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: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/165625 |
| _version_ | 1811690007532929024 |
|---|---|
| author | Chen, Chengxi Wong, Stanley Jian Liang Raghavan, Srinivasan Li, Hua |
| author2 | School of Mechanical and Aerospace Engineering |
| author_facet | School of Mechanical and Aerospace Engineering Chen, Chengxi Wong, Stanley Jian Liang Raghavan, Srinivasan Li, Hua |
| author_sort | Chen, Chengxi |
| collection | NTU |
| 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 | 2024-10-01T05:57:09Z |
| format | Journal Article |
| id | ntu-10356/165625 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:57:09Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1656252023-04-05T15:37:23Z Design of experiments informed deep learning for modeling of directed energy deposition process with a small-size experimental dataset Chen, Chengxi Wong, Stanley Jian Liang Raghavan, Srinivasan Li, Hua School of Mechanical and Aerospace Engineering Singapore Centre for 3D Printing Engineering::Mechanical engineering Directed Energy Deposition Single-Track Deposition 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. Economic Development Board (EDB) National Research Foundation (NRF) Published version This research is supported by Makino Asia Pte Ltd through the Economic Development Board Industrial Postgraduate Programme and the National Research Foundation, Prime Minister’s Office, Singapore under its Medium-Sized Centre funding scheme. 2023-04-04T06:37:50Z 2023-04-04T06:37:50Z 2022 Journal Article Chen, C., Wong, S. J. L., Raghavan, S. & Li, H. (2022). Design of experiments informed deep learning for modeling of directed energy deposition process with a small-size experimental dataset. Materials and Design, 222, 111098-. https://dx.doi.org/10.1016/j.matdes.2022.111098 0264-1275 https://hdl.handle.net/10356/165625 10.1016/j.matdes.2022.111098 2-s2.0-85137158529 222 111098 en Materials and Design © 2022 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). application/pdf |
| spellingShingle | Engineering::Mechanical engineering Directed Energy Deposition Single-Track Deposition Chen, Chengxi Wong, Stanley Jian Liang Raghavan, Srinivasan Li, Hua Design of experiments informed deep learning for modeling of directed energy deposition process with a small-size experimental dataset |
| 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 | Engineering::Mechanical engineering Directed Energy Deposition Single-Track Deposition |
| url | https://hdl.handle.net/10356/165625 |
| work_keys_str_mv | AT chenchengxi designofexperimentsinformeddeeplearningformodelingofdirectedenergydepositionprocesswithasmallsizeexperimentaldataset AT wongstanleyjianliang designofexperimentsinformeddeeplearningformodelingofdirectedenergydepositionprocesswithasmallsizeexperimentaldataset AT raghavansrinivasan designofexperimentsinformeddeeplearningformodelingofdirectedenergydepositionprocesswithasmallsizeexperimentaldataset AT lihua designofexperimentsinformeddeeplearningformodelingofdirectedenergydepositionprocesswithasmallsizeexperimentaldataset |