Classification Framework for Machine Learning Support in Manufacturing

Ördek, Baris; Borgianni, Yuri; Coatanéa, Éric

doi:10.1007/978-3-031-14317-5_6

Cited by 5 publications

(1 citation statement)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because of the mentioned growth of product complexity, the exploitation of internal and external knowledge is expensive and the manufacturing process selection turns to be increasingly time-consuming and resource-inefficient. In particular, due to industrial progress, selecting the most suitable manufacturing process has become challenging for designers since process selection involves a careful investigation of a wide range of aspects such as material type, cost, part quality, application area, and production performance (Ördek et al, 2022;Zhang et al, 2014). Machine learning (ML) applications have been introduced in the manufacturing industry with this main purpose (Hoefer and Frank, 2018).…”

Section: Introductionmentioning

confidence: 99%

Application of Unsupervised Learning and Image Processing Into Classification of Designs to Be Fabricated With Additive or Traditional Manufacturing

Ördek

Borgianni

2023

Proc. Des. Soc.

Self Cite

View full text Add to dashboard Cite

Manufacturing process (MP) selection systems require a large amount of labelled data, typically not provided as design outputs. This issue is made more severe with the continuous development of Additive Manufacturing systems, which can be increasingly used to substitute traditional manufacturing technologies. The objective of this paper is to investigate the application of image processing for classifying MPs in an unsupervised approach. To this scope, k-means and hierarchical clustering algorithms are applied to an unlabelled image dataset. The input dataset is constructed from freely accessible web databases and consists of twenty randomly selected CAD models and corresponding images of machine elements: 35% additively manufactured parts and 65% manufactured with traditional manufacturing technologies. The input images are pre-processed to have the same colour and size. The k-means and hierarchical clustering algorithms reported 65% and 60% accuracy, respectively. The algorithms show comparable performance, however, the k-means algorithm failed to predict the correct subdivisions. The research shows promising potential for MP classification and image processing applications.

show abstract

Section: Introductionmentioning

confidence: 99%