Data acqusition challenges in AI-driven surface inspection: a proven solution proposal on coated sheet metal parts
Publication date
2024-03
Document type
Conference paper
Author
Hunger, Sebastian
Breiter, Michael
Klein, Claudia
Organisational unit
Miele & Cie. KG
Eyyes GmbH
Book title
Machine learning for cyber physical systems
Part of the university bibliography
✅
Keyword
AI surface inspection
Data acquisition challenge
AI-driven quality control
Quality assurance in manufacturing
AI in industrial process
Convolutional neural network (CNN)
EfficientNet
VGG16
Abstract
This paper introduces an advanced AI-based automated surface inspection system for enhanced quality control in the manufacturing of white-coated sheet metal parts. The study emphasizes overcoming the challenges in AI-driven inspection, such as the need for large datasets corresponding to numerous physical components, which presents storage and logistical issues. By integrating Convolutional Neural Networks (CNNs) and a novel annotation process, the system can be trained effectively on various surface defects. The paper discusses three big data acquisition challenges and provides a solution approach, including large data volumes equivalent to numerous physical components, a novel division of the training process to reduce the workload for domain experts and the relevance of previously clearly defined defect classes.
Version
Published version
Access right on openHSU
Open access