Aiming at the practical engineering problem, it is easy to be confused and difficult to detect, such as the single pole high impedance ground fault and load switching of the DC microgrid. This paper proposes a method, which the impedance ground faults detection and classification method. Based on the combination of improved complete ensemble empirical mode decomposition with adaptive noise and random forest. First, the dependence of original signal is reduced by complete ensemble empirical mode decomposition with adaptive noise. Secondly, by comparing the cumulative slope sum k with the threshold, the abnormal conditions can be distinguished from the normal condition, load switching and the ground faults can be further distinguished through the energy ratio R ratio . Finally, the random forest is used to further classify the ground faults to achieve precise classification of impedance ground faults in the DC microgrid. The analysis of calculation examples shows the method, it is quickly and effectively to detect and classify impedance ground faults in DC microgrid quickly and effectively, without being affected by fault resistance, fault initiation time and fault location.

为降低海上风电场结构复杂、故障行波信号微弱等因素对集电线路故障定位的影响,提出一种基于决策系数与极点对称模态分解-Teager能量算子ESMD-TEO(extreme-point symmetric mode decomposition-Teager ener?gy operator)的集电多分支线路故障定位方法.分析风电场内不同位置故障的决策系数,得出决策系数与故障点位置之间的映射关系,基于此关系提出相对应故障支路判据.利用ESMD将故障初始行波分解成多个固有模态函数IMF(intrinsic mode function),并通过TEO对一阶IMF信号差分计算,实现行波波头准确标定.最后,结合双端行波法实现故障点定位.仿真结果表明,所提方法对微弱行波信号具有良好的检测效果,在不采集所有线路末端的故障数据的情况下仍能准确识别故障支路并实现主集电线路故障点定位,且定位结果不受故障起始角、故障类型和过渡电阻的影响,适用于海上风电场复杂多分支集电线路.

Multi-branch complex structure and harsh maintenance environment directly lead to the high-cost and time-consuming of fault detection in deep-sea offshore wind farms (DOWF). This paper proposes a traveling wave fault location method based on a bi-level decision matrix (BDM) aiming at multi-branch deep-sea offshore wind farm transmission lines. First, the first intrinsic mode function (IMF) signal is extracted by the variational mode decomposition (VMD) from initial traveling wave signals, which is further decomposed into S matrix by Stockwell-Transform (ST). Then based on the energy similarity between E matrix obtained through S matrix at all records, the area decision matrix is built to identify fault area. Second, S matrix recorded at both ends of fault area is extracted and analyzed by kurtosis to determine the traveling wave arrival time. Based on the fault area inherent topology and the traveling wave arrival time, the section decision matrix is built to identify fault section. Finally, the fault location is determined by the corresponding calculation process based on the identification results of BDM. Referring to the actual multi-branch topology of offshore wind farm (OWF), case studies are conducted under various fault conditions. The results show that the proposed method does not need to install recorders at all terminals, has high fault location accuracy, and is immune to noise.

Due to the difficulty and time-consumption in locating short-distance transmission lines for deep-sea offshore wind farm (DOWF)?this paper proposes a novel double-terminal fault location method by using Stockwell-transform (ST) and random-forest (RF). After the fault type and branch are accurately determined, the accurate transmission line fault location is located. Firstly, Stockwell-transform is employed to extract fault eigenvalues from the collected wind turbine (WT) current signals, which will reduce the sensitivity of eigenvalues to noise. And the Pearson correlation coefficient (PCC) is introduced to remove duplicate eigenvalues. Secondly, the reserved fault eigenvalues are taken as inputs to the different random-forest to classify fault types and identify the fault branch, respectively. Finally, the double-terminal fault location principle is established in fault negative sequence network (only ABCG uses positive sequence components). Newton-Raphson method (NRM) is used to eliminate the influence of asynchrony data, which implies an accurate transmission line fault location for deep-sea offshore wind farm. More than 4000 fault cases data obtained by Simulink simulation verify the feasibility and performance of the proposed method. The results show that the proposed location method has a high fault recognition rate and is immune to fault inception angle, resistance, location and noise.

Transmission line fault detection is a complex, high-cost and time-consuming work for deep-sea offshore wind farms. Therefore, rapid intelligent on-line fault detection and classification of submarine transmission lines play a very important role in the offshore wind farm reliability improving and operating costs reduction. This paper presents a novel hybrid on-line detection method that combines Wavelet noise Reduction, Clarke transform, Stockwell transform and Decision Tree (WRC-SDT). First, the measured Wind Turbine (WT) voltage signals are processed through wavelet noise reduction and Clarke transform to get the gradient of the voltage component. The gradient of the voltage component is then monitored in order to detect faults. Second, the recorded WT current date are processed through Stockwell transform with a view to obtaining the transmission line fault eigenvalues. The fault eigenvalues are then taken as the input of decision tree in order to classify different types of faults. To verify the feasibility and performance of the proposed method, the comparison of a detection and classification result is presented based on more than 1600 fault simulation data. The results show that WRC-SDT method is immune to fault resistance, starting angle and location. The proposed method is also robust to measurement noise.