Related Experiment Video
Updated: Jan 10, 2026
06:24
Generic Protocol for Optimization of Heterologous Protein Production Using Automated Microbioreactor Technology
Published on: December 15, 2017
10.6K
A Hybrid Fuzzy-PSO Framework for Multi-Objective Optimization of Stereolithography Process Parameters
Mohanned M H Al-Khafaji1, Abdulkader Ali Abdulkader Kadauw2,3, Mustafa Mohammed Abdulrazaq1
1Collage of Production Engineering and Metallurgy, University of Technology-Iraq, Baghdad 10066, Iraq.
Micromachines
|November 27, 2025
Summary
This study introduces a hybrid intelligent framework to optimize Stereolithography (SLA) 3D printing parameters for Acrylonitrile Butadiene Styrene (ABS) parts. The novel approach enhances part quality by accurately modeling and optimizing key performance characteristics.
Area of Science:
- Materials Science and Engineering
- Additive Manufacturing
- Computational Intelligence
Background:
- Additive manufacturing, particularly Stereolithography (SLA), is increasingly used for final part production.
- Optimizing SLA process parameters is crucial for achieving desired material properties and surface finish.
- Acrylonitrile Butadiene Styrene (ABS) photopolymers are common materials in SLA, requiring precise parameter control.
Purpose of the Study:
- To develop a hybrid intelligent framework for modeling and optimizing SLA 3D printing parameters.
- To investigate the complex, nonlinear relationships between SLA process parameters and performance characteristics.
- To achieve multi-objective optimization for enhanced mechanical properties and surface finish of ABS parts.
Main Methods:
- Employed a Taguchi design of experiments with an L18 orthogonal array for efficient experimental design.
- Developed a novel hybrid fuzzy logic-Particle Swarm Optimization (PSO) algorithm, ARGOS, for automated fuzzy inference system (FIS) generation and tuning.
- Utilized Modified Learn From Example (MLFE) for initial FIS creation, followed by PSO for predictive accuracy enhancement.
Main Results:
- The ARGOS models demonstrated exceptional predictive accuracy, with correlation coefficients (R²) exceeding 0.9999 for all five output responses.
- A multi-objective optimization using the weighted sum method identified optimal parameter settings for balancing key part qualities.
- The proposed hybrid approach proved robust and highly accurate for modeling and optimizing the SLA 3D printing process.
Conclusions:
- The hybrid intelligent framework effectively models and optimizes SLA 3D printing parameters for ABS parts.
- The ARGOS algorithm offers a powerful tool for generating accurate Mamdani-type FISs from experimental data.
- This research provides a valuable methodology for achieving high-quality 3D printed parts in real-world manufacturing applications.
