Journal
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
Volume 34, Issue 10, Pages 7024-7033Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2021.3137172
Keywords
Surface roughness; Rough surfaces; Generative adversarial networks; Feature extraction; Generators; Deep learning; Training; Auto-encoder (AE); deep coral; deep learning; generative adversarial network (GAN); surface roughness prediction
Ask authors/readers for more resources
The article proposes a new data augmentation method based on CoralGAN for predicting part surface roughness, addressing the issues of high collection cost, unbalanced categories, and complicated data distribution. The proposed method improves the prediction accuracy of part surface roughness, as demonstrated in experiments.
Deep learning networks can be applied to the field of intelligent prediction of part surface roughness. However, the surface roughness samples of parts have the problems of high collection cost, unbalanced categories, and complicated data distribution, which inevitably limit the application of deep learning network models in the field of intelligent prediction of part surface roughness. To solve these problems, this article proposes a novel data augmentation method based on CoralGAN for prediction of part surface roughness, which introduces the domain adaptive method deep coral function to help optimize the network parameters of the generator of generative adversarial network (GAN). Specifically, the vibration signal collected during processing is converted into frequency spectrum data and input into CoralGAN. The training of the generator is guided by coral loss, that is, the distance between the covariances of the real samples and generated samples features, not just the statistical consistency of the traditional GAN. Experiments have been carried out on the three-axis vertical machining center. Research shows that the proposed method can improve the prediction accuracy of part surface roughness to 95.5%.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available