Open Access

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

G. Bilowo

G. Bilowo

Informatics' Post Graduate Student, Post Graduate Program, Universitas Pelita HarapanTangerang, Indonesia
Search for this author on
Sciendo|Google Scholar
Bilowo, G.
 and 
B. Hardjono

B. Hardjono

Faculty of Computer Science, Post Graduate Program, Universitas Pelita HarapanTangerang, Indonesia
Search for this author on
Sciendo|Google Scholar
Hardjono, B.
  
Jul 01, 2025
3D print orientation optimization and comparative analysis of NSGA-II versus NSGA-II with Q-learning's Cover Image
About this article
Previous Article
Next Article
Cite
Download Cover
Article Category: Research Article
Published Online: Jul 01, 2025
Received: Apr 08, 2025
DOI: https://doi.org/10.2478/ijssis-2025-0035
Keywords
© 2025 G. Bilowo et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

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 model Dimensions (cm)
 Facet Support area Print time Surface roughness
X Y Z
1 bunny 0 0 0 292 2,168.3 1,023 101

Comparison of NSGAII with NSGAII-Q learning

3D model Objective NSGA_II NSGAII-Q learning Efficiency improvement
Bunny Material support 212,970 208,570 2.1
Print time 1,1847 11,393 3.8
Surface roughness 1.08 1.06 1.9
Language:
English
Publication timeframe:
1 times per year
Journal Subjects:
Engineering, Introductions and Overviews, Engineering, other
Journal RSS Feed