Search

Resistance spot-welded joints are crucial parts in contemporary manufacturing technology due to their ubiquitous use in the automobile industry. The necessity of improving manufacturing efficiency and quality at an affordable cost requires deep knowledge of the resistance spot welding (RSW) process and the development of artificial neural network (ANN)- and machine learning (ML)-based modelling techniques, apt for providing essential tools for design, planning, and incorporation in the welding process. Tensile shear force and nugget diameter are the most crucial outputs for evaluating the quality of a resistance spot-welded specimen. This study uses ML and ANN models to predict shear force and nugget diameter responses to RSW parameters. The RSW analysis was executed on similar and dissimilar AISI 304 and grade 2 titanium alloy joints with equal and unequal thicknesses. The input parameters included welding current, pressure, welding duration, squeezing time, holding time, pulse welding, and sheet thickness. Linear regression, Decision tree, Support vector machine (SVM), Random forest (RF), Gradient-boosting, CatBoost, K-Nearest Neighbour (KNN), Ridge, Lasso, and ElasticNet machine learning algorithms, along with two different structures of Multilayer Perceptron, were utilized for studying the impact of the RSW parameters on the shear force and nugget diameter. Different validation metrics were applied to assess each model's quality. Two equations were developed to determine the shear force and nugget diameter based on the investigation parameters. The current research also presents a prediction of the Relative Importance (RI) of RSW factors. Shear force and nugget diameter predictions were examined using SHapley (SHAP) Additive Explanations for the first time in the RSW field. Trainbr as the training function and Logsig as the transfer function delivered the best ANN model for predicting shear force in a one-output structure. Trainrp with Tansig made the most accurate predictions for nugget diameter in a one-output structure and for shear force and diameter in a two-output structure. Depending on validation metrics, the Random forest model outperformed the other ML algorithms in predicting shear force or nugget diameter in a one-output model, while the Decision tree model gave the best prediction using a two-output structure. Linear regression made the worst ML predictions for shear force, while ElasticNet made the worst nugget diameter forecasts in a one-output model. However, in two-output models, Lasso made the worst predictions. [ABSTRACT FROM AUTHOR]

The main objective of this research is to conduct an experimental investigation of the bimetallic material formed by 316LSI stainless steel and S275JR structural steel, produced via hybrid wire arc additive manufacturing technology with cool metal transfer welding and machining, and with the objective of being able to reduce the industrial cost of certain requirements for one of the materials. A methodological investigation has been carried out starting with welding beads of 316LSI on S275JR plates, followed by overlapping five beads and conducting final experiments with several vertical layers, with or without intermediate face milling. The results achieved optimal bead conditions for wire speeds of 4 m/min and 5 m/min at a travel speed of 400 mm/min. Overlap experiments show that the best deposition results are obtained with an overlap equal to or greater than 28%. Cooling time does not significantly influence the final geometry of the coatings. Regarding metallographic analysis, the filler material presents an austenitic columnar structure. In the base material, a bainitic structure with inferred grain refinement was detected in the heat-affected zone. An increase in hardness is observed in the heat-affected zone. In the results obtained from the tensile tests of the bimetallic material, an increase in mechanical strength and yield strength is observed in the tested specimens. [ABSTRACT FROM AUTHOR]

Myxoid pseudotumor is a pseudoneoplastic fibroblastic proliferation that has been described in the perinephric and renal sinus fat tissue. It is characterized by the presence of a myxoid matrix, intermingled with the adipocytes, and a hypocellular population of spindle-shaped and stellate cells. We report a myxoid pseudotumor involving the distal ureter, which broadens the spectrum of possible localizations of this lesion around the urinary tract. It occurred in an 80-year-old patient who underwent a nephroureterectomy indicated after an incidental radiological finding of a thickening of the distal left ureter wall which suggested a ureteral neoplasm. He had two voided urine and one ureteroscopic sample cytologies diagnosed as high-grade urothelial carcinoma, as well as a retrograde ureteroscopy ureteral biopsy which was diagnosed as urothelial carcinoma in situ. This emphasizes the problem of the possible misdiagnosis of myxoid pseudotumor as a ureteral infiltrative carcinoma due to the radiological findings being badly interpreted, compounded by the preoperative cytohistologic data on malignancy. A diffuse urothelial carcinoma in situ was seen in our specimen without infiltrative or papillary tumors. This would not support an obstructive pathogenetic mechanism as has been hypothesized for myxoid pseudotumor. [ABSTRACT FROM AUTHOR]

