Search

IntroductionAdditive manufacturing (AM) is a revolutionary technology transforming traditional production processes by providing exceptional mechanical characteristics.MethodsThe present study aims explicitly to predict the hardness of Polycarbonate (PC) parts produced using AM. The objectives of this study are: (1) To investigate the process parameters that impact the ability to estimate the hardness of PC materials accurately, and (2) To develop a best-performing ML model from a range of models that can reliably predict the hardness of additively manufactured PC parts. Initially, fused filament fabrication (FFF), the most affordable AM technique, was used for the manufacturing of parts. Four process parameters, infill density, print direction, raster angle, and layer thickness, are selected for investigation. A heatmap is generated to obtain the influence of process parameters on hardness. Then, machine learning (ML) techniques create a range of predictive models that can predict hardness value considering the level of process parameters.ResultsThe developed ML models include Linear Regression, Decision Tree, Random Forest, K-nearest neighbor, Support Vector Regression, AdaBoost, and Artificial Neural Network. Further, an investigation has been done that includes choosing and improving ML algorithms and assessing the models’ performance.DiscussionPrediction plots, residual plots, and evaluation metrics plots are prepared to gauge the performance of the developed models. Thus, the research enhances AM capabilities by applying predictive modeling to process parameters and improving the quality and reliability of fabricated components.

Utilizing Machine Learning (ML) to oversee the status of hobbing cutters aims to enhance the gear manufacturing process’s effectiveness, output, and quality. Manufacturers can proactively enact measures to optimize tool performance and minimize downtime by conducting precise real-time assessments of hobbing cutter conditions. This proactive approach contributes to heightened product quality and decreased production costs. This study introduces an innovative condition monitoring system utilizing a Machine Learning approach. A Failure Mode and Effect Analysis (FMEA) were executed to gauge the severity of failures in hobbing cutters of Computer Numerical Control (CNC) Hobbing Machine, and the Risk Probability Number (RPN) was computed. This numerical value aids in prioritizing preventive measures by concentrating on failures with the most substantial potential impact. Failures with high RPN numbers were considered to implement the Machine Learning approach and artificial faults were induced in the hobbing cutter. Vibration signals (displacement, velocity, and acceleration) were then measured using a commercial high-capacity and high-frequency range Data Acquisition System (DAQ). The analysis covered operating parameters such as speed (ranging from 35 to 45 rpm), feed (ranging from 0.6 to 1 mm/rev), and depth of cut (6.8 mm). MATLAB code and script were employed to extract statistical features. These features were subsequently utilized to train seven algorithms (Decision Tree, Naive Bayes, Support Vector Machine (SVM), Efficient Linear, Kernel, Ensemble and Neural Network) as well as the application of Bayesian optimization for hyperparameter tuning and model evaluation were done. Amongst these algorithms, J48 Decision tree (DT) algorithm demonstrated impeccable accuracy, correctly classifying 100% of instances in the provided dataset. These algorithms stand out for their accuracy and efficiency in building, making them well-suited for this purpose. Based on ML model performance, it is recommended to employ J48 Decision Tree Model for the condition monitoring of a CNC hobbing cutter. The emerging confusion matrix was crucial in creating a condition monitoring system. This system can analyze statistical features extracted from vibration signals to assess the health of the cutter and classify it accordingly. The system alerts the operator when a hobbing cutter approaches a worn or damaged condition, enabling timely replacement before any issues arise.

NAO brake friction materials with 4%, 5%, and 6% (w/v) sodium hydroxide treated hemp fiber reinforcement having 25% wt. fiber loading and fixed percentage of phenol formaldehyde resin content (20% wt.) along with other fillers have been studied and reported by the authors earlier. However, the effect of variations in the resin content on the tribological performance has been studied and reported in the present paper. Five variants were prepared with varying percentages of phenol formaldehyde resin from 12% wt. to 22% wt. with incremental steps of 2% wt, along with the optimum of 6% (w/v) sodium hydroxide treated hemp fibers and other fillers. The prepared test variants’ tribological characterization was done using Taguchi’s L25 orthogonal array on a pin-on-disc experimental setup, as per ASTM G99, at room temperature and compared with the best of the earlier studied friction composite. Fade and recovery tests of the best of the earlier studied and present ones were performed on a chase tribology tester per SAE J661 standards. The results revealed moderate coefficient of friction of 0.4496, lower wear rate of 0.57 gm, and better fade recovery for the HF25P20 variant compared to its counterparts studied here.

