基于EMD-MDT的直流微电网线路故障检测

LINE FAULT MONITORING OF DC MICROGRID BASED ON EMD-MDT

提出一种经验模态分解和决策树相结合的风光储直流微电网配电线路故障检测和分类方法。该方法通过经验模态分解对发送端测得的直流电流进行分解,得到多个本征模态函数,并采用最大加权相关系数方法计算选取灵敏度最高的2个本征模态函数,将9个统计方法应用于本征模态函数生成故障特征值,最终基于决策树,实现风光储直流微电网配电线路的精准检测和分类。算例分析表明,基于经验模态分解的风光储直流微电网配电线路故障检测方法可不受故障电阻、故障起始时刻和故障距离的影响,快速有效的对配电线故障进行检测和分类。

An empirical mode decomposition(EMD)and decision trees(DT)based fault detection and classification method for distribution lines of wind solar energy storage DC microgrid is proposed. This method decomposes the DC current measured by the transmitter through empirical mode decomposition(EMD)to obtain multiple intrinsic mode functions(IMFs). The maximum weighted correlation coefficient method is used to calculate and select the two IMFs with the highest sensitivity. The statistical method is applied to the eigenmode function to generate the fault characteristic value,and finally based on the decision tree,the accurate detection and classification of the wind-solar DC micro-grid distribution line is realized. The analysis of the calculation example shows that the windsolar DC microgrid distribution line fault detection method based on empirical mode decomposition can detect and classify the distribution line faults quickly and effectively without being affected by the fault resistance,the starting time of the fault and the fault distance.