Additive manufacturing (AM) and topology optimization (TO) emerge as vital processes in modern industries, with broad adoption driven by reduced expenses and the desire for lightweight and complex designs. However, iterative topology optimization can be inefficient and time-consuming for individual products with a large set of parameters. To address this shortcoming, machine learning (ML), primarily neural networks, is considered a viable tool to enhance topology optimization and streamline AM processes. In this work, a machine learning (ML) model that generates a parameterized optimized topology is presented, capable of eliminating the conventional iterative steps of TO, which shortens the development cycle and decreases overall development costs. The ML algorithm used, a conditional generative adversarial network (cGAN) known as Pix2Pix-GAN, is adopted to train using a variety of training data pairs consisting of color-coded images and is applied to an example of cantilever optimization, significantly enhancing model accuracy and operational efficiency. The analysis of training data numbers in relation to the model’s accuracy shows that as data volume increases, the accuracy of the model improves. Various ML models are developed and validated in this study; however, some artefacts are still present in the generated designs. Structures that are free from these artefacts achieve 91% reliability successfully. On the other hand, the images generated with artefacts may still serve as suitable design templates with minimal adjustments. Furthermore, this research also assesses compliance with two manufacturing constraints: the limitations on build space and passive elements (voids). Incorporating manufacturing constraints into model design ensures that the generated designs are not only optimized for performance but also feasible for production. By adhering to these constraints, the models can deliver superior performance in future use while maintaining practicality in real-world applications.

Lattice structures in additive manufacturing of 316L stainless steel have gained increasing attention due to their well-suited mechanical properties and lightweight characteristics. Infill structures such as honeycomb, lattice, and gyroid have shown promise in achieving desirable mechanical properties for various applications. However, the design process of these structures is complex and time-consuming. In this study, we propose a machine learning-based approach to optimize the design of honeycomb, lattice, and gyroid infill structures in 316L stainless steel fabricated using laser powder bed fusion (L-PBF) technology under different loading conditions. A dataset of simulated lattice structures with varying geometries, wall thickness, distance, and angle using a computational model that simulates the mechanical behavior of infill structures under different loading conditions was generated. The dataset was then used to train a machine learning model to predict the mechanical properties of infill structures based on their design parameters. Using the trained machine learning model, we then performed a design exploration to identify the optimal infill structure geometry for a given set of mechanical requirements and loading conditions. Finally, we fabricated the optimized infill structures using L-PBF technology and conducted a series of mechanical tests to validate their performance under different loading conditions. Overall, our study demonstrates the potential of machine learning-based approaches for efficient and effective designing of honeycomb, lattice, and gyroid infill structures in 316L stainless steel fabricated using L-PBF technology under different loading conditions. Furthermore, this approach can be used for dynamic loading studies of infill structures.

This study introduced a systematic framework to develop practical design guidelines specifically for filament-based material extrusion of metals (MEX/M), an additive manufacturing (AM) process defined by ISO/ASTM 52900. MEX/M provides a cost-efficient alternative to conventional manufacturing methods, which is particularly valuable for rapid prototyping. Although AM offers significant design flexibility, the MEX/M process imposes distinct geometric and process constraints requiring targeted optimization. The research formulates and validates design guidelines tailored for the MEX/M using an austenitic steel 316L (1.4404) alloy filament. The feedstock consists of a uniform blend of 316L stainless steel powder and polymeric binder embedded within a thermoplastic matrix, extruded and deposited layer by layer. Benchmark parts were fabricated to examine geometric feasibility, such as minimum printable wall thickness, feature inclination angles, borehole precision, overhang stability, and achievable resolution of horizontal and vertical gaps. After fabrication, the as-built (green-state) components undergo a two-step thermal post-processing treatment involving binder removal (debinding), followed by sintering at elevated temperatures to reach densification. Geometric accuracy was quantitatively assessed through a 3D scan by comparing the manufactured parts to their original CAD models, allowing the identification of deformation patterns and shrinkage rates. Finally, the practical utility of the developed guidelines was demonstrated by successfully manufacturing an impeller designed according to the established geometric constraints. These design guidelines apply specifically to the machine and filament type utilized in this study.

Improving mechanical topology optimization (TO) results by substituting biomimetic beams is one possibility to achieve designs of mechanical components that are highly sustainable and show good mechanical performance. Because of their geometric complexity, such designs were found to be well-suited for production by laser additive manufacturing. One obstacle of incorporating biomimetics beams in TO designs is the lack of detailed design methodologies. Röver et al. [“Methodology for integrating biomimetic beams in abstracted topology optimization results,” in Proceedings of the ASME 2022 International Mechanical Engineering Congress and Exposition. Volume 4: Biomedical and Biotechnology; Design, Systems, and Complexity Columbus, OH, 30 October–3 November (ASME, New York, 2022)] proposed a corresponding design concept. Building on their concept, we present in this work a detailed methodology for abstraction of TO results to a design consisting of ball nodes and cylindrical beams. Using such an auxiliary design, the internal forces and moments of the beams can be evaluated to allow for the substitution of suitable biomimetic beams to generate biomimetic component designs in a next step. We present a skeletonization algorithm based on the potential field approach. Using the skeletonization and an additional analysis of the dimensions of the beams in the TO result, the algorithm develops an auxiliary design of the original TO result. The final algorithm was applied to three common TO results to obtain one auxiliary component design each. The developed algorithm was found to generate abstractions that were well-suited for use in the methodology proposed in Röver et al. [“Methodology for integrating biomimetic beams in abstracted topology optimization results,” in Proceedings of the ASME 2022 International Mechanical Engineering Congress and Exposition. Volume 4: Biomedical and Biotechnology; Design, Systems, and Complexity Columbus, OH, 30 October–3 November (ASME, New York, 2022)], because internal forces and moments in the abstracted beams could be evaluated with less effort. Therefore, our work contributes to a detailed design methodology for biomimetic mechanical components in the field of design for additive manufacturing.

Additive manufacturing processes such as the material extrusion of metals (MEX/M) enable the production of complex and functional parts that are not feasible to create through traditional manufacturing methods. However, achieving high-quality MEX/M parts requires significant experimental and financial investments for suitable parameter development. In response, this study explores the application of machine learning (ML) to predict the surface roughness and density in MEX/M components. The various models are trained with experimental data using input parameters such as layer thickness, print velocity, infill, overhang angle, and sinter profile enabling precise predictions of surface roughness and density. The various ML models demonstrate an accuracy of up to 97% after training. In conclusion, this research showcases the potential of ML in enhancing the efficiency in control over component quality during the design phase, addressing challenges in metallic additive manufacturing, and facilitating exact control and optimization of the MEX/M process, especially for complex geometrical structures.