Classification of ductile cast iron specimens: a machine learning approach
In this paper an automatic procedure based on a machine learning approach is proposed to classify ductile cast iron specimens according to the American Society for Testing and Materials guidelines. The mechanical properties of a specimen are strongly influenced by the peculiar morphology of their gr...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Gruppo Italiano Frattura
2017-10-01
|
| Series: | Fracture and Structural Integrity |
| Subjects: | |
| Online Access: | http://www.gruppofrattura.it/pdf/rivista/numero42/numero_42_art_25.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841562942997266432 |
|---|---|
| author | A. De Santis D. Iacoviello V. Di Cocco F. Iacoviello |
| author_facet | A. De Santis D. Iacoviello V. Di Cocco F. Iacoviello |
| author_sort | A. De Santis |
| collection | DOAJ |
| description | In this paper an automatic procedure based on a machine learning approach is proposed to classify ductile cast iron specimens according to the American Society for Testing and Materials guidelines. The mechanical properties of a specimen are strongly influenced by the peculiar morphology of their graphite elements and useful characteristics, the features, are extracted from the specimens images; these characteristics examine the shape, the distribution and the size of the graphite particle in the specimen, the nodularity and the nodule count. The principal components analysis are used to provide a more efficient representation of these data. Support vector machines are trained to obtain a classification of the data by yielding sequential binary classification steps. Numerical analysis is performed on a significant number of images providing robust results, also in presence of dust, scratches and measurement noise |
| format | Article |
| id | doaj-art-a7373a35b47b403f95aeb0f8376fe8ba |
| institution | Kabale University |
| issn | 1971-8993 |
| language | English |
| publishDate | 2017-10-01 |
| publisher | Gruppo Italiano Frattura |
| record_format | Article |
| series | Fracture and Structural Integrity |
| spelling | doaj-art-a7373a35b47b403f95aeb0f8376fe8ba2025-01-03T00:39:31ZengGruppo Italiano FratturaFracture and Structural Integrity1971-89932017-10-01114223123810.3221/IGF-ESIS.42.2510.3221/IGF-ESIS.42.25Classification of ductile cast iron specimens: a machine learning approachA. De SantisD. IacovielloV. Di CoccoF. IacovielloIn this paper an automatic procedure based on a machine learning approach is proposed to classify ductile cast iron specimens according to the American Society for Testing and Materials guidelines. The mechanical properties of a specimen are strongly influenced by the peculiar morphology of their graphite elements and useful characteristics, the features, are extracted from the specimens images; these characteristics examine the shape, the distribution and the size of the graphite particle in the specimen, the nodularity and the nodule count. The principal components analysis are used to provide a more efficient representation of these data. Support vector machines are trained to obtain a classification of the data by yielding sequential binary classification steps. Numerical analysis is performed on a significant number of images providing robust results, also in presence of dust, scratches and measurement noisehttp://www.gruppofrattura.it/pdf/rivista/numero42/numero_42_art_25.pdfDuctile cast ironsGraphite nodulesMachine learning approach |
| spellingShingle | A. De Santis D. Iacoviello V. Di Cocco F. Iacoviello Classification of ductile cast iron specimens: a machine learning approach Fracture and Structural Integrity Ductile cast irons Graphite nodules Machine learning approach |
| title | Classification of ductile cast iron specimens: a machine learning approach |
| title_full | Classification of ductile cast iron specimens: a machine learning approach |
| title_fullStr | Classification of ductile cast iron specimens: a machine learning approach |
| title_full_unstemmed | Classification of ductile cast iron specimens: a machine learning approach |
| title_short | Classification of ductile cast iron specimens: a machine learning approach |
| title_sort | classification of ductile cast iron specimens a machine learning approach |
| topic | Ductile cast irons Graphite nodules Machine learning approach |
| url | http://www.gruppofrattura.it/pdf/rivista/numero42/numero_42_art_25.pdf |
| work_keys_str_mv | AT adesantis classificationofductilecastironspecimensamachinelearningapproach AT diacoviello classificationofductilecastironspecimensamachinelearningapproach AT vdicocco classificationofductilecastironspecimensamachinelearningapproach AT fiacoviello classificationofductilecastironspecimensamachinelearningapproach |