Bearbmagovva

Quality Inspection in Casting Aluminum Parts: A Machine Vision System for Filings Detection and Hole Inspection

Furkejuvvon:
Publikašuvnnas:Journal of Intelligent & Robotic Systems vol. 111, no. 2 (Jun 2025), p. 53
Váldodahkki: Nascimento, Rui
Eará dahkkit: Ferreira, Tony, Rocha, Cláudia D., Filipe, Vítor, Silva, Manuel F., Veiga, Germano, Rocha, Luis
Almmustuhtton:
Springer Nature B.V.
Fáttát:
Fatigue
Template matching
Quality assessment
Image analysis
Inspection
Machine vision
Image segmentation
Aluminum
Instance segmentation
Computer vision
Machine learning
Image processing
Vision systems
Filing
Image processing systems
Liŋkkat:Citation/Abstract
Full Text - PDF
Fáddágilkorat: Lasit fáddágilkoriid
Eai fáddágilkorat, Lasit vuosttaš fáddágilkora!
Abstrákta:Quality inspection inspection systems are critical for maintaining product integrity. Being a repetitive task, when performed by operators only, it can be slow and error-prone. This paper introduces an automated inspection system for quality assessment in casting aluminum parts resorting to a robotic system. The method comprises two processes: filing detection and hole inspection. For filing detection, five deep learning modes were trained. These models include an object detector and four instance segmentation models: YOLOv8, YOLOv8n-seg, YOLOv8s-seg, YOLOv8m-seg, and Mask R-CNN, respectively. Among these, YOLOv8s-seg exhibited the best overall performance, achieving a recall rate of 98.10%, critical for minimizing false negatives and yielding the best overall results. Alongside, the system inspects holes, utilizing image processing techniques like template-matching and blob detection, achieving a 97.30% accuracy and a 2.67% Percentage of Wrong Classifications. The system improves inspection precision and efficiency while supporting sustainability and ergonomic standards, reducing material waste and reducing operator fatigue.
ISSN:0921-0296
1573-0409
DOI:10.1007/s10846-025-02251-2
Gáldu:Advanced Technologies & Aerospace Database