From Segmentation to Classification: A Deep Learning Scheme for Sintered Surface Images Processing
-
Published:2023-12-25
Issue:1
Volume:12
Page:53
-
ISSN:2227-9717
-
Container-title:Processes
-
language:en
-
Short-container-title:Processes
Author:
Yang Yi12ORCID, Chen Tengtuo1ORCID, Zhao Liang3
Affiliation:
1. School of Reliability and Systems Engineering, Beihang University, Beijing 100191, China 2. Peng Cheng Laboratory, Shenzhen 518000, China 3. School of Software Technology, Dalian University of Technology, Dalian 116024, China
Abstract
Effectively managing the quality of iron ore is critical to iron and steel metallurgy. Although quality inspection is crucial, the perspective of sintered surface identification remains largely unexplored. To bridge this gap, we propose a deep learning scheme for mining the necessary information in sintered images processing to replace manual labor and realize intelligent inspection, consisting of segmentation and classification. Specifically, we first employ a DeepLabv3+ semantic segmentation algorithm to extract the effective material surface features. Unlike the original model, which includes a high number of computational parameters, we use SqueezeNet as the backbone to improve model efficiency. Based on the initial annotation of the processed images, the sintered surface dataset is constructed. Then, considering the scarcity of labeled data, a semi-supervised deep learning scheme for sintered surface classification is developed, which is based on pseudo-labels. Experiments show that the improved semantic segmentation model can effectively segment the sintered surface, achieving 98.01% segmentation accuracy with only a 5.71 MB size. In addition, the effectiveness of the adopted semi-supervised learning classification method based on pseudo-labels is validated in six state-of-the-art models. Among them, the ResNet-101 model has the best classification performance, with 94.73% accuracy for the semi-supervised strategy while only using 30% labeled data, which is an improvement of 1.66% compared with the fully supervised strategy.
Funder
National Science Foundation of China Innovation Project of Qiyuan Laboratory Equipment Shared Technology Pre-Research Foundation National Defense Technology Basic Research Foundation
Subject
Process Chemistry and Technology,Chemical Engineering (miscellaneous),Bioengineering
Reference40 articles.
1. Event-based modeling and control for the burnthrough point in sintering processes;Kwon;IEEE Trans. Control. Syst. Technol.,1999 2. du Preez, S.P., van Kaam, T.P.M., Ringdalen, E., Tangstad, M., Morita, K., Bessarabov, D.G., van Zyl, P.G., and Beukes, J.P. (2023). An Overview of Currently Applied Ferrochrome Production Processes and Their Waste Management Practices. Minerals, 13. 3. Chen, R., Shi, L., Huang, H., and Yuan, J. (2023). Extraction of Iron and Alumina from Red Mud with a Non-Harmful Magnetization Sintering Process. Minerals, 13. 4. Chen, S., Li, J., You, Q., Wang, Z., Shan, W., Bo, X., and Zhu, R. (2023). Improving the Air Quality Management: The Air Pollutant and Carbon Emission and Air Quality Model for Air Pollutant and Carbon Emission Reduction in the Iron and Steel Industries of Tangshan, Hebei Province, China. Atmosphere, 14. 5. A novel automatic classification method based on the hybrid lightweight shunt network for sintered surfaces;Fan;IEEE Trans. Instrum. Meas.,2022
|
|