Author Login IJIRT Partner Network (IPN) Login

AI DRIVEN STEEL AND WELD DEFECT DETECTION USING DEEP LEARNING

  • Unique Paper ID: 179160
  • Volume: 11
  • Issue: 12
  • PageNo: 5713-5717
  • Abstract:
  • Detecting defects in steel materials is essential for ensuring product quality and reliability across various industrial applications. Conventional defect detection methods are often labor-intensive, time-consuming, and susceptible to human error. However, advancements in deep learning have paved the way for automated solutions that significantly enhance accuracy and efficiency. This study presents a Steel Defect Detection system utilizing a custom designed deep neural network inspired by the ResNet architecture. The model integrates novel attention layers, which have not been previously incorporated into similar architectures, to improve predictive performance. Additionally, data augmentation techniques are employed to enhance the model’s ability to generalize and accurately detect defects in complex and subtle patterns. The proposed multiclass semantic segmentation model achieves an accuracy exceeding 91%, making it a viable solution for automating the defect detection process. This automation substantially reduces inspection costs and time, optimizing industrial workflows.
Download article email to a friend

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 12
  • PageNo: 5713-5717

AI DRIVEN STEEL AND WELD DEFECT DETECTION USING DEEP LEARNING

Related Articles

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

Latest Publication

Archive

View More

Recent Conferences

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024 Last Date: 15th March 2024

Submit inquiry