The purpose of this paper is to develop machine learning (ML) models for prediction of surface roughness and cutting forces of 42CrMo4 steel in hard turning process. A full factorial experimental design with four input parameters: cutting speed, depth of cut, feed and insert radius was used to develop ML models for predicting the performance of turning process. The backward linear regression, random forest (RF) and XGBoost were used. Also, for the linear regression model and for the best RF and XGBoost model five-fold cross validation was done to confirm that the models provide reliable generalization estimates rather than performance dependent on a single data split. The XGBoost model demonstrates the most compact clustering of residuals with fewer large errors, indicating better overall stability and predictive consistency compared to the linear regression and RF models. The application of different ML methods with monitoring of standardized residuals on unseen data confirms the reliability of the developed models in real application conditions. This study provides a structured and comparative modeling framework across multiple output variables, where backward linear regression, RF and XGBoost models were developed. Several architectural and hyperparameter variations of the RF and XGBoost models were evaluated to ensure optimal configuration for each output. Also, variable influence was examined through permutation feature importance for ensemble models and statistical significance testing for linear regression, enabling interpretation and discussion of the influence of input variables on selected outputs.

Fused deposition modelling (FDM) of carbon fibre reinforced polyamide (PA6-CF10) parts is subjected to challenges related to dimensional stability and mechanical properties. This study investigated the effect of annealing as a post-processing method for carbon fibre reinforced polyamide parts produced by FDM to enhance the mechanical properties while preserving dimensional accuracy immediately after processing and after 90 days of ambient storage. It provides a comprehensive evaluation of the effect of annealing on the mechanical properties, dimensional stability, and long-term behaviour of FDM-printed PA6-CF10 components under ambient storage conditions. To analyse mechanical properties and dimensional accuracy, samples were annealed at 90 °C to 180 °C for 60 min to 360 min. Optimal conditions were 180 °C for 210 min, yielding significant gains in tensile properties, especially for samples stored in ambient storage for 90 days after annealing. The tensile strength and tensile modulus after annealing increased by 7.27% and 5.15% compared to unannealed samples; samples tested 90 days after annealing have the tensile strength and tensile modulus increased by 14.53% and 13.79%. Dimensional deviation of the annealed samples compared to the 3D CAD model was less than 1% for samples tested 90 days after annealing. These results indicate that annealing improves both immediate mechanical performance and long-term stability of PA6-CF10 components while maintaining dimensional accuracy.

This paper analyzes different approaches for the mathematical modeling and optimization of process parameters in the hard turning process of 42CrMo4 steel using a hybrid approach combining response surface methodology (RSM), multi-criteria decision making (MCDM), and machine learning through, support vector regression (SVR) with one-factor-at-a-time (OFAT) sensitivity analysis. Controlled process parameters such as cutting speed, depth of cut, feed, and insert radius are applied to conduct the experiments based on a full factorial experimental design. RSM was used to develop models that describe the effect of controlled parameters on surface roughness and cutting forces. Special emphasis was placed on the analysis of standardized residuals to evaluate the predictive capabilities of the RSM-developed model on an unseen data set. For all four outputs considered, analysis of the standardized residuals shows that over 97% of the points lie within ±3 standard deviations. A multi-criteria optimization technique was applied to establish an optimal combination of input parameters. The SVR model had high performance for all outputs, with coefficient of determination values between 89.91% and 99.39%, except for surface roughness on the test set, with a value of 9.92%. While the SVR model achieved high predictive accuracy for cutting forces, its limited generalization capability for surface roughness highlights the higher complexity and stochastic nature of surface formation mechanisms in the turning process. OFAT analysis showed that feed rate and depth of cut have been shown to be the most important input variables for all analyzed outputs.

The application of additive manufacturing technologies for producing parts from polymer composite materials has gained significant attention due to the ability to create fully functional components that leverage the advantages of both polymer matrices and fiber reinforcements while maintaining the benefits of additive technology. Polymer composites are among the most advanced and widely used composite materials, offering high strength and stiffness with low mass and variable resistance to different media. This study aims to experimentally investigate the impact of selected process parameters, namely, wall thickness, raster angle, printing temperature, and build plate temperature, on the flexural properties of carbon fiber reinforced polyamide (CFrPA) fused deposition modeling (FDM) printed samples, as per ISO 178 standards. Additionally, regression and artificial neural network (ANN) models have been developed to predict these flexural properties. ANN models are developed for both normal and augmented inputs, with the architecture and hyperparameters optimized using random search technique. Response surface methodology (RSM), which is based on face centered composite design, is employed to analyze the effects of process parameters. The RSM results indicate that the raster angle and build plate temperature have the greatest impact on the flexural properties, resulting in an increase of 51% in the flexural modulus. The performance metrics of the optimized RSM and ANN models, characterized by low MSE, RMSE, MAE, and MAPE values and high R2 values, suggest that these models provide highly accurate and reliable predictions of flexural strength and modulus for the CFrPA material. The study revealed that ANN models with augmented inputs outperform both RSM models and ANN models with normal inputs in predicting these properties.

