You Li, Ling Zaixun, Cui Yibo, Cai Wanli, He Shunfan
State Grid Hubei Electric Power Research Institute, Wuhan 430077, China.
Department of Automation, South-Central University for Nationalities, Wuhan 430070, China.
Entropy (Basel). 2023 May 10;25(5):778. doi: 10.3390/e25050778.
To detect open circuit faults of grid-connected T-type inverters, this paper proposed a real-time method based on fast S transform and random forest. The three-phase fault currents of the inverter were used as the inputs of the new method and no additional sensors were needed. Some fault current harmonics and direct current components were selected as the fault features. Then, fast S transform was used to extract the features of fault currents, and random forest was used to recognize the features and the fault type, as well as locate the faulted switches. The simulation and experiments showed that the new method could detect open-circuit faults with low computation complexity and the detection accuracy was 100%. The real-time and accurate open circuit fault detection method was proven effective for grid-connected T-type inverter monitoring.
为检测并网T型逆变器的开路故障，本文提出了一种基于快速S变换和随机森林的实时方法。该方法以逆变器的三相故障电流作为输入，无需额外的传感器。选取了一些故障电流谐波和直流分量作为故障特征。然后，利用快速S变换提取故障电流特征，采用随机森林识别这些特征和故障类型，并对故障开关进行定位。仿真和实验结果表明，该新方法能够以较低的计算复杂度检测开路故障，检测准确率为100%。该实时、准确的开路故障检测方法被证明对并网T型逆变器监测有效。
