Power grid fault line judgment method and system based on auto-encoder

• Main Authors: ZHANG CHUN, ZHU XIN, ZHANG PENG, LIU MINGZHONG, TENG YUFEI, HU RONG, DING XUANWEN, DAI YUHAN, LONG CHENG, ZHOU WENYUE, SUN YONGCHAO
• Format: Patent
• Language: Chinese; English
• Published: 09.03.2021
• Subjects: MEASURING; MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES; PHYSICS; TESTING

The invention discloses a power grid fault line judgment method and system based on an auto-encoder. The method comprises the following steps: acquiring PMU data by adopting an IEEE39 node model simulation experiment; dividing the acquired PMU data into a training set and a test set, and performing data processing on the training set and the test set; training the neural network of the auto-encoder by adopting the training set having been subjected to data processing; and testing the trained neural network of the auto-encoder by adopting the test set having been subjected to data processing, and realizing positioning of a faulty power transmission line according to the fact that whether a loss value between the input and the output of the trained neural network of the auto-encoder exceedsa threshold value or not. According to the invention, existing fault information data can be effectively utilized, and the problems of large workload and low efficiency of manual troubleshooting and positioning are solved. 本发