Intelligent representation method of image flatness for cold rolled strip

• Published in: Journal of iron and steel research, international Vol. 31; no. 5; pp. 1177 - 1195
• Main Authors: Xu, Yang-huan, Wang, Dong-cheng, Liu, Hong-min, Duan, Bo-wei
• Format: Journal Article
• Language: English
• Published: Singapore Springer Nature Singapore 01.05.2024
• Subjects: Applied and Technical Physics; Engineering; Machines; Manufacturing; Materials Engineering; Materials Science; Metallic Materials; Original Paper; Physical Chemistry; Processes; Representation learning; Location detection; Cold rolled strip; Image flatness; Bottleneck layer
• ISSN: 1006-706X; 2210-3988
• DOI: 10.1007/s42243-023-01068-3

Real flatness images are the bases for flatness detection based on machine vision of cold rolled strip. The characteristics of a real flatness image are analyzed, and a lightweight strip location detection (SLD) model with deep semantic segmentation networks is established. The interference areas in the real flatness image can be eliminated by the SLD model, and valid information can be retained. On this basis, the concept of image flatness is proposed for the first time. An image flatness representation (IFAR) model is established on the basis of an autoencoder with a new structure. The optimal structure of the bottleneck layer is 16 × 16 × 4, and the IFAR model exhibits a good representation effect. Moreover, interpretability analysis of the representation factors is carried out, and the difference and physical meaning of the representation factors for image flatness with different categories are analyzed. Image flatness with new defect morphologies (bilateral quarter waves and large middle waves) that are not present in the original dataset are generated by modifying the representation factors of the no wave image. Lastly, the SLD and IFAR models are used to detect and represent all the real flatness images on the test set. The average processing time for a single image is 11.42 ms, which is suitable for industrial applications. The research results provide effective methods and ideas for intelligent flatness detection technology based on machine vision.