• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.8 s.185
• /
• pp.80-88
• /
• 2006

This paper proposes a new steel strip surface inspection system. The system acquires bright and dark field images of defects by using a stroboscopic IR LED illuminator and area camera system and the defect images are preprocessed and segmented in real time for feature extraction. 4113 defect samples of hot rolled steel strip are used to develop KNN (k- Nearest Neighbor) classifier which classifies the defects into 8 different types. The developed KNN classifier demonstrates about 85% classifying performance which is considered very plausible result.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.10a
• /
• pp.379-383
• /
• 2005

This paper proposes a new steel strip surface inspection system. The system acquires bright and dark field images of defects by using a stroboscopic IR LED light and area camera system and the defect images are preprocessed and segmented in real time for feature extraction. 4113 defect samples of cold roll steel strips are used to develop KNN (k-Nearest Neighbor) classifier which classifies the defects into 8 different types. The developed KNN classifier demonstrates about 85% classifying performance which is considered very plausible result.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.4
• /
• pp.247-252
• /
• 2016

In this paper, we propose a new defect detection technology for micro-defect on the surface of steel products. Due to depth and size of microscopic defect, slop of surface and vibration of strip, the conventional optical method cannot guarantee the detection performance. To solve the above-mentioned problems and increase signal to noise ratio, a novel retro-schlieren method that consists of retro reflector and knife edge is proposed. Moreover dual switching lighting method is also applied to distinguish uneven micro defects and surface noise. In proposed method, defective regions are represented by a black and white pattern. This pattern is detected by a defect detection algorithm with Gabor filter. Experimental results by simulator for sample defects of cold rolled steel show that the proposed method is effective.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.31 no.6 s.261
• /
• pp.651-658
• /
• 2007

A new tree-structured neural network classifier is proposed for the automatic real-time inspection of cold-rolled steel strip surface defects. The defects are classified into 3 groups such as area type, disk type, area & line type in the first stage of the tree-structured neural network. The defects are classified in more detail into 11 major defect types which are considered as serious defects in the second stage of neural network. The tree-structured neural network classifier consists of 4 different neural networks and optimum features are selected for each neural network classifier by using SFFS algorithm and correlation test. The developed classifier demonstrates very plausible result which is compatible with commercial products having high world-wide market shares.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2009.04a
• /
• pp.73-76
• /
• 2009

Increase in tensile strength of steel is important for fuel efficiency and $CO_2$ reduction. But the higher the strip strength, the more defect could be generated in hot strip mill. This study focuses on line-type edge scab. One of the causes for the defect is initial edge cracks commonly observed on a slab but their correlation has not been verified yet. Thus, the objective of this report is to verify if the edge crack is exactly the seed for edge scab. For this, we conducted pilot hot rolling test with cracked slab and compared the development of cracks and edge scabs on hot-rolled strip.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.3
• /
• pp.19-26
• /
• 2020

Steel production requires high-quality surfaces with minimal defects. Therefore, the detection algorithms for the surface defects of steel strip should have good generalization performance. To meet the growing demand for high-quality products, the use of intelligent visual inspection systems is becoming essential in production lines. In this paper, we proposed a ShuffleDefectNet defect detection system based on deep learning. The proposed defect detection system exceeds state-of-the-art performance for defect detection on the Northeastern University (NEU) dataset obtaining a mean average accuracy of 99.75%. We train the best performing detection with different amounts of training data and observe the performance of detection. We notice that accuracy and speed improve significantly when use the overall architecture of ShuffleDefectNet.

• Transactions of Materials Processing
• /
• v.11 no.2
• /
• pp.147-154
• /
• 2002

The tension levelling Process is Performed to elongate the strip plastically In combination of tensile and bending strain so that all longitudinal fibers In the strip have an approximately equal amount ofn length and undesirable strip shapes are corrected to the flat shape. Thus paper is concerned with a simulation of the tension levelling process based on the analysis of tile unit model for the tension leveller. Analysis technique such as the sequential analysis of the unit model is suggested and verified with the assembly analysis of the unit model for the effective arts economic analysis of the full set of the tension leveller. Analysis of the full tension levelling Process using sequential unit models Is carried out for steel strips with the shape defect and provides the effect of the intermesh and optimum amount of the intermesh in tension levelling process.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.05a
• /
• pp.61-62
• /
• 2006

A new neural network classifier is proposed for the automatic real-time surface inspection of high-speed cold steel strips having 11 different types of defects. 46 geometrical and gray-level features are extracted for the defect classification. 3241 samples of Posco's Kwangyang steel factory are used for training and testing the neural network classifier. The developed classifier produces plausible 15% error rate which is much better than 20-30% error rate of human vision inspection adopted in most of domestic steel factories.

• Journal of the Korean Society for Precision Engineering
• /
• v.24 no.4 s.193
• /
• pp.76-83
• /
• 2007

A new neural network classifier is proposed for the automatic real-time surface inspection of high-speed cold steel strips having 11 different types of defects. 46 geometrical and gray-level features are extracted for the defect classification. 3241 samples of Posco's Kwangyang steel factory are used for training and testing the neural network classifier. The developed classifier produces plausible 15% error rate which is much better than 20-30% error rate of human vision inspection adopted in most of domestic steel factories.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.16 no.4
• /
• pp.819-827
• /
• 1992

Investigations of the fatigue damage of roughing mill roll and experimentally. By the computer simulation for analysing the stresses on the roll surface and experimental hot rolling, the following results were drawn : The crakcs observed on the roll surface were initiated thermally in the initial stage of the rolling and propagated by repeated thermal and bending stresses. The size of the roll surface cracks smaller than 4.87mm could avoid the occurrence of tiny scab, surface defect of hot steel strip. Since the size of surface cracks observed on the roughing mill roll was very small, the fatigue damage of roll surface was found not to be the major factor for the formation of the scab.