Use this link to cite:
http://hdl.handle.net/2183/33692 Automatic classification of pores in aluminum castings using machine learning
Loading...
Identifiers
Publication date
Authors
Chaves, Deisy
Fidalgo, Eduardo
Rodríguez-González, P.
Fernández-Abia, A.I.
Alegre, Enrique
Barreiro, Joaquín
Advisors
Other responsabilities
Journal Title
Bibliographic citation
Chaves, D., Fidalgo, E., Rodríguez-González, P., Fernández-Abia, A., Alegre, E., Barreiro, J., 2023. Automatic pore classification in aluminum castings using machine learning. XLIV Jornadas de Automática, 849-854. https://doi.org/10.17979/spudc.9788497498609.849
Type of academic work
Academic degree
Abstract
[Resumen] La inspección de la porosidad de piezas fabricadas se ha realizado tradicionalmente mediante el uso de microscopía manipulada por parte de un técnico humano. Sin embargo, la persona involucrada necesita experiencia en esta tarea, y la cantidad de piezas que se pueden inspeccionar por unidad de tiempo es limitada. La presencia de porosidad en el material es crítica, ya que puede afectar negativamente a las propiedades mecánicas y la calidad de la pieza. En este trabajo se propone automatizar la clasificación de los defectos de porosidad que aparecen en el interior de las piezas fabricadas por fundición. En primer lugar, adquirimos imágenes a partir de piezas de aluminio fabricadas por dos métodos de fundición: uno tradicional usando molde de arena y otro más moderno con la técnica de fabricación aditiva Binder Jetting (BJ). Luego, recortamos regiones con y sin poros, que posteriormente
caracterizamos usando descriptores SIFT codificados en características de BoVW para alimentar y entrenar dos clasificadores SVM: uno para predecir si la imagen contiene poro o no, y el otro para indicar si el poro detectado es debido al efecto de gases o por contracción durante la solificación.
[Abstract] Porosity inspection of manufactured parts has traditionally been performed using microscopy manipulated by a human technician. However, the person involved needs experience in this task, and the number of parts that can be inspected per unit of time is limited. The presence of porosity in the material is critical, as it can negatively affect the mechanical properties and the quality of the part. In this paper, we propose to automate the classification of the porosity defects that appear inside the parts manufactured by casting. First, we acquire images from aluminum parts manufactured by two casting methods: a traditional one using sand molding and a more modern one with the Binder Jetting (BJ) additive manufacturing technique. Then, we crop regions with and without pores we later describe using SIFT descriptors encoded into BoVW features to feed and train two SVM classifiers: one for predicting if the image contains a pore or not, and the other for also indicating if the pore detected is due to the effect of gases or by shrinkage during solidification.
[Abstract] Porosity inspection of manufactured parts has traditionally been performed using microscopy manipulated by a human technician. However, the person involved needs experience in this task, and the number of parts that can be inspected per unit of time is limited. The presence of porosity in the material is critical, as it can negatively affect the mechanical properties and the quality of the part. In this paper, we propose to automate the classification of the porosity defects that appear inside the parts manufactured by casting. First, we acquire images from aluminum parts manufactured by two casting methods: a traditional one using sand molding and a more modern one with the Binder Jetting (BJ) additive manufacturing technique. Then, we crop regions with and without pores we later describe using SIFT descriptors encoded into BoVW features to feed and train two SVM classifiers: one for predicting if the image contains a pore or not, and the other for also indicating if the pore detected is due to the effect of gases or by shrinkage during solidification.
Description
Editor version
Rights
Attribution-NonCommercial-ShareAlike 4.0 lnternational (CC BY-NC-SA 4.0) https://creativecommons.org/licenses/by-ncsa/4.0/


