Improved YOLO algorithm for identifying abnormal states in electric energy metering devices

The energy metering device is an important component of the power system, and its normal operation is crucial for ensuring the reliability of power supply. In order to timely identify the abnormal state of the device, the time-series data of the operating state of the electric energy metering device is collected. The Fourier transform algorithm is used to obtain the frequency domain characteristics of the operating voltage data of the intelligent electric energy metering device. In order to address the problem of misjudgment that may occur when analyzing state data with high similarity using the YOLO algorithm, the K-means clustering algorithm is used to improve the YOLO algorithm. By updating the clustering center, the clustering results of the intelligent electric energy metering device data are optimized, and finally the abnormal state recognition results of the electric energy metering device are obtained. The test results verified that the voltage monitoring results of the method are basically consistent with the true values, and the extracted current operation data features are basically consistent with the actual features, with small errors and high recognition accuracy.