An Investigation of Thermal Fault Diagnosis of Substation Equipment Based on Improved Faster R-CNN
In order to establish an intelligent thermal fault diagnosis method for substation equipment,the research process analyzes the causes of thermal faults of high-voltage sets,circuit breakers,disconnect switches,surge arresters,current transformers,voltage transformers,and improves the deep learning algorithm Faster R-CNN,which improves the performance indexes of the accuracy of image recognition,the recall rate,the average classification accuracy of different categories,and the detection rate,then the algorithm is applied to classify and identify the thermal faults of substation equipment.The improved algorithm is used to classify and recognize infrared images of substation equipment,and establish the diagnosis process and judgment basis for thermal faults.The results show that the thermal fault diagnosis model based on the improved Faster R-CNN algorithm has good application effect.
NETL
NSTL
万方数据
