A LSTM Line Selection Method of Single-phase Ground Fault Based on Big-data Platform

Author(s):  
Liu Zhengyi ◽  
Deng Changhong ◽  
Ying Huamei ◽  
Fan Hu
2021 ◽  
Vol 2095 (1) ◽  
pp. 012029
Author(s):  
Yicen Liu ◽  
Xiaojiang Liu ◽  
Songhai Fan ◽  
Xiaomin Ma ◽  
Sijing Deng

Abstract In view of the complex characteristics of nonlinearity and non-stableness of the zero-order current of each line after the single-phase ground fault of the distribution network, a distribution network fault selection method based on Sooty Tern Optimization Algorithm(STOA) and the combination of support vector machine is proposed. At first, the zero-sequence current before and after fault is obtained, then five kinds of IMFs including different components are obtained by ensemble empirical mode decomposition, and the energy entropy of the fault transient zero-sequence current is obtained by Hilbert transform, the results of training and testing are obtained by inputting the feature vector. The simulation results show that the accuracy of the proposed line selection model is 97.5%.


2012 ◽  
Vol 482-484 ◽  
pp. 2197-2203 ◽  
Author(s):  
Fang Peng ◽  
Yu Shen Zhou ◽  
Yong Feng Liu ◽  
An Hui Yuan ◽  
Lei Zhu

Abstract:This paper analyses characteristics of single-phase ground fault in distribution system. Now, most of the line selection methods have some limitations, which leads to the low accuracy of the fault line selection. In order to solve above problems, make use of the matlab software in this article to simulate and analyze the isolated neutral system and resonance neutral earthing system when they occur single-phase ground fault. Finally, the new method based on first half wave method and increment of residual current to improve the accuracy of fault line selection is proposed.


2012 ◽  
Vol 217-219 ◽  
pp. 2629-2633 ◽  
Author(s):  
Yang Liu ◽  
Zhang Bao Chen ◽  
Lin Ye

In order to find new fault line selection method of single-phase distribution network, First parallel resistance in the neutral point in order to increase the transient component of the fault line, obtained the line energy after the failure through the integral transform , initially selected probable fault lines , on this basis, decompose all the transient zero sequence currents in every line by separation based on nicer separate frequency characteristic of wavelet packets, to accurately determine the greatest fault line by the characteristic that the value of second singular point generated by zero sequence current is maximum and its polarity is opposite to the other normal lines, simulation results show the effectiveness and correctness of the method. So the method for detection of the fault line based on wavelet packets and the compare of energy is new and effective.


2013 ◽  
Vol 340 ◽  
pp. 445-450
Author(s):  
Jun Ying Zhao ◽  
Xing He Ma ◽  
Bing Yao Yan

In order to solve the high-voltage grid electricity coal mine one-phase ground fault (high leak), choose the theory of fuzzy algorithm. According to the current harmonic fault diagnostic, zero sequence active power method and transient zero sequence current mutual product summation method, three methods set fault measure membership function and weight coefficient membership function, realize fuzzy comprehensive decision, judge single-phase grounding line. Through the Matlab/Simulink simulation experiment, fuzzy theory algorithm can accurately choose single-phase grounding line.


Sign in / Sign up

Export Citation Format

Share Document