Weld defect detection of metro vehicle based on improved faster R-CNN

The safety of train operation is seriously threatened by welding defects. In order to solve the problem of missing detection and wrong detection in aluminum alloy body weld of metro vehicles, a method based on improved Faster R-CNN is proposed in this paper. Firstly, the weld defects of aluminum alloy car body were simulated by Abaqus, and several groups of similar defects were obtained. Then, defects are classified based on the Faster R-CNN framework, and Unet model and Resnet model are introduced to improve the original Faster R-CNN framework to improve the recognition accuracy. Finally, the noise signal graph is detected to verify the robustness of the model. The simulation results show that the improved model has a higher recognition rate and robustness for Aluminum car body weld defect detection. © 2020, Central South University Press. All rights reserved.