As manufacturing technologies advance, the integration of artificial neural networks in machining high-hardness materials and optimization of multi-objective parameters is becoming increasingly prevalent. By employing modeling and optimization strategies during the machining of such materials, manufacturers can improve surface roughness and tool life while minimizing cutting time, tool vibrations, and cutting forces. In this paper, the aim was to analyze the impact of input parameters (cutting speed, feed rate, depth of cut, and insert radius) on surface roughness and cutting forces during the machining of 90MnCrV7 using feed-forward neural network models and SHAP analysis. Afterward, multi-criteria optimization was applied to determine the optimal parameter levels to achieve minimum surface roughness and cutting forces using the modified PSI-TOPSIS method. According to the SHAP analysis, the insert radius has the most significant impact on the surface roughness and passive force, while in the multi-criteria analysis, according to ANOVA results, the insert radius has the most significant impact on all considered outputs. The results show that an insert radius of 0.8 mm, a cutting speed of 260 m/min, a feed rate of 0.08 mm, and a depth of cut of 0.5 mm are the optimal combination of input parameters.

Fused deposition modelling (FDM) is one of the mostly used additive technologies, due to its ability to produce complex parts with good mechanical properties. The selection of FDM process parameters is crucial to achieve good mechanical properties of the manufactured parts. Therefore, in this paper, a hybrid multi-criteria decision-making (MCDM) approach based on Preference Selection Index (PSI) and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) is proposed for the selection of optimal process parameters in FDM printing of polylactic acid (PLA) parts. Printing temperature, layer thickness and raster angle were considered as input process parameters. In order to prove the effectiveness of the proposed hybrid PSI – TOPSIS method, the obtained results were compared with the results obtained with different MCDM methods. The obtained best option of process parameters was confirmed by other MCDM methods. The optimal combination of process parameters to achieve the maximal flexural strength, maximal flexural modulus and maximal compressive strength is selected using the hybrid PSI-TOPSIS method. The results show that the hybrid PSI-TOPSIS approach could be used for optimisation process parameters for any machining process.

Reinforcing the polymer with nanoparticles and fibers improves the mechanical, thermal and electrical properties. Owing to this, the functional parts produced by the FDM process of such materials can be used in industrial applications. However, optimal parameters’ selection is crucial to produce parts with optimal properties, such as mechanical strength. This paper focuses on the analysis of influential process parameters on the tensile strength of FDM printed parts. Two statistical methods, RSM and ANN, were applied to investigate the effect the layer thickness, printing speed, raster angle and wall thickness on the tensile strength of test specimens printed with a short carbon fiber reinforced polyamide composite. The reduced cubic model was developed by the RSM method, and the correlation between the input parameters and the output response was analyzed by ANOVA. The results show that the layer thickness and raster angle have the most significant influence on tensile strength. As for machine learning, among the nine different tested ANN topologies, the best configuration was found based on the lowest MAE and MSE test sample result. The results show that the proposed model could be a useful tool for predicting tensile strength. Its main advantage is the reduction in time needed for experiments with the LOSO (leave one subject out) k-fold cross validation scheme, offering better generalization ability, given the small set of learning examples.

Microneedles (MNs) represent the concept of attractive, minimally invasive puncture devices of micron-sized dimensions that penetrate the skin painlessly and thus facilitate the transdermal administration of a wide range of active substances. MNs have been manufactured by a variety of production technologies, from a range of materials, but most of these manufacturing methods are time-consuming and expensive for screening new designs and making any modifications. Additive manufacturing (AM) has become one of the most revolutionary tools in the pharmaceutical field, with its unique ability to manufacture personalized dosage forms and patient-specific medical devices such as MNs. This review aims to summarize various 3D printing technologies that can produce MNs from digital models in a single step, including a survey on their benefits and drawbacks. In addition, this paper highlights current research in the field of 3D printed MN-assisted transdermal drug delivery systems and analyzes parameters affecting the mechanical properties of 3D printed MNs. The current regulatory framework associated with 3D printed MNs as well as different methods for the analysis and evaluation of 3D printed MN properties are outlined.

Microneedles (MNs) have been manufactured using a variety of methods from a range of materials, but most of them are expensive and time-consuming for screening new designs and making any modifications. Therefore, stereolithography (SLA) has emerged as a promising approach for MN fabrication due to its numerous advantages, including simplicity, low cost, and the ability to manufacture complex geometrical products at any time, including modifications to the original designs. This work aimed to print MNs using SLA technology and investigate the effects of post-printing curing conditions on the mechanical properties of 3D-printed MNs. Solid MNs were designed using CAD software and printed with grey resin (Formlabs, UK) using Form 3 printer (Formlabs, UK). MNs dimensions were 1.2 × 0.4 × 0.05 mm, arranged in 6 rows and 6 columns on a 10 × 10 mm baseplate. MNs were then immersed in an isopropyl alcohol bath to remove unpolymerized resin residues and cured in a UV-A heated chamber (Formlabs, UK). In total, nine samples were taken for each combination of curing temperature (35°C, 50°C, and 70°C) and curing time (5 min, 20 min, and 60 min). Fracture tests were conducted using a hardness apparatus TB24 (Erweka, Germany). MNs were placed on the moving probe of the machine and compressed until fracture. The optimization of the SLA process parameters for improving the strength of MNs was performed using the Taguchi method. The design of experiments was carried out based on the Taguchi L9 orthogonal array. Experimental results showed that the curing temperature has a significant influence on MN strength improvements. Improvement of the MN strength can be achieved by increasing the curing temperature and curing time.