Current Transformer Oil Leak Detection Algorithm Based on Change Detection and Grayscale Histogram Double Gaussian Fitting

Current transformers are important equipment in unattended substations. Its operating conditions must be monitored in real time, and corresponding alarms should be generated when abnormal conditions occur. A current transformer oil leak detection algorithm based on change detection and grayscale histogram double Gaussian fit analysis is proposed in this paper. The ViBe algorithm is used to determine the anomalous region, and the gray histogram of the anomalous region is subjected to double Gaussian fitting analysis. The analysis results can be used to determine whether there is oil leakage in the anomalous region. Experiments show that the method introduced in this paper can detect abnormal oil leakage of current transformer more accurately , and can well eliminate the impacts of external factors such as changes in light conditions, shadows, and rain. It also provides support for monitoring and early warning of current transformers.