Search

The UHVDC transmission system has been increasingly used because of the advantages in long distance and large capacity transmission. However, the existing traveling-wave-based protection for UHVDC transmission lines is not sensitive enough to properly detect the internal fault with high fault resistance. A novel traveling-wave-based protection scheme for bipolar UHVDC lines is proposed in this paper. The discriminative characteristic between the internal and external fault, embodied in the backward traveling wave, is extracted to formulate the main protection criterion. The faulty line is identified by the polarity of the voltage fault component. In addition, only the single-pole voltage and current of rectifier side are required for the proposed protection scheme. The simulation and field data tests show that the proposed protection scheme can make a correct identification of the fault section and selection of the faulty line in the $\pm $ 800 kV UHVDC system and $\pm $500 kV HVDC system. Besides, the proposed protection can correctly detect the grounding fault with fault resistance up to 500 $\Omega $. [ABSTRACT FROM PUBLISHER]

This paper presents an ultra-high-speed (UHS) pilot protection of transmission lines based on directional comparison of the transient energy (TE). The proposed method can easily determine the fault direction by calculating the TE during a very short period. The obtained fault directions at both ends of the protected line will be compared to discriminate the internal faults. In contrast to the conventional UHS protection using initial traveling waves, this method is able to correctly operate even when the fault inception angle is at zero crossing. In order to correctly indicate the fault direction and improve its sensitivity, the data-processing window has been reasonably chosen to obtain TE by analyzing the polarity variation of the transient power. A large number of various fault scenarios have been simulated on the 750-kV system using PSCAD/EMTDC, and the results show that the proposed method is able to discriminate the internal fault very rapidly and reliably. [ABSTRACT FROM AUTHOR]

The lack of fault data is the major constraint on data-driven fault detection and isolation schemes for DC microgrids. To solve this problem, this paper develops an adversarial-based deep transfer learning model that can detect and classify short-circuit faults in DC microgrids without using historical fault data. In this transfer learning framework, the knowledge of faults is extracted from the transient features of line currents during normal operating disturbances, which is adversarially augmented and then transferred to a target domain as the labels of faults. With the transferred knowledge, a deep learning model combining convolutional neural network and attention-based bidirectional long short-term memory is trained, which is strengthened by attention and soft-voting ensemble mechanisms. In verification tests, this model reaches a high accuracy of over 90 % in classifying various short-circuit faults in a multi-terminal DC microgrid model within a short response time of less than 1 ms. Moreover, it is robust against measurement noises and adaptive to system configuration changes. The test results prove the effectiveness of the proposed method in the protection of DC microgrids without prior knowledge of faults. • No historical fault data needed for the proposed fault classification model. • Fault knowledge obtained from non-fault disturbances through transfer learning. • High accuracy (> 90 %) and short response time (< 1 ms). • Good robustness against measurement noises and changes in system configurations. [ABSTRACT FROM AUTHOR]