Prediction of Both E-Jet Printing Ejection Cycle Time and Droplet Diameter Based on Random Forest Regression
Electrohydrodynamic jet (E-jet) printing has broad application prospects in the preparation of flexible electronics and optical devices. Ejection cycle time and droplet size are two key factors affecting E-jet-printing quality, but due to the complex process of E-jet printing, it remains a challenge...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Micromachines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-666X/14/3/623 |
| _version_ | 1797610075242627072 |
|---|---|
| author | Yuanfen Chen Zongkun Lao Renzhi Wang Jinwei Li Jingyao Gai Hui You |
| author_facet | Yuanfen Chen Zongkun Lao Renzhi Wang Jinwei Li Jingyao Gai Hui You |
| author_sort | Yuanfen Chen |
| collection | DOAJ |
| description | Electrohydrodynamic jet (E-jet) printing has broad application prospects in the preparation of flexible electronics and optical devices. Ejection cycle time and droplet size are two key factors affecting E-jet-printing quality, but due to the complex process of E-jet printing, it remains a challenge to establish accurate relationships among ejection cycle time and droplet diameter and printing parameters. This paper develops a model based on random forest regression (RFR) for E-jet-printing prediction. Trained with 72 groups of experimental data obtained under four printing parameters (voltage, nozzle-to-substrate distance, liquid viscosity, and liquid conductivity), the RFR model achieved a MAPE (mean absolute percent error) of 4.35% and an RMSE (root mean square error) of 0.04 ms for eject cycle prediction, as well as a MAPE of 2.89% and an RMSE of 0.96 μm for droplet diameter prediction. With limited training data, the RFR model achieved the best prediction accuracy among several machine-learning models (RFR, CART, SVR, and ANN). The proposed prediction model provides an efficient and effective way to simultaneously predict the ejection cycle time and droplet diameter, advancing E-jet printing toward the goal of accurate, drop-on-demand printing. |
| first_indexed | 2024-03-11T06:09:23Z |
| format | Article |
| id | doaj.art-882e7550e3c3450481acd79761a48131 |
| institution | Directory Open Access Journal |
| issn | 2072-666X |
| language | English |
| last_indexed | 2024-03-11T06:09:23Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Micromachines |
| spelling | doaj.art-882e7550e3c3450481acd79761a481312023-11-17T12:43:24ZengMDPI AGMicromachines2072-666X2023-03-0114362310.3390/mi14030623Prediction of Both E-Jet Printing Ejection Cycle Time and Droplet Diameter Based on Random Forest RegressionYuanfen Chen0Zongkun Lao1Renzhi Wang2Jinwei Li3Jingyao Gai4Hui You5School of Mechanical Engineering, Guangxi University, Nanning 530004, ChinaSchool of Mechanical Engineering, Guangxi University, Nanning 530004, ChinaSchool of Mechanical Engineering, Guangxi University, Nanning 530004, ChinaSchool of Mechanical Engineering, Guangxi University, Nanning 530004, ChinaSchool of Mechanical Engineering, Guangxi University, Nanning 530004, ChinaSchool of Mechanical Engineering, Guangxi University, Nanning 530004, ChinaElectrohydrodynamic jet (E-jet) printing has broad application prospects in the preparation of flexible electronics and optical devices. Ejection cycle time and droplet size are two key factors affecting E-jet-printing quality, but due to the complex process of E-jet printing, it remains a challenge to establish accurate relationships among ejection cycle time and droplet diameter and printing parameters. This paper develops a model based on random forest regression (RFR) for E-jet-printing prediction. Trained with 72 groups of experimental data obtained under four printing parameters (voltage, nozzle-to-substrate distance, liquid viscosity, and liquid conductivity), the RFR model achieved a MAPE (mean absolute percent error) of 4.35% and an RMSE (root mean square error) of 0.04 ms for eject cycle prediction, as well as a MAPE of 2.89% and an RMSE of 0.96 μm for droplet diameter prediction. With limited training data, the RFR model achieved the best prediction accuracy among several machine-learning models (RFR, CART, SVR, and ANN). The proposed prediction model provides an efficient and effective way to simultaneously predict the ejection cycle time and droplet diameter, advancing E-jet printing toward the goal of accurate, drop-on-demand printing.https://www.mdpi.com/2072-666X/14/3/623e-jet printingejection cycle time predictiondroplet diameter predictionrandom forest regression |
| spellingShingle | Yuanfen Chen Zongkun Lao Renzhi Wang Jinwei Li Jingyao Gai Hui You Prediction of Both E-Jet Printing Ejection Cycle Time and Droplet Diameter Based on Random Forest Regression Micromachines e-jet printing ejection cycle time prediction droplet diameter prediction random forest regression |
| title | Prediction of Both E-Jet Printing Ejection Cycle Time and Droplet Diameter Based on Random Forest Regression |
| title_full | Prediction of Both E-Jet Printing Ejection Cycle Time and Droplet Diameter Based on Random Forest Regression |
| title_fullStr | Prediction of Both E-Jet Printing Ejection Cycle Time and Droplet Diameter Based on Random Forest Regression |
| title_full_unstemmed | Prediction of Both E-Jet Printing Ejection Cycle Time and Droplet Diameter Based on Random Forest Regression |
| title_short | Prediction of Both E-Jet Printing Ejection Cycle Time and Droplet Diameter Based on Random Forest Regression |
| title_sort | prediction of both e jet printing ejection cycle time and droplet diameter based on random forest regression |
| topic | e-jet printing ejection cycle time prediction droplet diameter prediction random forest regression |
| url | https://www.mdpi.com/2072-666X/14/3/623 |
| work_keys_str_mv | AT yuanfenchen predictionofbothejetprintingejectioncycletimeanddropletdiameterbasedonrandomforestregression AT zongkunlao predictionofbothejetprintingejectioncycletimeanddropletdiameterbasedonrandomforestregression AT renzhiwang predictionofbothejetprintingejectioncycletimeanddropletdiameterbasedonrandomforestregression AT jinweili predictionofbothejetprintingejectioncycletimeanddropletdiameterbasedonrandomforestregression AT jingyaogai predictionofbothejetprintingejectioncycletimeanddropletdiameterbasedonrandomforestregression AT huiyou predictionofbothejetprintingejectioncycletimeanddropletdiameterbasedonrandomforestregression |