Predicting the Optimal Input Parameters for the Desired Print Quality Using Machine Learning.

3D printing is a growing technology being incorporated into almost every industry. Although it has obvious advantages, such as precision and less fabrication time, it has many shortcomings. Although several attempts were made to monitor the errors, many have not been able to thoroughly address them, like stringing, over-extrusion, layer shifting, and overheating. This paper proposes a study using machine learning to identify the optimal process parameters such as infill structure and density, material (ABS, PLA, Nylon, PVA, and PETG), wall and layer thickness, count, and temperature. The result thus obtained was used to train a machine learning algorithm. Four different network architectures (CNN, Resnet152, MobileNet, and Inception V3) were used to build the algorithm. The algorithm was able to predict the parameters for a given requirement. It was also able to detect any errors. The algorithm was trained to pause the print immediately in case of a mistake. Upon comparison, it was found that the algorithm built with Inception V3 achieved the best accuracy of 97%. The applications include saving the material from being wasted due to print time errors in the manufacturing industry.

A Comparative Study on Bio-Based PU Foam Reinforced with Nanoparticles for EMI-Shielding Applications.

Today, most commercial polyols used to make polyurethane (PU) foam are produced from petrochemicals. A renewable resource, castor oil (CO), was employed in this study to alleviate concerns about environmental contamination. This study intends to fabricate a bio-based and low-density EMI-defending material for communication, aerospace, electronics, and military appliances. The mechanical stirrer produces the flexible bio-based polyurethane foam and combines it with nanoparticles using absorption and hydrothermal reduction processes. The nanoparticles used in this research are graphite nanoplates (GNP), zirconium oxide (ZrO2), and bamboo charcoal (BC). Following fabrication, the samples underwent EMI testing using an EMI test setup with model number N5230A PNA-L. The EMI experimental results were compared with computational simulation using COMSOL Multiphysics 5.4 and an optimization tool using response surface methodology. A statistical design of the experimental approach is used to design and evaluate the experiments systematically. An experimental study reveals that a 0.3 weight percentage of GNP, a 0.3 weight percentage of ZrO2, and a 2.5 weight percentage of BC depict a maximum EMI SE of 28.03 dB in the 8-12 GHz frequency band.

Experimental and Numerical Analyses on the Buckling Characteristics of Woven Flax/Epoxy Laminated Composite Plate under Axial Compression.

The evolution of a sustainable green composite in various loadbearing structural applications tends to reduce pollution, which in turn enhances environmental sustainability. This work is an attempt to promote a sustainable green composite in buckling loadbearing structural applications. In order to use the green composite in various structural applications, the knowledge on its structural stability is a must. As the structural instability leads to the buckling of the composite structure when it is under an axial compressive load, the work on its buckling characteristics is important. In this work, the buckling characteristics of a woven flax/bio epoxy (WFBE) laminated composite plate are investigated experimentally and numerically when subjected to an axial compressive load. In order to accomplish the optimization study on the buckling characteristics of the composite plate among various structural criterions such as number of layers, the width of the plate and the ply orientation, the optimization tool "response surface methodology" (RSM) is used in this work. The validation of the developed finite element model in Analysis System (ANSYS) version 16 is carried out by comparing the critical buckling loads obtained from the experimental test and numerical simulation for three out of twenty samples. A comparison is then made between the numerical results obtained through ANSYS16 and the results generated using the regression equation. It is concluded that the buckling strength of the composite escalates with the number of layers, the change in width and the ply orientation. It is also noted that the weaving model of the fabric powers the buckling behavior of the composite. This work explores the feasibility of the use of the developed green composite in various buckling loadbearing structural applications. Due to the compromised buckling characteristics of the green composite with the synthetic composite, it has the capability of replacing many synthetic composites, which in turn enhances the sustainability of the environment.