Assessment of the Critical Defect in Additive Manufacturing Components through Machine Learning Algorithms
The design against fatigue failures of Additively Manufactured (AM) components is a fundamental research topic for industries and universities. The fatigue response of AM parts is driven by manufacturing defects, which contribute to the experimental scatter and are strongly dependent on the process...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/7/4294 |
| _version_ | 1827747056421175296 |
|---|---|
| author | Andrea Tridello Alberto Ciampaglia Filippo Berto Davide Salvatore Paolino |
| author_facet | Andrea Tridello Alberto Ciampaglia Filippo Berto Davide Salvatore Paolino |
| author_sort | Andrea Tridello |
| collection | DOAJ |
| description | The design against fatigue failures of Additively Manufactured (AM) components is a fundamental research topic for industries and universities. The fatigue response of AM parts is driven by manufacturing defects, which contribute to the experimental scatter and are strongly dependent on the process parameters, making the design process rather complex. The most effective design procedure would involve the assessment of the defect population and the defect size distribution directly from the process parameters. However, the number of process parameters is wide and the assessment of a direct relationship between them and the defect population would require an unfeasible number of expensive experimental tests. These multivariate problems can be effectively managed by Machine Learning (ML) algorithms. In this paper, two ML algorithms for assessing the most critical defect in parts produced by means of the Selective Laser Melting (SLM) process are developed. The probability of a defect with a specific size and the location and scale parameters of the statistical distribution of the defect size, assumed to follow a Largest Extreme Value Distribution, are estimated directly from the SLM process parameters. Both approaches have been validated using literature data obtained by testing the AlSi10Mg and the Ti6Al4V alloy, proving their effectiveness and predicting capability. |
| first_indexed | 2024-03-11T05:42:47Z |
| format | Article |
| id | doaj.art-4f78e79404304d33a177d946fad85adf |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T05:42:47Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-4f78e79404304d33a177d946fad85adf2023-11-17T16:18:18ZengMDPI AGApplied Sciences2076-34172023-03-01137429410.3390/app13074294Assessment of the Critical Defect in Additive Manufacturing Components through Machine Learning AlgorithmsAndrea Tridello0Alberto Ciampaglia1Filippo Berto2Davide Salvatore Paolino3Department of Mechanical and Aerospace Engineering, Politecnico di Torino, 10129 Turin, ItalyDepartment of Mechanical and Aerospace Engineering, Politecnico di Torino, 10129 Turin, ItalyDepartment of Chemical Engineering Materials Environment, Sapienza—Università Di Roma, 00184 Rome, ItalyDepartment of Mechanical and Aerospace Engineering, Politecnico di Torino, 10129 Turin, ItalyThe design against fatigue failures of Additively Manufactured (AM) components is a fundamental research topic for industries and universities. The fatigue response of AM parts is driven by manufacturing defects, which contribute to the experimental scatter and are strongly dependent on the process parameters, making the design process rather complex. The most effective design procedure would involve the assessment of the defect population and the defect size distribution directly from the process parameters. However, the number of process parameters is wide and the assessment of a direct relationship between them and the defect population would require an unfeasible number of expensive experimental tests. These multivariate problems can be effectively managed by Machine Learning (ML) algorithms. In this paper, two ML algorithms for assessing the most critical defect in parts produced by means of the Selective Laser Melting (SLM) process are developed. The probability of a defect with a specific size and the location and scale parameters of the statistical distribution of the defect size, assumed to follow a Largest Extreme Value Distribution, are estimated directly from the SLM process parameters. Both approaches have been validated using literature data obtained by testing the AlSi10Mg and the Ti6Al4V alloy, proving their effectiveness and predicting capability.https://www.mdpi.com/2076-3417/13/7/4294machine learningsupervised feed-forward neural networks (FFNNs)fatigue designAdditive ManufacturingAlSi10Mg alloyTi6Al4V alloy |
| spellingShingle | Andrea Tridello Alberto Ciampaglia Filippo Berto Davide Salvatore Paolino Assessment of the Critical Defect in Additive Manufacturing Components through Machine Learning Algorithms Applied Sciences machine learning supervised feed-forward neural networks (FFNNs) fatigue design Additive Manufacturing AlSi10Mg alloy Ti6Al4V alloy |
| title | Assessment of the Critical Defect in Additive Manufacturing Components through Machine Learning Algorithms |
| title_full | Assessment of the Critical Defect in Additive Manufacturing Components through Machine Learning Algorithms |
| title_fullStr | Assessment of the Critical Defect in Additive Manufacturing Components through Machine Learning Algorithms |
| title_full_unstemmed | Assessment of the Critical Defect in Additive Manufacturing Components through Machine Learning Algorithms |
| title_short | Assessment of the Critical Defect in Additive Manufacturing Components through Machine Learning Algorithms |
| title_sort | assessment of the critical defect in additive manufacturing components through machine learning algorithms |
| topic | machine learning supervised feed-forward neural networks (FFNNs) fatigue design Additive Manufacturing AlSi10Mg alloy Ti6Al4V alloy |
| url | https://www.mdpi.com/2076-3417/13/7/4294 |
| work_keys_str_mv | AT andreatridello assessmentofthecriticaldefectinadditivemanufacturingcomponentsthroughmachinelearningalgorithms AT albertociampaglia assessmentofthecriticaldefectinadditivemanufacturingcomponentsthroughmachinelearningalgorithms AT filippoberto assessmentofthecriticaldefectinadditivemanufacturingcomponentsthroughmachinelearningalgorithms AT davidesalvatorepaolino assessmentofthecriticaldefectinadditivemanufacturingcomponentsthroughmachinelearningalgorithms |