Design of experiments informed deep learning for modeling of directed energy deposition process with a small-size experimental dataset
In order to address the high throughput data generation challenges in the directed energy deposition (DED) process development, a design of experiments (DOE) informed deep learning (DL) model is developed for modeling of laser powder-based DED process. A small-size experimental dataset is obtained a...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-10-01
|
| Series: | Materials & Design |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0264127522007201 |
| _version_ | 1811180828318760960 |
|---|---|
| author | Chengxi Chen Stanley Jian Liang Wong Srinivasan Raghavan Hua Li |
| author_facet | Chengxi Chen Stanley Jian Liang Wong Srinivasan Raghavan Hua Li |
| author_sort | Chengxi Chen |
| collection | DOAJ |
| description | In order to address the high throughput data generation challenges in the directed energy deposition (DED) process development, a design of experiments (DOE) informed deep learning (DL) model is developed for modeling of laser powder-based DED process. A small-size experimental dataset is obtained according to DOE, by which a large-size dataset is augmented via the DOE regression model and then used to pre-train the DL model. A subset of experimental data is employed to fine-tune the DL model. The presently developed DOE-informed DL model is validated via single-track deposition of stainless steel 316L, in which the cross-section dilution shape (including depth) and the geometrical characteristics of beads, including the width, height, area, and wetting angle are predicted accurately. The prediction of the porosity and hardness are acceptable for single-track deposition, since variations of both the experimental porosity (from 0.04 % to 0.30 %) and hardness (from 168 HV to 182 HV) are quite small for the single-track deposition, especially predicted ranges for the porosity (from 0.05 % to 0.25 %) and hardness (from 170 HV to 180 HV) are the subset of the experimental results.The DOE-informed DL model developed in this study is based on a single-track deposition dataset; in future work, the DOE-informed DL model will be extended to multi-layer deposition. |
| first_indexed | 2024-04-11T09:09:54Z |
| format | Article |
| id | doaj.art-e59d3f1a01914e589b6cba4fa7c98d96 |
| institution | Directory Open Access Journal |
| issn | 0264-1275 |
| language | English |
| last_indexed | 2024-04-11T09:09:54Z |
| publishDate | 2022-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Materials & Design |
| spelling | doaj.art-e59d3f1a01914e589b6cba4fa7c98d962022-12-22T04:32:32ZengElsevierMaterials & Design0264-12752022-10-01222111098Design of experiments informed deep learning for modeling of directed energy deposition process with a small-size experimental datasetChengxi Chen0Stanley Jian Liang Wong1Srinivasan Raghavan2Hua Li3Singapore Centre for 3D Printing, School of Mechanical and Aerospace Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798, Republic of Singapore; Makino Asia Pte Ltd, 2 Gul Avenue, Singapore 629649, Republic of SingaporeSingapore Centre for 3D Printing, School of Mechanical and Aerospace Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798, Republic of Singapore; Makino Asia Pte Ltd, 2 Gul Avenue, Singapore 629649, Republic of SingaporeMakino Asia Pte Ltd, 2 Gul Avenue, Singapore 629649, Republic of SingaporeSingapore Centre for 3D Printing, School of Mechanical and Aerospace Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798, Republic of Singapore; Corresponding author.In order to address the high throughput data generation challenges in the directed energy deposition (DED) process development, a design of experiments (DOE) informed deep learning (DL) model is developed for modeling of laser powder-based DED process. A small-size experimental dataset is obtained according to DOE, by which a large-size dataset is augmented via the DOE regression model and then used to pre-train the DL model. A subset of experimental data is employed to fine-tune the DL model. The presently developed DOE-informed DL model is validated via single-track deposition of stainless steel 316L, in which the cross-section dilution shape (including depth) and the geometrical characteristics of beads, including the width, height, area, and wetting angle are predicted accurately. The prediction of the porosity and hardness are acceptable for single-track deposition, since variations of both the experimental porosity (from 0.04 % to 0.30 %) and hardness (from 168 HV to 182 HV) are quite small for the single-track deposition, especially predicted ranges for the porosity (from 0.05 % to 0.25 %) and hardness (from 170 HV to 180 HV) are the subset of the experimental results.The DOE-informed DL model developed in this study is based on a single-track deposition dataset; in future work, the DOE-informed DL model will be extended to multi-layer deposition.http://www.sciencedirect.com/science/article/pii/S0264127522007201Design of experiments informed deep learningSmall-size experimental datasetDirected energy depositionSingle-track depositionGeometrical characteristics |
| spellingShingle | Chengxi Chen Stanley Jian Liang Wong Srinivasan Raghavan Hua Li Design of experiments informed deep learning for modeling of directed energy deposition process with a small-size experimental dataset Materials & Design Design of experiments informed deep learning Small-size experimental dataset Directed energy deposition Single-track deposition Geometrical characteristics |
| title | Design of experiments informed deep learning for modeling of directed energy deposition process with a small-size experimental dataset |
| title_full | Design of experiments informed deep learning for modeling of directed energy deposition process with a small-size experimental dataset |
| title_fullStr | Design of experiments informed deep learning for modeling of directed energy deposition process with a small-size experimental dataset |
| title_full_unstemmed | Design of experiments informed deep learning for modeling of directed energy deposition process with a small-size experimental dataset |
| title_short | Design of experiments informed deep learning for modeling of directed energy deposition process with a small-size experimental dataset |
| title_sort | design of experiments informed deep learning for modeling of directed energy deposition process with a small size experimental dataset |
| topic | Design of experiments informed deep learning Small-size experimental dataset Directed energy deposition Single-track deposition Geometrical characteristics |
| url | http://www.sciencedirect.com/science/article/pii/S0264127522007201 |
| work_keys_str_mv | AT chengxichen designofexperimentsinformeddeeplearningformodelingofdirectedenergydepositionprocesswithasmallsizeexperimentaldataset AT stanleyjianliangwong designofexperimentsinformeddeeplearningformodelingofdirectedenergydepositionprocesswithasmallsizeexperimentaldataset AT srinivasanraghavan designofexperimentsinformeddeeplearningformodelingofdirectedenergydepositionprocesswithasmallsizeexperimentaldataset AT huali designofexperimentsinformeddeeplearningformodelingofdirectedenergydepositionprocesswithasmallsizeexperimentaldataset |