A methodology for part classification with supervised machine learning. Issue 1 (28th August 2018)

• Record Type: Journal Article
• Authors: Rucco, Matteo; Giannini, Franca; Lupinetti, Katia; Monti, Marina
• Is Part Of: AI EDAM. Volume 33:Issue 1(2019)
• Page Start: 100
• Page End: 113
• Publication Date: 2018-08-28
• Subjects: CAD, -- machine learning, -- shape classification, -- shape recognition, -- 3D Search; Engineering design -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; 620.00420285
• DOI: 10.1017/S0890060418000197
• Languages: English
• ISSNs: 0890-0604

Abstract

Abstract: In this paper, we report on a data analysis process for the automated classification of mechanical components. In particular, here, we describe, how to implement a machine learning system for the automated classification of parts belonging to several sub-categories. We collect models that are typically used in the mechanical industry, and then we represent each object by a collection of features. We illustrate how to set-up a supervised multi-layer artificial neural network with an ad-hoc classification schema. We test our solution on a dataset formed by 2354 elements described by 875 features and spanned among 15 sub-categories. We state the accuracy of classification in terms of average area under ROC curves and the ability to classify 606 unknown 3D objects by similarity coefficients. Our parts' classification system outperforms a classifier based on the Light Field Descriptor, which, as far as we know, actually represents the gold standard for the identification of most types of 3D mechanical objects.