The synthesis and manufacturing of polymer nanocomposites have garnered interest in recent research and development because of their superiority compared to traditionally employed industrial materials.

The synergistic integration of nanocomposites and 3D printing has opened a gateway to the future and is soon expected to surpass its rivalry with traditional manufacturing techniques. However, there is always a challenge associated with preparing a nanocomposite resin for polymerization-based 3D printing, which is the agglomeration of nanoparticles. Due to the high surface-area-to-volume ratio, the nanoparticles form clusters in the composite matrix, which affects the final properties. This paper aims to analyze the effects of graphene oxide (GO) dispersion on the mechanical and thermal properties of 3D-printed nanocomposites. In particular, a well-dispersed sonication dispersion route is employed for analyzing high and poor GO dispersions and their effects on different properties. After different microscopic analyses and testing, the optimum sonication condition was 30 min at an amplitude of 70%. In terms of mechanical properties, both tensile and compression strength first increased and then decreased gradually with different dispersions as well as varying GO concentrations. Furthermore, there was less or no effect on thermal stability. GO of 0.05 wt.% had the highest compression and tensile strength, while beyond 0.05 to 0.5 wt.%, both strengths reduced slowly. These 3D-printed nanocomposites have found their application in automotive, sports, and biomedical fields.

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.

This study discusses the effectual variable parameters of multi-walled carbon nanotubes and titanium oxide (MWCNT–TiO₂) contents and welding current in obtaining a response on mechanical behavior. The experimental work involved three levels of both parameters, which included 1, 1.5, and 2 wt.% of MWCNTs–TiO₂ and 160, 180, and 200 A of current by forming a full design that represented a 3² (3 ^k) factorial model. The results of an analysis of variance (ANOVA) were critically employed to assess the variation between the variables and within their levels for approaching the significant combination of parameters. The joints welded with MWCNT–TiO₂-coated fillers tendered a significant reduction in grain size (GS) along with high values of tensile strength (TS). From the ANOVA, it was determined that both the investigated parameters and their combined effect created a significant response for GS reduction and increment in TS. The presented empirical regression quadratic model was validated for the adequacy of the projected results that were shown to be acceptable with the experimental investigated data. In addition, the desirability function approach was applied for a multiple response optimization in yielding the desired responses of GS and TS and simultaneously providing an optimized set of process parameters. Thus, the function declared 1.5 wt.% MWCNT–TiO₂ and 180 A as the optimized process set for delivering the maximum TS at the designated range of GS for this system.