Hardness and Surface Roughness of 3D-Printed ASA Components Subjected to Acetone Vapor Treatment and Different...

Area of Science:

• Materials Science
• Additive Manufacturing
• Machine Learning

Background:

• Acrylonitrile styrene acrylate (ASA) is a high-performance thermoplastic suitable for outdoor applications, requiring excellent hardness and surface finish.
• Post-processing is crucial for 3D-printed ASA components to meet aesthetic and performance demands.
• Optimizing 3D printing parameters and post-treatment is essential for enhancing ASA material properties.

Purpose of the Study:

• To investigate the combined effects of acetone vapor treatment and 3D printing parameters on ASA hardness and surface roughness.
• To apply machine learning (ML) and deep learning (DL) strategies for predicting these properties.
• To identify optimal processing conditions for superior ASA component performance.

Main Methods:

• Experimental analysis of ASA components subjected to varying acetone vapor durations (15-120 min), layer thicknesses (0.1-0.4 mm), and infill rates (25-100%).
• Implementation of multiple ML/DL models, including Support Vector Regressor (SVR), Gradient Boosting (GB), Recurrent Neural Networks (RNNs), and 1D Convolutional Neural Networks (1D-CNNs).
• Comparative evaluation of model predictive accuracy for hardness and surface roughness.

Main Results:

• The combination of SVR and 1D-CNNs demonstrated the highest prediction accuracy for ASA hardness and surface roughness.
• Gradient Boosting (GB) and Recurrent Neural Networks (RNNs) also provided reliable, low-error forecasts.
• Optimal hardness was achieved at 45 minutes of acetone vapor treatment, with a positive correlation observed between layer thickness/infill rate and Shore D hardness.

Conclusions:

• Machine learning, particularly SVR with 1D-CNNs, is effective for optimizing ASA 3D printing and post-processing.
• Acetone vapor treatment duration is a critical factor, with 45 minutes yielding peak hardness.
• The study provides a data-driven approach to enhance the mechanical and surface properties of 3D-printed ASA for demanding applications.