A Data Reconstruction Method based on Adversarial Conditional Variational Autoencoder

Aiming at the problem of sample missing for magnetic flux leakage (MFL), a data reconstruction method based on conditional autoencoder (CVAE) and generative adversarial networks (GAN) is proposed. This method combines the advantages of CVAE and GAN, and generates high-quality samples steadily. The proposed CVAE-GAN method can not only reconstruct the missing MFL samples, but also generate a large amount of real and diverse defect sample, which solves the problem of low accuracy of the defect detection model due to insufficient samples and lack of diversity of samples. The defect sample are collected from the domestic in-service oil pipelines in experiments. The experimental results illustrate that the proposed method can effectively generate high-quality samples.