Abstract
This paper presents a micro defect data set expansion method focuses on the microcrack defect of magnetic ring. Deep neural networks require a mass of training samples to be fully optimized. However, it is difficult to obtain a mass of defective samples in industrial field. In the case of insufficient samples, using GANs (Generative Adversarial Networks) for data expansion can effectively solve the problems of model over-fitting and low detection accuracy caused by insufficient training samples. However, it is difficult for conventional GANs to generate microcrack defective samples of high quality. This paper presents Defect Enhancement Generative Adversarial Network (DEGAN). This model can generate microcrack defects with obvious defect characteristics and high diversity. The experimental results show that the defective samples generated by DEGAN are very close to the real ones. The data set amplified by this model can significantly optimize deep neural network and achieve higher defect detection accuracy.
Highlights
The discriminator of Defect Enhancement Generative Adversarial Network (DEGAN) in this paper uses the structure of autoencoder, which is similar to another classic generation confrontation model Boundary Equilibrium Generative adversarial networks (GANs) (BEGAN)
In this paper, we proposed a new framework of GAN, namely DEGAN, to solve the problem of insufficient samples of crack defects in magnetic rings
Compared with DCGAN model, the defective samples generated by DEGAN have higher diversity, clearer details, which are closer to the real defective samples
Summary
In order to solve the problem of insufficient defect data, this paper proposes defect enhancement GAN(DEGAN) model, which improves the algorithm and structure of defect generation based on DCGAN. The discriminator of DEGAN in this paper uses the structure of autoencoder, which is similar to another classic generation confrontation model Boundary Equilibrium GAN (BEGAN). Both can use the discriminator in the form of an autoencoder to output reconstruction errors.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.