A hybrid transfer learning framework for in-plane freeform shape accuracy control in additive manufacturing

Abstract

Shape accuracy control is one of the quality issues of greatest concern in Additive Manufacturing (AM). An efficient approach to improving the shape accuracy of a fabricated product is to compensate the fabrication errors of AM systems by modifying the input shape defined by a digital design model. In contrast with mass production, AM processes typically fabricate customized products with extremely low volume and huge shape varieties, which makes shape accuracy control in AM a challenging problem. In this article, we propose a hybrid transfer learning framework to predict and compensate the in-plane shape deviations of new and untried freeform products based on a small number of previously fabricated products. Within this framework, the shape deviation is decomposed into a shape-independent error and a shape-specific error. A parameter-based transfer learning approach is used to facilitate a sharing of parameters for modeling the shape-independent error, whereas a feature-based transfer learning approach is taken to promote the learning of a common representation of local shape features for modeling the shape-specific error. Experimental studies of a fused filament fabrication process demonstrate the effectiveness of our proposed framework in predicting the shape deviation and improving the shape accuracy of new products with freeform shapes.

Keywords:

• Additive manufacturing
• feature transfer
• freeform shape
• functional linear model
• parameter transfer
• shape accuracy control

Acknowledgments

The authors greatly acknowledge the insightful comments provided by the editor and the three referees that have resulted in a great improvement of this article.

Additional information

Funding

This work was supported by the National Natural Science Foundation of China under Grant 71931006, 71602155; Hong Kong RGC General Research Funds under Grant 16201718 and 16203917; Hong Kong Innovation and Technology Fund Postdoctoral Hub Programme under Grant PiH/246/18; and Hong Kong Innovation and Technology Fund Project under Grant ITS/184/18FX.

Notes on contributors

Longwei Cheng

Longwei Cheng is currently a Senior Engineer in Huawei Technologies Co., Ltd., Shenzhen, China. He received his Ph.D. degree in industrial engineering and logistics management in 2018 from HKUST, Hong Kong, and his bachelor’s degree in automation in 2014 from the University of Science and Technology of China, Anhui, China. His research focuses on statistical methods for 3D printing, machine learning and database technologies.

Kai Wang

Kai Wang is currently an assistant professor in the Department of Industrial Engineering, School of Management, at the Xi’an Jiaotong University, Xi’an, China. He received his Ph.D. degree in industrial engineering and logistics management in 2018 from HKUST, Hong Kong, and his bachelor’s degree in industrial engineering in 2014 from Xi’an Jiaotong University, Shaanxi, China. His research focuses on industrial big data analytics, machine learning and transfer learning, statistical process control and monitoring.

Fugee Tsung

Fugee Tsung is a chair professor in the Department of Industrial Engineering and Decision Analytics (IEDA), Director of the Quality and Data Analytics Lab (QLab), at the Hong Kong University of Science and Technology (HKUST), Hong Kong, China. He is a Fellow of the American Society for Quality, Fellow of the American Statistical Association, Academician of the International Academy for Quality, and Fellow of the Hong Kong Institution of Engineers. He received both his M.Sc. and Ph.D. from the University of Michigan, Ann Arbor, and his B.Sc. from the National Taiwan University. His research interests include quality analytics in advanced manufacturing and service processes, industrial big data and statistical process control, monitoring, and diagnosis.