Surface quality prediction and quantitative evaluation of process parameter effects for 3D printing with transfer learning-enhanced gradient-boosting decision trees

Zhu，Jianjian1,2; Su，Zhongqing1,2; Wang，Qingqing1,3; Lan，Zifeng4; Siu-fai Chan，Frankie5; Han，Zhibin6; Wang，Zhaokun1; Wing-fai Wong，Sidney5; Chi-fung Ngan，Andy5

2024-03-01

10.1016/j.eswa.2023.121478

Expert Systems with Applications   影响因子和分区

0957-4174

3D printing has the potential to revolutionize industrial manufacturing through efficient and sustainable techniques. Fused Deposition Modeling (FDM) is a broadly deployed technique among various 3D printing methods. However, the surface quality of FDM is greatly influenced by multiple factors, making it challenging to unravel the relationship between printing quality and parameter settings. To break through this bottleneck, this study proposes an intelligent approach that combines Transfer Learning (TL)-based Feature Extractor (FE) and Gradient-Boosting Decision Trees (GBDT) to investigate the effects of FDM printing parameters on surface quality. Experiments are conducted in the laboratory to validate the effectiveness of the FE-GBDT, which is then compared with the exemplary Machine Learning (ML) algorithms. The results show that our proposed TL model can achieve high precision and accuracy over 0.9900, demonstrating the efficacy of FE-GBDT in deciphering the impact of FDM printing parameters on surface quality. The contribution of each parameter is evaluated and indicates that layer height could dramatically affect the surface quality with an importance score of 0.626. The results provide valuable insights for the 3D printing community, proving that the FE-GBDT approach offers improved generalization, faster training, enhanced feature extraction, addressing data scarcity, and the ability to leverage the strengths of both approaches for superior performance across various tasks.

3D printing Fused deposition modeling Gradient-boosting decision trees Process parameters Surface quality Transfer learning

SCI ; EI

英语

其他

ENGINEERING

2-s2.0-85172012234

Scopus

1.Department of Mechanical Engineering,The Hong Kong Polytechnic University,Kowloon, Hong Kong S.A.R,Hong Kong
2.The Hong Kong Polytechnic University Shenzhen Research Institute,Shenzhen,518057,China
3.School of System Design and Intelligent Manufacturing,Southern University of Science and Technology,Shenzhen,518055,China
4.School of Engineering,The University of Tokyo,Tokyo,Japan
5.Industrial Center,The Hong Kong Polytechnic University,Kowloon, Hong Kong S.A.R,Hong Kong
6.Department of Mechanical and Automation Engineering,The Chinese University of Hong Kong,Hong Kong S.A.R,Hong Kong

Zhu，Jianjian,Su，Zhongqing,Wang，Qingqing,et al. Surface quality prediction and quantitative evaluation of process parameter effects for 3D printing with transfer learning-enhanced gradient-boosting decision trees[J]. Expert Systems with Applications,2024,237.

Zhu，Jianjian.,Su，Zhongqing.,Wang，Qingqing.,Lan，Zifeng.,Siu-fai Chan，Frankie.,...&Chi-fung Ngan，Andy.(2024).Surface quality prediction and quantitative evaluation of process parameter effects for 3D printing with transfer learning-enhanced gradient-boosting decision trees.Expert Systems with Applications,237.

Zhu，Jianjian,et al."Surface quality prediction and quantitative evaluation of process parameter effects for 3D printing with transfer learning-enhanced gradient-boosting decision trees".Expert Systems with Applications 237(2024).