Author:
Karimova Nazokat,Ochilov Ulugbek,Tuyboyov Oybek,Yakhshiev Sherali,Egamberdiev Ilhom
Abstract
In modern manufacturing, providing high-quality surface finishes to mechanical parts is critical to maintaining product integrity and optimizing the performance of mechanical systems. Surface roughness directly affects various aspects of part functionality, including friction, wear resistance, and overall durability. Therefore, accurate and efficient assessment of surface finish quality is of paramount importance to ensure the reliability and longevity of mechanical components. To meet this need, this study proposes an intelligent system that leverages the capabilities of deep learning and computer vision technologies to estimate the surface roughness of machined steel parts. By combining these advanced techniques, manufacturers can automate and improve the surface quality inspection process, resulting in increased productivity and reduced costs associated with manual inspection methods. This paper proposes an innovative method for determining surface roughness after machining by combining 3D scanning technologies with the deep learning algorithm YOLOv4.
Reference14 articles.
1. Intelligent surface roughness measurement using deep learning and computer vision: a promising approach for manufacturing quality control
2. Deep Learning Advances in Computer Vision with 3D Data
3. Pahwa R.S., Nwe M.T.L., Chang R., Min O.Z., Jie W., Gopalakrishnan S., 2021 IEEE 71st Electronic Components and Technology Conference (ECTC), 2196–2204, (2021).
4. Sarkar D., Bali R., Ghosh T., Hands-On Transfer Learning with Python: Implement advanced deep learning and neural network models using TensorFlow and Keras (Packt Publishing Ltd, 2018)
5. Defect Inspection Using Modified YoloV4 on a Stitched Image of a Spinning Tool