Optimization of Process Parameters to Investigate the Fatigue Behavior of Fused Deposition Modeling-Fabricated ABS Parts Using Hybrid Tool

Abstract

This proposed work focuses on optimizing process parameters to enhance the fatigue strength of fused deposition modeling-fabricated acrylonitrile butadiene styrene (ABS) parts, which are widely used in industries such as automotive, aerospace, and medical applications. These fields demand lightweight, durable components capable of withstanding repeated loading cycles. The study specifically optimizes process parameters such as layer thickness, infill density, and infill pattern to improve fatigue performance. The methodology includes both experimental analysis and optimization techniques. Experimental results were analyzed using analysis of variance to investigate the consequence of varying the process parameters on the fatigue life of ABS parts. Additionally, two predictive models—a mathematical model based on response surface methodology and a neural network model based on artificial neural networks (ANNs)—were developed to explore the correlation between process parameters and fatigue strength. A genetic algorithm (GA) was integrated with the ANN model that had the better overall R² value of 0.9981. The GA–ANN model improved the fatigue strength by 13.28% to 15.86 MPa with optimized process parameters: 0.146 mm layer thickness, 100% infill density, and a tri-hexagon infill pattern, with an accuracy of 99%. Validation tests disclosed strong agreement between the predicted and experimental results. The optimized fatigue strength can improve the reliability of components like gears, housings, prosthetics, and implants, thus enhancing overall performance and safety.