In the last few years, due to the superior mechanical qualities of Additive Manufacturing (AM) AlSi10Mg alloy to those of traditional casting process AlSi10Mg alloys, the application of AM technology has significantly increased. The ballistic impact research has a wide range of uses, notably in the mining, construction, spacecraft and defence sectors. This work focuses on analyzing the behavior of different projectile nose shapes on the AlSi10Mg alloy fabricated by AM. There are several projectile nose forms to consider, including blunt, hemispherical, conical, and ogive shapes. The impact of various projectile shapes on the ballistic limit of the additively created AlSi10Mg alloy is carefully examined in this study. All numerical simulations were carried out using LS-DYNA software, and the Johnson-Cook material and damage model were considered to assess the ballistic resistance behavior. The ballistic limit for various projectile shapes is computed using the Jonas-Lambert model, which describes the connection between residual velocity and starting projectile velocity. The results showed that, the ogive-shaped Projectile offers the highest ballistic limit, and the blunt projectile shows the lowest ballistic limit for a 5 mm thin target plate. The ballistic impact phenomenon showed plugging failure for the blunt nose projectile, the formation of plug and small fragments were observed in the case of hemispherical nose projectile, fragmenting failure is observed with radial necking in the case of conical nose projectile and petals are formed at the impacted zone in ogive nose shape projectile. Moreover, the ballistic limit of AM AlSi10Mg alloy was slightly higher compared to the ballistic limit of the die-cast AlSi10Mg alloy for the 7.62 mm AP bullet (core). Therefore, AM AlSi10Mg alloy may have equal or good ballistic properties compared to die-cast AlSi10Mg alloy.

This experimental study investigated the abrasive wear behaviour of pure copper-based and multi-walled carbon nanotube (MWCNT) doped composites synthesized by the powder metallurgy technique. Composite structures were formed by reinforcing MWCNT at different ratios between 1% and 8% in 99.9% pure copper by powder metallurgy. The microstructures of the nanocomposite samples were analyzed by X-ray diffraction. Then, density and hardness measurements and abrasive wear tests were performed to determine their mechanical properties. The collected data were evaluated with scanning electron microscopy images. It has been determined that copper’s nano-sized carbon reinforcement material has a dry lubricant effect up to a specific ratio, reducing wear losses. On the contrary, wear losses increase as the MWCNT reinforcement ratio increases between 4% and 8%. The best results in lowering wear losses were obtained from the sample with 1% MWCNT reinforcement. Depending on the increase in the amount of nanomaterial reinforcement in the composite structure, it was observed that pore formation enlarges with reinforcement agglomeration. It was concluded that the dense porosity in the composite structure neglects the lubricating properties of the MWCNT reinforcement material and increases the wear losses by having a negative effect.

This research focuses on the relationship between the tensile strength of PLA material and several 3D printing parameters, such as infill density, layer height, print speed, and extrusion temperature, utilizing the Fused Deposition Modeling (FDM) method of Additive Manufacturing (AM). Tensile strength of the samples was determined in compliance with ASTM D638 standard, and the experiments were carried out according to a planned arrangement. Six distinct methods were used to optimize the tensile strength: Particle Swarm Optimization (PSO), Teaching Learning Based Optimization (TLBO), Genetic Algorithm (GA), Simulated Annealing (SA), and Cohort Intelligence (CI). Several runs of the optimization methods demonstrated their consistency in producing the same values of tensile strength, indicating their reliability. The optimization results showed that JAYA performed better than the other algorithms, resulting in a material with the maximum tensile strength of 55.475 N/mm2. Validation experiments were carried out to confirm the efficacy of these algorithms. The results showed that the ideal input parameters produced tensile strength values that closely matched the anticipated values with a low percentage error. The benefits of applying these algorithms to improve the tensile strength of PLA materials for 3D printing are demonstrated by this study, which also offers insightful information about how to optimize FDM procedures.

Nowadays, research has shown the emergence of the 3D printing method for printing a functionalized component. Graphene nanomaterial has an enormous conducting property that can compete with conducting materials like copper and silicon. This paper describes the electrical conductivity investigation of 3D-printed graphene nanomaterial in extrusion-based 3D printing methods. In extrusion, two different approaches of the 3D printing method were used to print the graphene-based structure: the fused deposition modeling (FDM) method and the direct ink writing (DIW) method. Both printing methods follow the two printing processes and select material forms. Selection of testing was made to analyze the characterization variations in the printed material, such as XRD, TGA, viscosity, Raman shift, and Scanning Electron Microscopy analyses, which shows the changes of effect in the conductivity due to various parameter differences in both the printing methods. A four-point probe technique was used to analyze the electrical conductivity of the two different methods. These analysis results prove that the characterization variations differ in the FDM and DIW printed models.