Non-member Accurate and reliable fault location technology is essential to the stable operation of the modular multilevel converter-high voltage direct current (MMC-HVDC) system. Aiming at the difficulty of locating high-resistance ground faults on MMC-HVDC transmission lines, this paper proposes a method for fault location of transmission lines based on wavelet transform and deep belief network (DBN). First, the wavelet transform is used to decompose the original single pole ground fault voltage waveform, and then the high-frequency and low-frequency components obtained are used as training samples to train different DBN models, the final fault location results are obtained by superimposing the outputs of each model at last. The ±250 kV double-ended MMC-HVDC system model is established by using PSCAD/EMTDC, which can simulate the faults of different positions and different transition resistances. In order to verify the fault location performance of the proposed method, it is compared with two machine learning fault location methods. The results show that this method can accurately and reliably locate the single pole-to-ground fault of the transmission line with transition resistance of up to 10 000 at low sampling frequency of 20 kHz.

To solve the problem of the location of the fault point of single-pole-to-ground faults in the transmission lines of MMC-HVDC systems, this paper designs a fault location system based on support vector machine (SVM). The waveform of the traveling wave after the fault occurs is collected as a feature, and the regression mechanism of the SVM is utilized to achieve fault location. Because it is very difficult to locate high-resistance ground faults, this paper first analyzes the waveform characteristics of highresistance ground faults. Next, three steps are proposed to reduce the influence of grounding resistance on fault location. These steps include using the active pulse waveform as a new feature, classifying the samples according to ground resistance values before training regression models, and a method for adaptively extracting fault distance features is proposed. Finally, a complete location system design is proposed, and its workflow is illustrated. After the simulation test, the proposed location system only needs to obtain a single-ended fault voltage waveform at a fault recording frequency of 20 kHz to achieve an accurate location of single-pole-to-ground faults for different values of grounding resistance.

No abstract