Cyclegan Network for Sheet Metal Welding Drawing Translation

TL;DR

This paper introduces a CycleGAN-based method for automatic translation of welding engineering drawings, significantly improving efficiency and accuracy in manufacturing processes by reducing manual translation efforts.

Contribution

The paper develops an improved CycleGAN model with a high-dimensional sparse generator and residual blocks, enhancing noise robustness and resolution for engineering drawing translation.

Findings

Achieved PSNR of 44.89%, SSIM of 99.58%, MSE of 2.11.

Model outperforms traditional networks in training speed and accuracy.

Meets welding engineering precision standards.

Abstract

In intelligent manufacturing, the quality of machine translation engineering drawings will directly affect its manufacturing accuracy. Currently, most of the work is manually translated, greatly reducing production efficiency. This paper proposes an automatic translation method for welded structural engineering drawings based on Cyclic Generative Adversarial Networks (CycleGAN). The CycleGAN network model of unpaired transfer learning is used to learn the feature mapping of real welding engineering drawings to realize automatic translation of engineering drawings. U-Net and PatchGAN are the main network for the generator and discriminator, respectively. Based on removing the identity mapping function, a high-dimensional sparse network is proposed to replace the traditional dense network for the Cyclegan generator to improve noise robustness. Increase the residual block hidden layer to increase the resolution of the generated graph. The improved and fine-tuned network models are experimentally validated, computing the gap between real and generated data. It meets the welding engineering precision standard and solves the main problem of low drawing recognition efficiency in the welding manufacturing process. The results show. After training with our model, the PSNR, SSIM and MSE of welding engineering drawings reach about 44.89%, 99.58% and 2.11, respectively, which are superior to traditional networks in both training speed and accuracy.