Machine Learning-Enabled Optimization and Prediction of Mechanical Properties of 3D-Printed PLA Composites Filled...

Area of Science:

• Materials Science
• Polymer Composites
• Sustainable Materials

Background:

• Polylactic acid (PLA) is a biodegradable polymer with potential for 3D printing applications.
• Incorporating sustainable fillers like rice husk biochar (RHBC) can enhance PLA's mechanical properties and reduce environmental impact.

Purpose of the Study:

• To optimize the use of rice husk biochar (RHBC) as a sustainable filler in polylactic acid (PLA) for 3D printing.
• To investigate the influence of 3D printing parameters on the mechanical properties of PLA/RHBC composites.
• To develop machine learning models for predicting the mechanical performance of these composites.

Main Methods:

• Central Composite Design (CCD) and Analysis of Variance (ANOVA) were employed to evaluate filler content, nozzle temperature, orientation angle, and fill pattern.
• Experimental data on tensile strength, Young's modulus, and hardness were collected.
• Machine learning models (MLR, KNN, SVM, Gradient Boosting) were utilized for property prediction.

Main Results:

• Filler content significantly impacted tensile strength and Young's modulus, while filler content and nozzle temperature were key for hardness.
• PLA/RHBC composites showed substantial improvements in mechanical properties compared to pure PLA.
• The Gradient Boosting model achieved high prediction accuracy (R² > 96%) for all tested mechanical properties.

Conclusions:

• RHBC is an effective sustainable filler for enhancing PLA composites for 3D printing.
• A combined approach of experimental design and machine learning provides a robust framework for material optimization.
• Optimized PLA/RHBC composites are suitable for applications in the automotive, sports, and aerospace industries.