Investigation and prediction of crystallization of PA12 in multi jet fusion process using regression model

• Main Author: Foo, Yuan Ru
• Other Authors: Du Hejun
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2021
• Subjects: Engineering::Mechanical engineering
• Online Access: https://hdl.handle.net/10356/150917
• Institution: Nanyang Technological University

The growing popularity of additive manufacturing has ignited the possibility of mass manufacturing. This has led to special attention in polymer powder bed fusion technologies such multi jet fusion (MJF). This report analyses the material properties of Polyamide 12 (PA12) powders and printed dogbone samples using MJF technologies. The point is identified where a small amount of specimen would be cut from to conduct numerous Differential Scanning Calorimetry (DSC) tests that measures the degree of crystallinity value of each sample. Three different regression models are then developed using the crystallinity data obtained from the DSC tests and have their accuracy compared with parameters such as the coefficient of determination, mean and maximum error. The results showed that the Lasso regression model was the best but still had certain limitations in its predictive accuracy. This report details the investigation of how crystallinity degree can be predicted within the MJF print chamber using regression models. It includes the experiment process, results obtained and development process of the regression model.