期刊
IEEE SENSORS LETTERS
卷 6, 期 3, 页码 -出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LSENS.2022.3150776
关键词
Microstructure; Noise reduction; Steel; Generators; Feature extraction; Carbon; Training; Sensor phenomena; deep learning; generative adversarial networks (GANs); grain boundary; heat treatment; image processing; microstructure image denoising
资金
- Science and Engineering Research Board (SERB), Department of Science and Technology (DST) [ECR/2016/000040]
Thermo-mechanical treatments are important for improving the quality of metals by enabling the evolution of metal microstructures. Computer-based simulations of these treatments have become popular in the metallurgy industry due to their efficiency and accuracy. In this study, a generative adversarial network architecture is proposed for denoising steel microstructure images, which shows better performance compared to state-of-the-art techniques.
Thermo-mechanical treatments are employed to bring about variety in the quality of metals. These treatments only work when carried out in accordance with appropriate schedules, so as to enable the evolution of metal microstructures in a suitable way. Recently, computer-based simulations of these treatments have become hugely desired in the metallurgy industry, due to their time and resource efficiency, and also because they are free from manual experimentation errors. However, such simulations are realizable only with digital microstructure images, accessible in proper digitized forms. Taking that into consideration, we propose a generative adversarial network architecture for denoising steel microstructure images. Experimental results demonstrate the efficacy of the proposed model in comparison to the contemporary state-of-the-art techniques.
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