Deep Learning Applied to Automated Visual Defect Detection forWind Towers Painting Process

[EN] Zero Defect Manufacturing (ZDM) strategies focus on promptly and precisely detecting defects to reduce material and energy consumption, and avoid product failure while the product is in use. Integrating a computer vision defect detection system is an important approach to improving the quality...

Descripción completa

Detalles Bibliográficos
Autores: Lario-Femenía, Joan|||0000-0003-4843-3334, Pérez-García de la Puente, Natalia Lourdes|||0009-0009-9704-9102, Mateos-Luengo, Javier, Aksu, Salih
Tipo de recurso: artículo
Fecha de publicación:2025
País:España
Institución:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:dnet:riunet______::fa77ad81a1639c2e68158c5e5fcfe1ed
Acceso en línea:https://riunet.upv.es/handle/10251/235138
Access Level:acceso embargado
Palabra clave:Defect detection
Artificial intelligence
Computer vision
Quality
Inspection
Deep learning
Surface defects
07.- Asegurar el acceso a energías asequibles, fiables, sostenibles y modernas para todos
08.- Fomentar el crecimiento económico sostenido, inclusivo y sostenible, el empleo pleno y productivo, y el trabajo decente para todos
09.- Desarrollar infraestructuras resilientes, promover la industrialización inclusiva y sostenible, y fomentar la innovación
12.- Garantizar las pautas de consumo y de producción sostenibles
Descripción
Sumario:[EN] Zero Defect Manufacturing (ZDM) strategies focus on promptly and precisely detecting defects to reduce material and energy consumption, and avoid product failure while the product is in use. Integrating a computer vision defect detection system is an important approach to improving the quality of inspection policies and the performance of the manufacturing process. Last year¿s high attention has been paid to surface image defect detection based on deep learning algorithms. The deep learning methods on automated vision systems require large quantities of annotated data. Acquiring defects is a costly and time-consuming task in industrial contexts since defects only occur in small percentages, data is biased through the predomination of non-defective samples, and there is a lack of publicly available datasets to train the algorithms. This study aims to evaluate the performance of a deep learning algorithm based on the dataset employed and the training parameters selected