainly consist of two parts, the digital part and the analogue one, when the power grid is malfunctioning. The digital information reflects the status of relays and circuit breakers by which most methods for fault diagnosis utilize this information. The analogue information is about the transient value and the wave of voltage and current. The analogue information can accurately describe the properties of failure in the power grid. However, few methods for fault diagnosis use this data resource. A new fault diagnosis method, i.e. information fusion of multi-data resources in fault diagnosis based on improved D-S theory （IMFD） with digital and analogue information is presented. The digital information is transformed to fuzzy fault degree through fuzzy Petri nets and the analogue information is transformed to wavelet fault characteristics through the wavelet analysis. Then fault diagnosis is conducted based on information fusion with the improved D-S evidence theory. Finally, the fault element is identified with C-mean algorithm. Simulation results indicate that the proposed method can improve the accuracy and the real-time performance of fault diagnosis in the power grid.