Knowledge discovery in steel bar rolling mills using scheduling data and automated inspection

Agarwal, Kuldeep; Shivpuri, Rajiv

doi:10.1007/s10845-013-0730-5

Cited by 10 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Knowledge discovery models [3] have been used in investigating the role of material and process uncertainty in scatter. A simple approach is to introduce uncertainty in a deterministic process model through variance in the material and process properties and constants.…”

Section: Deterministic and Probabilistic Predictionsmentioning

confidence: 99%

Metal forming beyond shaping: Predicting and setting product properties

et al. 2015

View full text Add to dashboard Cite

Section: Deterministic and Probabilistic Predictionsmentioning

confidence: 99%

Metal forming beyond shaping: Predicting and setting product properties

et al. 2015

View full text Add to dashboard Cite

“…Recently, several studies have been conducted on computer vision systems for the factory automation in steel industry. [1][2][3][4][5][6] To achieve factory automation, it is important to develop a system that recognizes the steel product identification number, which is the analogue of a person's name, [7][8][9][10] as this should be managed and tracked for customized production. Among steel products, billets are considered in this study.…”

Section: Introductionmentioning

confidence: 99%

End-to-end Billet Identification Number Recognition System

et al. 2019

View full text Add to dashboard Cite

In steel industry, product number recognition is necessary for factory automation. Before final production, the billet identification number (BIN) should be checked to prevent mixing billets of different material. There are two types of BINs, namely, paint-type and sticker-type BINs. In addition, the BIN comprises seven to nine alphanumeric characters except the letters I and O. The BIN may be rotated in various directions. Therefore, for proper recognition and accident prevention, end-to-end BIN recognition system that uses the deep learning is proposed. Specifically, interpretation and sticker extraction modules are developed. Furthermore, the fully convolutional network (FCN) with deconvolution layer is used and optimized. To increase the BIN recognition accuracy, the FCN was simulated for various structures and was transferred from the pre-trained model. The BIN is identified by the trained FCN model and interpretation module. If the BIN is sticker-type, it is inferred after the sticker region is extracted by the sticker extraction module. The accuracy of the proposed system was shown to be approximately 99.59% in an eight-day period.

show abstract

“…Among the various non-contact methods of detecting and tracking, the machine vision is more suitable for longdistance detection and tracking in steelworks. Hence many steelworks have shown great interests in the application of machine vision to solve this kind of problem [6][7][8].…”

Section: Introductionmentioning

confidence: 99%

Toward intelligent manufacturing: label characters marking and recognition method for steel products with machine vision

Zhao

Cao

2014

Adv. Manuf.

View full text Add to dashboard Cite

Correctly coding materials and identifying characters marked on materials are very important for steel manufacturing industry to realize informatization management and intelligent manufacturing. However, the steel products manufacturing is often in a high temperature environment, and there are a lot of material storage and retrieval processes, workers are not easily close to the environment and complete tasks, so it is a great challenge to automatically mark and identify characters on the steel products. This paper presents a framework of label characters marking and management for steel materials, furthermore, a kind of marked characters online detection and tracking method has been provided based on machine vision. In addition, some experiments have been done in BaoSteel to mark characters on hot billets and recognize them in multi situations, and the results show that the proposed method is practical, and has provided a helpful exploration in obtaining accurate fundamental data for the intelligent manufacturing system in steelworks.

show abstract

Knowledge discovery in steel bar rolling mills using scheduling data and automated inspection

Cited by 10 publications

References 10 publications

Metal forming beyond shaping: Predicting and setting product properties

Metal forming beyond shaping: Predicting and setting product properties

End-to-end Billet Identification Number Recognition System

Toward intelligent manufacturing: label characters marking and recognition method for steel products with machine vision

Contact Info

Product

Resources

About