Xiaotian Tang

TL;DR: A robustness-improved method for dynamic equivalent modeling of ADN is proposed and long short-term memory neural network is adopted to generalize the identified parameters and enhance the robustness of equivalent model.

TL;DR: The singularity detection theory of wavelet transform is adopted and used to decompose the node fault voltage when the fault occurs and reduced the accuracy of fault location and fault type judgment.

TL;DR: In this paper , the authors proposed a novel arc fault identification approach, which evaluated both the transient and steady dynamic states of arcing faults by time-frequency analysis, and the complete ensemble empirical mode decomposition with adaptive noise, incorporated with Hilbert transform, has been designed to realize the rapid and reliable signatures extraction from arc fault profiles.

TL;DR: In this paper, a novel arc flash preemptive detection and location mechanism is proposed for weak system source and high arcing resistance featured medium-low voltage arc flash, which shows a good ability to catch the transient dynamics of arcing current in the early initiating stage, and also proves the reliability and accuracy on fast detection and position uses.

TL;DR: A robust-improved method for dynamic equivalent modeling of ADN and Elman Neural Network is used to derive the robust sets of parameters that are able to help the developed equivalent model adaptable for the wide range of distinct ADN operation conditions.