Deep learning based porosity prediction for additively manufactured laser powder-bed fusion parts
Machine learning techniques are extensively used to understand and predict complex non-linear phenomena across various applications. Moreover, these techniques minimize the time and costs associated with experimental and numerical analysis. In this work, a deep learning technique, specifically artif...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-11-01
|
| Series: | Journal of Materials Research and Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2238785423028090 |
| _version_ | 1797301467644690432 |
|---|---|
| author | Anwaruddin Siddiqui Mohammed Mosa Almutahhar Karim Sattar Ali Alhajeri Aamer Nazir Usman Ali |
| author_facet | Anwaruddin Siddiqui Mohammed Mosa Almutahhar Karim Sattar Ali Alhajeri Aamer Nazir Usman Ali |
| author_sort | Anwaruddin Siddiqui Mohammed |
| collection | DOAJ |
| description | Machine learning techniques are extensively used to understand and predict complex non-linear phenomena across various applications. Moreover, these techniques minimize the time and costs associated with experimental and numerical analysis. In this work, a deep learning technique, specifically artificial neural networks (ANN), was employed to predict the density/porosity of laser powder-bed fusion (LPBF) additively manufactured (AM) parts by training the ANN model with X-ray computed tomography (CT) images. In addition to the experimental data, synthetic CT data was generated and used to improve the performance of the ANN model. The ANN model was then optimized for the number of hidden layers and neurons. Different errors like mean absolute error (MAE), root mean square error (RMSE), and square of co-relation coefficient (R2) were used as performance metrics to determine the accuracy and effectiveness of the network. The proposed ANN model was validated and showed excellent predictions (R2 = 0.9981, MAE = 1.6944 x 10−5). The framework proposed in this work can be used to speed-up the quality assurance of AM parts by reducing the time required for the analysis of CT data. |
| first_indexed | 2024-03-07T23:23:00Z |
| format | Article |
| id | doaj.art-8b29d3ed2fc845ca9b2fe30a779f8a5f |
| institution | Directory Open Access Journal |
| issn | 2238-7854 |
| language | English |
| last_indexed | 2024-03-07T23:23:00Z |
| publishDate | 2023-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Materials Research and Technology |
| spelling | doaj.art-8b29d3ed2fc845ca9b2fe30a779f8a5f2024-02-21T05:27:35ZengElsevierJournal of Materials Research and Technology2238-78542023-11-012773307335Deep learning based porosity prediction for additively manufactured laser powder-bed fusion partsAnwaruddin Siddiqui Mohammed0Mosa Almutahhar1Karim Sattar2Ali Alhajeri3Aamer Nazir4Usman Ali5Department of Mechanical Engineering, King Fahd University of Petroleum & Minerals, Dhahran, 31261, Saudi ArabiaDepartment of Mechanical Engineering, King Fahd University of Petroleum & Minerals, Dhahran, 31261, Saudi ArabiaInterdisciplinary Research Center for Smart Mobility and Logistics, King Fahd University of Petroleum & Minerals, Dhahran, 31261, Saudi ArabiaDepartment of Mechanical Engineering, King Fahd University of Petroleum & Minerals, Dhahran, 31261, Saudi ArabiaDepartment of Mechanical Engineering, King Fahd University of Petroleum & Minerals, Dhahran, 31261, Saudi Arabia; Interdisciplinary Research Center on Advanced Materials, King Fahd University of Petroleum & Minerals, Dhahran, 31261, Saudi ArabiaDepartment of Mechanical Engineering, King Fahd University of Petroleum & Minerals, Dhahran, 31261, Saudi Arabia; Interdisciplinary Research Center on Advanced Materials, King Fahd University of Petroleum & Minerals, Dhahran, 31261, Saudi Arabia; K.A. CARE Energy Research & Innovation Center at Dhahran, Saudi Arabia; Corresponding author. Department of Mechanical Engineering, King Fahd University of Petroleum & Minerals, Dhahran, 31261, Saudi Arabia.Machine learning techniques are extensively used to understand and predict complex non-linear phenomena across various applications. Moreover, these techniques minimize the time and costs associated with experimental and numerical analysis. In this work, a deep learning technique, specifically artificial neural networks (ANN), was employed to predict the density/porosity of laser powder-bed fusion (LPBF) additively manufactured (AM) parts by training the ANN model with X-ray computed tomography (CT) images. In addition to the experimental data, synthetic CT data was generated and used to improve the performance of the ANN model. The ANN model was then optimized for the number of hidden layers and neurons. Different errors like mean absolute error (MAE), root mean square error (RMSE), and square of co-relation coefficient (R2) were used as performance metrics to determine the accuracy and effectiveness of the network. The proposed ANN model was validated and showed excellent predictions (R2 = 0.9981, MAE = 1.6944 x 10−5). The framework proposed in this work can be used to speed-up the quality assurance of AM parts by reducing the time required for the analysis of CT data.http://www.sciencedirect.com/science/article/pii/S2238785423028090X-ray computed tomographyPorosityArtificial neural networkMachine learning |
| spellingShingle | Anwaruddin Siddiqui Mohammed Mosa Almutahhar Karim Sattar Ali Alhajeri Aamer Nazir Usman Ali Deep learning based porosity prediction for additively manufactured laser powder-bed fusion parts Journal of Materials Research and Technology X-ray computed tomography Porosity Artificial neural network Machine learning |
| title | Deep learning based porosity prediction for additively manufactured laser powder-bed fusion parts |
| title_full | Deep learning based porosity prediction for additively manufactured laser powder-bed fusion parts |
| title_fullStr | Deep learning based porosity prediction for additively manufactured laser powder-bed fusion parts |
| title_full_unstemmed | Deep learning based porosity prediction for additively manufactured laser powder-bed fusion parts |
| title_short | Deep learning based porosity prediction for additively manufactured laser powder-bed fusion parts |
| title_sort | deep learning based porosity prediction for additively manufactured laser powder bed fusion parts |
| topic | X-ray computed tomography Porosity Artificial neural network Machine learning |
| url | http://www.sciencedirect.com/science/article/pii/S2238785423028090 |
| work_keys_str_mv | AT anwaruddinsiddiquimohammed deeplearningbasedporositypredictionforadditivelymanufacturedlaserpowderbedfusionparts AT mosaalmutahhar deeplearningbasedporositypredictionforadditivelymanufacturedlaserpowderbedfusionparts AT karimsattar deeplearningbasedporositypredictionforadditivelymanufacturedlaserpowderbedfusionparts AT alialhajeri deeplearningbasedporositypredictionforadditivelymanufacturedlaserpowderbedfusionparts AT aamernazir deeplearningbasedporositypredictionforadditivelymanufacturedlaserpowderbedfusionparts AT usmanali deeplearningbasedporositypredictionforadditivelymanufacturedlaserpowderbedfusionparts |