期刊
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
卷 18, 期 12, 页码 8988-8998出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2022.3168432
关键词
Generative adversarial networks; Training; Manufacturing; Surface treatment; Feature extraction; Steel; Image segmentation; Attention mechanism; cycle-consistent adversarial networks (CycleGAN); small samples; surface defect classification (SDC)
类别
资金
- Natural Science Foundation of China [U21B2029, 51805192]
- Major Special Science and Technology Project of Hubei Province [2020AEA009]
- State Key Laboratory of Digital Manufacturing Equipment and Technology of Huazhong University of Science and Technology [DMETKF2020029, TII-21-5749]
This article proposes a new surface defect detection method called AttenCGAN, which utilizes cycle-consistent adversarial networks with attention mechanism. By synthesizing defect samples and enhancing features using attention mechanism, this method outperforms other published methods in terms of accuracy.
Surface defect detection is the essential process to ensure the quality of products. Surface defect classification (SDC) based on deep learning (DL) has shown its great potential. However, the well-trained SDC model usually requires large training data, and the small intraclass differences between the defect and normal samples also degrades the performance of SDC model. To overcome these drawbacks, this article proposed a new cycle-consistent adversarial networks with attention mechanism (AttenCGAN). First, AttenCGAN is used for synthesizing defect samples to enlarge the samples volume. Second, the attention mechanism is adopted for the feature enhancement by finding the discriminative parts of the samples and enlarging the differences among the samples. AttenCGAN is tested on KolektorSDD and DAGM2007 datasets, and its accuracies are 98.53% and 99.57% with only a few samples. The experiment results show that AttenCGAN outperforms other published SDC methods based on DL and machine learning, which validates its potential.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据