MACHINE LEARNING DRIVEN QUALITY CONTROL SYSTEMS FOR DEFECT DETECTION IN STRUCTURAL COMPONENT FABRICATION

Pablo Ross Susan

MACHINE LEARNING DRIVEN QUALITY CONTROL SYSTEMS FOR DEFECT DETECTION IN STRUCTURAL COMPONENT FABRICATION

Authors

Pablo Ross Susan

Machine Learning Engineer, Argentina.

Keywords:

Machine Learning, Quality Control, Defect Detection, Structural Fabrication, Convolutional Neural Networks, Smart Manufacturing

Synopsis

Structural component fabrication is a critical phase in engineering where precision and integrity are paramount. Traditional quality control systems often fall short in terms of adaptability and real-time responsiveness. This paper explores machine learning (ML) applications in automated defect detection, demonstrating their potential to significantly enhance fabrication reliability. Leveraging image recognition, anomaly detection, and supervised learning models, ML systems offer cost-effective, scalable, and high-accuracy alternatives to manual inspection. Through a review of prior works and analysis of recent advancements, we propose a framework integrating convolutional neural networks (CNNs) and real-time sensors to detect and classify fabrication defects with high precision.

References

[1] Chen, J., et al. (2020). CNN-Based Steel Surface Defect Classification. Journal of Intelligent Manufacturing, 31(4), 871–883.

[2] Liu, Y., & Wang, Q. (2021). SVM-based Ultrasonic Defect Detection in Aluminum Casting. NDT & E International, 118, 102429.

[3] Zhang, L., et al. (2019). Sensor Fusion for Welding Defect Detection Using Random Forest. Procedia CIRP, 83, 532–537.

[4] Park, S., & Lee, H. (2022). YOLOv5 for Semiconductor Defect Localization. IEEE Transactions on Semiconductor Manufacturing, 35(2), 102–110.

[5] Singh, R., & Sharma, K. (2022). Ensemble Learning for Anomaly Detection in Manufacturing. Journal of Manufacturing Systems, 62, 264–272.

[6] Ito, M., et al. (2021). Hybrid ML Models for Composite Defect Detection. Composites Part B, 218, 108927.

[7] Gummadi, V. P. K. (2020). API design and implementation: RAML and OpenAPI specification. Journal of Electrical Systems, 16(4). https://doi.org/10.52783/jes.9329

[8] Ren, Y., Huang, S., & Wang, L. (2018). Automated Visual Inspection System for Surface Defects in Manufacturing Using Deep Learning. Robotics and Computer-Integrated Manufacturing, 54, 65–73.

[9] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778.

[10] Zhang, Y., & Xie, M. (2017). Intelligent Quality Control System Based on Convolutional Neural Networks for Composite Materials. Advanced Materials Research, 1133, 59–64.

[11] Tsai, D. M., & Hsieh, C. Y. (2015). Automated Surface Inspection Using Gabor Filters and Machine Learning. Image and Vision Computing, 32(10), 764–776.

[12] Rausch, A., & Lienkamp, M. (2020). Sensor Fusion and Machine Learning for Weld Defect Detection in Automated Manufacturing.

Procedia Manufacturing, 48, 955–962.

[13] Boussaid, L., & Fnaiech, F. (2018). Acoustic Emission-Based Defect Classification Using ML Algorithms in Structural Health Monitoring. Expert Systems with Applications, 104, 153–162.

[14] Leung, C. K., & Li, Q. (2019). Machine Learning Techniques for Crack Detection in Concrete Structures Using UAV Images. Automation in Construction, 100, 44–52.