The automobile industry relies primarily on spot welding operations, particularly resistance spot welding (RSW). The performance and durability of the resistance spot-welded joints are significantly impacted by the welding quality outputs, such as the shear force, nugget diameter, failure mode, and the hardness of the welded joints. In light of this, the present study sought to determine how the aforementioned welding quality outputs of 0.5 and 1 mm thick austenitic stainless steel AISI 304 were affected by RSW parameters, such as welding current, welding time, pressure, holding time, squeezing time, and pulse welding. In order to guarantee precise evaluation and experimental analysis, it is essential that they are supported by a numerical model using an intelligent model. The primary objective of this research is to develop and enhance an intelligent model employing artificial neural network (ANN) models. This model aims to provide deeper knowledge of how the RSW parameters affect the quality of optimum joint behavior. The proposed neural network (NN) models were executed using different ANN structures with various training and transfer functions based on the feedforward backpropagation approach to find the optimal model. The performance of the ANN models was evaluated in accordance with validation metrics, like the mean squared error (MSE) and correlation coefficient (R2). Assessing the experimental findings revealed the maximum shear force and nugget diameter emerged to be 8.6 kN and 5.4 mm for the case of 1–1 mm, 3.298 kN and 4.1 mm for the case of 0.5–0.5 mm, and 4.031 kN and 4.9 mm for the case of 0.5–1 mm. Based on the results of the Pareto charts generated by the Minitab program, the most important parameter for the 1–1 mm case was the welding current; for the 0.5–0.5 mm case, it was pulse welding; and for the 0.5–1 mm case, it was holding time. When looking at the hardness results, it is clear that the nugget zone is much higher than the heat-affected zone (HZ) and base metal (BM) in all three cases. The ANN models showed that the one-output shear force model gave the best prediction, relating to the highest R and the lowest MSE compared to the one-output nugget diameter model and two-output structure. However, the Levenberg–Marquardt backpropagation (Trainlm) training function with the log sigmoid transfer function recorded the best prediction results of both ANN structures. [ABSTRACT FROM AUTHOR]

This article presents an experimental study of the material extrusion process to examine the impact of less-analyzed factors on surface roughness, not including the commonly known layer height. The study also gives attention to the inner surfaces of printed samples. The design of experiments used a fractional factorial design with five two-level factors: bed temperature, fan percentage, printing speed, printing temperature, and wall thickness. Thus, the purpose of the design is screening. A two-dimensional contact profilometer was used to measure the surface roughness. Generally, the inner faces of the printed samples showed lower surface roughness. In addition, four analysis of variance showed that wall thickness (for Ra and Rz) and printing speed (for Ra) are significant for the outer and inner surfaces, respectively. As the wall thickness increased, the surface roughness decreased. Meanwhile, the lower the printing speed, the worse the surface quality on the inner faces. [ABSTRACT FROM AUTHOR]

In this work we performed a detailed numerical analysis to investigate the dynamic susceptibility of 1000 nm long Fe3O4 nanotubes by varying the diameter, the tube wall thickness and the magnitude of the external magnetic field applied along the tube axis. We found two well-defined modes, one of low frequency associated with the caps of the nanotubes, and another of high frequency associated with the central area of the nanotubes, which can be controlled by varying the geometry of the tubes or the external magnetic field to which they are subjected. These results allow us to suggest the use of these nanotubes in applications that require controlling the resonant frequency in the GHz range. [ABSTRACT FROM AUTHOR]

In this paper, our objective was to investigate the static and dynamic magnetic properties of Fe3O4 nanotubes that are 1000 nm long, by varying the external radius and the thickness of the tube wall. We performed a detailed numerical analysis by simulating hysteresis curves with an external magnetic field applied parallel to the axis of the tubes (along the z-axis). Our findings indicate that nanotubes with an external radius of 30 nm exhibit non-monotonic behavior in their coercivity due to a change in the magnetization reversal mechanism, which was not observed in nanotubes with external radii of 80 nm. Additionally, we explored the dynamic susceptibility of these nanotubes and found that the position and number of resonance peaks can be controlled by manipulating the nanotube geometry. Overall, our study provides valuable insights into the behavior of Fe3O4 nanotubes, which can aid in the design and improvement in pseudo-one-dimensional technological devices. [ABSTRACT FROM AUTHOR]