Power distribution network fault positioning method based on deep neural network

• Main Authors: DAWA LUNJU, CI REN, WAN JUN, NIPPING, TAO XIAOLI, ZHANG HAORAN, DONG ZHIHUA, LIU HAILONG, ZHANG ZHIYUAN, WANG ZHIYONG, WU YUANXIANG, DU YANGKANG, ZHOU YONGJUN, WANG ZHENLONG, LI FAGUANG
• Format: Patent
• Language: Chinese; English
• Published: 24.06.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; MEASURING; MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES; PHYSICS; TESTING

The invention discloses a fault positioning method based on a power distribution network transformer substation line topology. The method comprises the following steps: optimizing a power distribution network transformer substation line topology structure and adding virtual lines and virtual monitoring points; obtaining high-frequency components and low-frequency components of a plurality of effective data sections of each transformer substation outgoing line; obtaining high-frequency components and low-frequency components of a plurality of effective data sections of each monitoring point; and inputting the high-frequency component and the low-frequency component into a fault line selection deep neural network model and a fault positioning deep neural network model to obtain a probability X that a line has a fault and a probability Y that the monitoring point is located in front of a fault area, and carrying out weighted summation on X and Y to obtain a final probability that the monitoring point is located