A knowledge transfer framework to support rapid process modeling in aerosol jet printing
Aerosol jet printing (AJP) technology recently gained considerable attention in an electronic manufacturing industry due to its ability to fabricate parts with fine resolution and high flexibility. However, morphology control has been identified as the main limitation of AJP process, which drastical...
| Huvudupphovsmän: | , , , |
|---|---|
| Övriga upphovsmän: | |
| Materialtyp: | Journal Article |
| Språk: | English |
| Publicerad: |
2022
|
| Ämnen: | |
| Länkar: | https://hdl.handle.net/10356/160378 |
| _version_ | 1826129160567783424 |
|---|---|
| author | Zhang, Haining Choi, Joon Phil Moon, Seung Ki Ngo, Teck Hui |
| author2 | School of Mechanical and Aerospace Engineering |
| author_facet | School of Mechanical and Aerospace Engineering Zhang, Haining Choi, Joon Phil Moon, Seung Ki Ngo, Teck Hui |
| author_sort | Zhang, Haining |
| collection | NTU |
| description | Aerosol jet printing (AJP) technology recently gained considerable attention in an electronic manufacturing industry due to its ability to fabricate parts with fine resolution and high flexibility. However, morphology control has been identified as the main limitation of AJP process, which drastically affects the electrical performance of printed components. Even though previous researches have made significant efforts in process modeling to improve the controllability of the the printed line morphology, the modeling process is still inefficient under modified operating conditions due to the repeated experiments. In this paper, a knowledge transfer framework is proposed for efficient modeling of the AJP process under varied operating conditions. The proposed framework consists of three critical steps for rapid process modeling of AJP. First, a sufficient source domain dataset at a certain operating condition is collected to develop a source model based on Gaussian process regression. Then, the representative experimental points are selected from the source domain to construct a target dataset under different operating conditions. Finally, classical knowledge transfer approaches are adopted to extract the built-in knowledge from the source model; thus, a new process model can be developed efficiently by the transferred knowledge and the representative dataset from the target domain. The validity of the proposed framework for the rapid process modeling of AJP is investigated by case study, and the limitations of the classical knowledge transfer approaches adopted in AJP are also analyzed systematically. The proposed framework is developed based on the principles of knowledge discovery, which is different from traditional process modeling approaches in AJP. Therefore, the modeling process is more systematic and cost-efficient, which will be helpful to improve the controllability of the line morphology. Additionally, due to its data-driven based characteristics, the proposed framework can be applied to other additive manufacturing technologies for process modeling researches. |
| first_indexed | 2024-10-01T07:36:11Z |
| format | Journal Article |
| id | ntu-10356/160378 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:36:11Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1603782022-07-20T05:54:25Z A knowledge transfer framework to support rapid process modeling in aerosol jet printing Zhang, Haining Choi, Joon Phil Moon, Seung Ki Ngo, Teck Hui School of Mechanical and Aerospace Engineering Engineering::Mechanical engineering Aerosol Jet Printing Knowledge Transfer Aerosol jet printing (AJP) technology recently gained considerable attention in an electronic manufacturing industry due to its ability to fabricate parts with fine resolution and high flexibility. However, morphology control has been identified as the main limitation of AJP process, which drastically affects the electrical performance of printed components. Even though previous researches have made significant efforts in process modeling to improve the controllability of the the printed line morphology, the modeling process is still inefficient under modified operating conditions due to the repeated experiments. In this paper, a knowledge transfer framework is proposed for efficient modeling of the AJP process under varied operating conditions. The proposed framework consists of three critical steps for rapid process modeling of AJP. First, a sufficient source domain dataset at a certain operating condition is collected to develop a source model based on Gaussian process regression. Then, the representative experimental points are selected from the source domain to construct a target dataset under different operating conditions. Finally, classical knowledge transfer approaches are adopted to extract the built-in knowledge from the source model; thus, a new process model can be developed efficiently by the transferred knowledge and the representative dataset from the target domain. The validity of the proposed framework for the rapid process modeling of AJP is investigated by case study, and the limitations of the classical knowledge transfer approaches adopted in AJP are also analyzed systematically. The proposed framework is developed based on the principles of knowledge discovery, which is different from traditional process modeling approaches in AJP. Therefore, the modeling process is more systematic and cost-efficient, which will be helpful to improve the controllability of the line morphology. Additionally, due to its data-driven based characteristics, the proposed framework can be applied to other additive manufacturing technologies for process modeling researches. Nanyang Technological University National Research Foundation (NRF) This research work was conducted in the SMRT-NTU Smart Urban Rail Corporate Laboratory with funding support from the National Research Foundation (NRF), SMRT and Nanyang Technological University; under the Corp Lab@University Scheme. 2022-07-20T05:54:25Z 2022-07-20T05:54:25Z 2021 Journal Article Zhang, H., Choi, J. P., Moon, S. K. & Ngo, T. H. (2021). A knowledge transfer framework to support rapid process modeling in aerosol jet printing. Advanced Engineering Informatics, 48, 101264-. https://dx.doi.org/10.1016/j.aei.2021.101264 1474-0346 https://hdl.handle.net/10356/160378 10.1016/j.aei.2021.101264 2-s2.0-85101372951 48 101264 en Advanced Engineering Informatics © 2021 Elsevier Ltd. All rights reserved. |
| spellingShingle | Engineering::Mechanical engineering Aerosol Jet Printing Knowledge Transfer Zhang, Haining Choi, Joon Phil Moon, Seung Ki Ngo, Teck Hui A knowledge transfer framework to support rapid process modeling in aerosol jet printing |
| title | A knowledge transfer framework to support rapid process modeling in aerosol jet printing |
| title_full | A knowledge transfer framework to support rapid process modeling in aerosol jet printing |
| title_fullStr | A knowledge transfer framework to support rapid process modeling in aerosol jet printing |
| title_full_unstemmed | A knowledge transfer framework to support rapid process modeling in aerosol jet printing |
| title_short | A knowledge transfer framework to support rapid process modeling in aerosol jet printing |
| title_sort | knowledge transfer framework to support rapid process modeling in aerosol jet printing |
| topic | Engineering::Mechanical engineering Aerosol Jet Printing Knowledge Transfer |
| url | https://hdl.handle.net/10356/160378 |
| work_keys_str_mv | AT zhanghaining aknowledgetransferframeworktosupportrapidprocessmodelinginaerosoljetprinting AT choijoonphil aknowledgetransferframeworktosupportrapidprocessmodelinginaerosoljetprinting AT moonseungki aknowledgetransferframeworktosupportrapidprocessmodelinginaerosoljetprinting AT ngoteckhui aknowledgetransferframeworktosupportrapidprocessmodelinginaerosoljetprinting AT zhanghaining knowledgetransferframeworktosupportrapidprocessmodelinginaerosoljetprinting AT choijoonphil knowledgetransferframeworktosupportrapidprocessmodelinginaerosoljetprinting AT moonseungki knowledgetransferframeworktosupportrapidprocessmodelinginaerosoljetprinting AT ngoteckhui knowledgetransferframeworktosupportrapidprocessmodelinginaerosoljetprinting |