Low-voltage fault arc detection method based on self-organizing brain emotional learning

Abstract

The invention provides a low-voltage fault arc detection method based on self-organizing brain emotional learning, and the method comprises the steps: S1, calculating a periodic sampling current mean square error and a periodic current wavelet decomposition and reconstruction high-frequency component through the current detection data of a low-voltage power supply and distribution line; s2, constructing a function adjustment function with two channels and a fuzzy brain emotional learning neural network model of an automatic preferential adjustment model structure and parameters; s3, an optimization learning rate of the model is set by using a Lyapunov function, so that a model system is stable, and the fault arc in the low-voltage power supply and distribution line is correctly detected; a periodic sampling current mean square error obtained through calculation of fault arc current data and a high-frequency component obtained through periodic current wavelet decomposition and reconstruction serve as feature data, and the feature data are input into the model to train the model until the model converges; and S4, performing fault arc detection on the to-be-detected current through the low-voltage distribution line fault arc model based on self-organizing brain emotional learning.

Description

technical field [0001] The invention relates to the technical field of low-voltage fault arc detection, in particular to a low-voltage fault arc detection method based on self-organized brain emotional learning. Background technique [0002] The fault current of low-voltage distribution network is mostly caused by arc fault, which is a continuous discharge phenomenon between two electrodes across an insulating medium, often accompanied by local heating of the electrodes. A typical arc is formed in the air space between the poles, and its core temperature is generally 5000 to 15000 degrees Celsius. In the low-voltage distribution network, the lines and equipment work for a long time and the operating environment is complex. The insulation layer may be aged, damaged or poor in contact, resulting in a decrease in its insulation capacity and a fault arc. After a fault arc is generated, a very high temperature can be generated at a small current, enough to ignite combustibles ar...

AI Technical Summary

Problems solved by technology

Therefore, a single criterion is traditionally used to distinguish arc faults, and the misjudgment rate is high.

Images