Have a personal or library account? Click to login
3D print orientation optimization and comparative analysis of NSGA-II versus NSGA-II with Q-learning Cover

3D print orientation optimization and comparative analysis of NSGA-II versus NSGA-II with Q-learning

International Journal on Smart Sensing and Intelligent Systems
Volume 18 (2025): Issue 1 (January 2025)
By: G. Bilowo and  B. Hardjono  
Open Access
|Jul 2025

Figures & Tables

Figure 1:

NSGA-II flowchart [13]. NSGA-II, non-dominated sorting genetic algorithm II.
NSGA-II flowchart [13]. NSGA-II, non-dominated sorting genetic algorithm II.

Figure 2:

Flowchart of the Q-learning and NSGA-II hybrid combination [21]. NSGA-II, non-dominated sorting genetic algorithm II.
Flowchart of the Q-learning and NSGA-II hybrid combination [21]. NSGA-II, non-dominated sorting genetic algorithm II.

Figure 3:

Medium-complexity 3D model (low poly bunny, author's own work).
Medium-complexity 3D model (low poly bunny, author's own work).

Figure 4:

3D Model with visualization of normal vectors.
3D Model with visualization of normal vectors.

Figure 5:

Stair-stepping effect due to layer stacking on an inclined surface [8].
Stair-stepping effect due to layer stacking on an inclined surface [8].

Figure 6:

Bar chart of the initial value of objective function with the final value of objective function. NSGA-II, non-dominated sorting genetic algorithm II.
Bar chart of the initial value of objective function with the final value of objective function. NSGA-II, non-dominated sorting genetic algorithm II.

Figure 7:

Histogram of the distribution objective function.
Histogram of the distribution objective function.

Figure 8:

Line chart history of three objective function with NSGAII used bunny.stl as 3D model. NSGA-II, non-dominated sorting genetic algorithm II.
Line chart history of three objective function with NSGAII used bunny.stl as 3D model. NSGA-II, non-dominated sorting genetic algorithm II.

Figure 9:

Pareto optimal front for the bunny 3D Model by NSGA-II. NSGA-II, non-dominated sorting genetic algorithm II.
Pareto optimal front for the bunny 3D Model by NSGA-II. NSGA-II, non-dominated sorting genetic algorithm II.

Figure 10:

Validate optimal orientation with Makerbot desktop slicer.
Validate optimal orientation with Makerbot desktop slicer.

Figure 11:

Bar chart of the initial value of objective function with the final value of objective function for the bunny 3D Model by NSGA-II with Q-learning. (Author's own work). NSGA-II, non-dominated sorting genetic algorithm II.
Bar chart of the initial value of objective function with the final value of objective function for the bunny 3D Model by NSGA-II with Q-learning. (Author's own work). NSGA-II, non-dominated sorting genetic algorithm II.

Figure 12:

Histogram of three objective function with NSGAII-Q-learning. NSGA-II, non-dominated sorting genetic algorithm II.
Histogram of three objective function with NSGAII-Q-learning. NSGA-II, non-dominated sorting genetic algorithm II.

Figure 13:

Line chart of three objective function for the bunny 3D model by NSGA-II with Q-learning. NSGA-II, non-dominated sorting genetic algorithm II.
Line chart of three objective function for the bunny 3D model by NSGA-II with Q-learning. NSGA-II, non-dominated sorting genetic algorithm II.

Figure 14:

Pareto optimal front for the bunny 3D model by NSGA-II with Q-learning. NSGA-II, non-dominated sorting genetic algorithm II.
Pareto optimal front for the bunny 3D model by NSGA-II with Q-learning. NSGA-II, non-dominated sorting genetic algorithm II.

Figure 15:

Validate optimal orientation NSGAII-Q learning with Makerbot desktop slicer. NSGA-II, non-dominated sorting genetic algorithm II.
Validate optimal orientation NSGAII-Q learning with Makerbot desktop slicer. NSGA-II, non-dominated sorting genetic algorithm II.

Figure 16:

Histogram comparison NSGAII with NSGAII-Q learning. NSGA-II, non-dominated sorting genetic algorithm II.
Histogram comparison NSGAII with NSGAII-Q learning. NSGA-II, non-dominated sorting genetic algorithm II.

Dataset of 3D model

No.3D modelDimensions (cm)
FacetSupport areaPrint timeSurface roughness
XYZ
1bunny0002922,168.31,023101

Comparison of NSGAII with NSGAII-Q learning

3D modelObjectiveNSGA_IINSGAII-Q learningEfficiency improvement
BunnyMaterial support212,970208,5702.1
Print time1,184711,3933.8
Surface roughness1.081.061.9
DOI: https://doi.org/10.2478/ijssis-2025-0035 | Journal eISSN: 1178-5608
Journal RSS Feed
Language: English
Submitted on: Apr 8, 2025
|
Published on: Jul 1, 2025
Published by: Professor Subhas Chandra Mukhopadhyay
In partnership with: Paradigm Publishing Services
Publication frequency: 1 issue per year
Keywords:
NSGA-II,
Pareto front,
Q-learning,
FDM,
multi-objective optimization,
3D printing orientation
Related subjects:
Engineering,
Introductions and overviews,
Engineering, other

© 2025 G. Bilowo, B. Hardjono, published by Professor Subhas Chandra Mukhopadhyay
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Previous articleVolume 18 (2025): Issue 1 (January 2025)Next article