A power quality disturbance identification method based on markov transition field and lightweight dense connection network

Abstract

The application discloses a power quality disturbance identification method based on a Markov transition field and a lightweight dense connection network, and comprises the following steps: constructing a PQDs standard signal set, converting a complex PQDs one-dimensional signal set into a two-dimensional feature image data set based on an MTF visualization conversion method, and dividing the two-dimensional feature image data set into a training set, a verification set and a test set; developing a DenseNet-L lightweight identification network model based on a dense connection mechanism; constructing a CBAM attention mechanism model combined with a CAM and a SAM; combining the DenseNet-L model and the CBAM model through module fusion to construct a DenseNet-LC lightweight identification model; training the DenseNet-LC model through the training set, saving an optimal performance model; and testing the identification performance of the DenseNet-LC optimal performance model through the test set to obtain a final complex PQDs identification result. The method can effectively improve the classification precision and noise resistance of complex PQDs, has real-time performance in terms of efficiency performance, and can provide technical support for the rapid perception of the operation health status of a power distribution network system.

Images