Automatic Detection of Injection and Press Mold Parts on 2D Drawing Using Deep Neural Network

This paper proposes a deep learning-based method to automatically detect the injection mold parts (i.e., hook or boss) and press mold parts (i.e., DPS or Embo) in 3D CAD models of commercial TV. We first converted the 3D CAD models into 2D drawings and cropped them into a smaller image patch for the training efficiency of a deep neural network. Then, we found the position and type of mold parts using Cascade R-CNN and estimated the orientation of the detected mold parts using ResNet-50. Finally, we converted the 2D position of the mold parts to the 3D position of the original image. We obtained detection accuracy of injection mold parts with an average precision (AP) of 84.1% and an average recall (AR) of 91.2% and detection accuracy of press mold parts with an AP of 72.0% and an AR of 87.0%, as well as an orientation accuracy of injection and press mold parts with 94.4% and 92.0%, respectively, which can facilitate faster industrial product design.

Automated summary

This paper presents a deep learning-based method for automatically detecting injection mold parts and press mold parts in 3D CAD models of commercial TVs. By converting and cropping the models, alongside using Cascade R-CNN and ResNet-50, the study achieved accurate detection and localization of mold parts, enhancing industrial product design efficiency.