Analysis of Trolley Wire Wear and Temperature on an Electric Train Catenary System Based on Image Processing

The catenary system particularly the trolley wire in electric trains, is vulnerable to temperature changes and wear, which affects both safety and operating effectiveness. This study provides an image processing‐based approach to replace ineffective human inspections. We collected trolley wire data using a thermal Flir One Gen 3 camera and a Z Cam E2 camera. Convolutional neural network (CNN) techniques were then used to identify wear and arcing (electrical sparks). According to test findings, the thermal Flir One Gen 3 camera measures temperature with an average accuracy of 99.80%. By merging three transfer learning models VGG16, ResNet50, and VGG16‐Alt—our trained CNN model was able to identify the suggested arcing with an accuracy of 94.83%, according to experimental data. Additionally, two CNN architectures were tested for trolley wire wear analysis: with specialized tuning for trolley wire contour identification, EfficientNetB0 attained an accuracy of 87.2%, whereas ensemble ResNet50 obtained 87.48% using 5‐Fold Cross‐Validation.