Design and development of automatic surface defect detection in hot rolled steel strip

Pradnya D. Sutar; Pallavi S. Chandanshive; Pushpa D. Kale; Aarti H. Chavan; Uttam Y.siddha

Design and development of automatic surface defect detection in hot rolled steel strip

Authors: Pradnya D. Sutar, Pallavi S. Chandanshive, Pushpa D. Kale, Aarti H. Chavan, Uttam Y.siddha

Unique Paper ID: 151743
Volume: 8
Issue: 1
PageNo: 701-704

Keywords: steel surface defect detection; Convocutional neural network python deep learning classification

Abstract:
In the steel industry Automatic detection of steel surface defects is very important for product quality control. However, the traditional method cannot be well applied in the production line, because of slow running speed and its low accuracy. The current, popular algorithm (based on deep learning) also has the problem of low accuracy, and there is still a lot of room for improvement. This paper proposes a method combining improved and enhanced faster region convolutional neural networks (faster R-CNN) to improve the accuracy reduce the average running time . Firstly, the image input into the improved model, which add the deformable revolution network (DCN) and improved cutout to classify the sample with defects and without defects. If the probability of having a defect is less , the algorithm directly outputs the sample without defects. Otherwise, the samples are further input into the improved faster CNN . The output is the classification and location of the defect in the sample or without defect in the sample. By analyzing the data set which is obtained in the real factory environment, the accuracy of this method can reach 98%. At the same time, the average running time is faster than other models.Here, the NEU database, used for improve efficiency of model,which having six kinds of typical surface defects of hot-rolled steel strip. The results show that in all kinds of defects in database, the proposed model can perform defect segmentation ,in this process there is no need of skilled learning with no labeling and small training procedure so it is easy to give required application. also, this defect detection shall improve the reliability and productivity of steel strip's production process.

Download article

email to a friend

Cite This Article

ISSN: 2349-6002
Volume: 8
Issue: 1
PageNo: 701-704

Design and development of automatic surface defect detection in hot rolled steel strip

Available:https://ijirt.org/Article?manuscript=151743

Impact Factor
8.01 (Year 2024)

UGC Approved
Journal no 47859

Join Our IPN

IJIRT Partner Network

Submit your research paper and those of your network (friends, colleagues, or peers) through your IPN account, and receive 800 INR for each paper that gets published.

Join Now