Application of Machine Learning Techniques to Predict the Mechanical Properties of Polyamide 2200 (PA12) in Additive Manufacturing

Abstract

Additive manufacturing (AM) is an attractive technology for the manufacturing industry due to flexibility in its design and functionality, but inconsistency in quality is one of the major limitations preventing utilizing this technology for the production of end-use parts. The prediction of mechanical properties can be one of the possible ways to improve the repeatability of results. The part placement, part orientation, and STL model properties (number of mesh triangles, surface, and volume) are used to predict tensile modulus, nominal stress, and elongation at break for polyamide 2200 (also known as PA12). An EOS P395 polymer powder bed fusion system was used to fabricate 217 specimens in two identical builds (434 specimens in total). Prediction is performed for XYZ, XZY, ZYX, and Angle orientations separately, and all orientations together. The different non-linear models based on machine learning methods have higher prediction accuracy compared with linear regression models. Linear regression models only have prediction accuracy higher than 80% for Tensile Modulus and Elongation at break in Angle orientation. Since orientation-based modeling has low prediction accuracy due to a small number of data points and lack of information about the material properties, these models need to be improved in the future based on additional experimental work.

Development and Optimization of Medical-Grade Multi-Functional Polyamide 12-Cuprous Oxide Nanocomposites with Superior Mechanical and Antibacterial Properties for Cost-Effective 3D Printing

“…Polyamides are well-known polymers and are widely used in engineering applications. A polyamide used so far, mainly in selective laser sintering (SLS) and binder jet technologies of AM, is polyamide 12 (PA12) [ 29 , 43 ] PA12 is a material that can be employed in many implementations due to its thermomechanical properties. It is not widely used in MEX implementations yet, with its filament market share being significantly lower than other materials [ 44 ].…”

A comparative study of machine learning in predicting the mechanical properties of the deposited AA6061 alloys via additive friction stir deposition

“…Baturynska et al. successfully predicted the tensile modules and nominal stress of polymer powder bed fusion through the Gradient boosting regressor, Decision tree regressor and AdaBoost regressor [13] . Meanwhile, Zhan and the co‐workers found that random forest (RF) exhibited the highest accuracy to predict the fatigue life of printed stainless steel 316L, compared to artificial neural network (ANN) and support vector machine (SVM) methods [14] .…”

Trilateral Multi-Functional Polyamide 12 Nanocomposites with Binary Inclusions for Medical Grade Material Extrusion 3D Printing: The Effect of Titanium Nitride in Mechanical Reinforcement and Copper/Cuprous Oxide as Antibacterial Agents

“…Polyamide 12 (PA12) is a popular polyamide, due to its enhanced thermal and mechanical response [ 8 ]. This specific grade has been investigated and applied in different additive manufacturing (AM) processes, such as binder jetting [ 9 ], powder bed fusion [ 10 , 11 ], and material extrusion (MEX) as pure material, or as the matrix material in composites [ 5 , 8 , 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 , 20 , 21 ]. PA12 is a material suitable for the 3D printing (3DP) process, due to its rheological characteristics [ 22 ], its toughness, and high strain values before its failure [ 10 , 23 , 24 , 25 ].…”