Deep Fractional Multidimensional Spectrum Convolutional Neural Fusion Network for Identifying Complex Power Quality Disturbance

The widespread utilization of renewable energy sources can cause serious power quality problems. It presents new challenges for detecting power quality. A deep fractional multidimensional spectrum convolutional neural fusion network (FMSNet) method for automatically identifying and classifying complex power quality disturbance (PQD) signals is proposed in this article. It includes a 1-D spatial sense convolution block (SSCB), streamline sandwich block (SSB), and spatial fractional Fourier transform (SFRFT). Specifically, the SFRFT extracts the fractional domain features of the PQD signal. The issue of complex disturbance signals lacking detailed feature information is overcome by utilizing dynamic spatial fractional domain information. Moreover, the properties of FMSNet are further improved by combining the proposed SSCB and SSB. It is shown based on a large number of simulation experiments and hardware test experiments that the method presents significant detection capability and excellent noise immunity for the identification of complex PQD signals under different noise conditions.