An Automatic Monitoring Method for Power Circuit Breaker Tripping Status Based on Machine Vision

In the power system, the monitoring of the tripping status of power supply circuit breakers often relies on manual inspection, which is inefficient and the accuracy and comprehensiveness of the monitoring results are difficult to guarantee. Therefore, this study proposes an automatic monitoring method for the tripping status of power circuit breakers based on machine vision. After collecting the monitoring images of the tripping state of the power circuit breaker using a visual sensor, the images are subjected to grayscale conversion and Gaussian filtering denoising processing. Then, based on machine learning technology, an SVM model is constructed. The preprocessed visual monitoring images are input for classification and recognition, and the automatic monitoring results of the power circuit breaker tripping state are obtained and output. The experimental results show that after applying this method, the false detection rate of the automatic monitoring results of the power supply circuit breaker tripping state is only 0.49% and the missed detection rate is only 0.63%, indicating that this method can provide reliable technical support for the stable operation of the power system.