Search

Classification of cast iron alloys based on graphite morphology plays a crucial role in materials science and engineering. Traditionally, this classification has relied on visual analysis, a method that is not only time‐consuming but also suffers from subjectivity, leading to inconsistencies. This study introduces a novel approach utilizing convolutional neural networks—MobileNet for image classification and U‐Net for semantic segmentation—to automate the classification process of cast iron alloys. A significant challenge in this domain is the limited availability of diverse and comprehensive datasets necessary for training effective machine learning models. This is addressed by generating a synthetic dataset, creating a rich collection of 2400 pure and 1500 mixed images based on the ISO 945‐1:2019 standard. This ensures a robust training process, enhancing the model's ability to generalize across various morphologies of graphite particles. The findings showcase a remarkable accuracy in classifying cast iron alloys (achieving an overall accuracy of 98.9 ± 0.4%—and exceeding 97% for all six classes—for classification of pure images and ranging between 84% and 93% for semantic segmentation of mixed images) and also demonstrate the model's ability to consistently identify and graphite morphology with a level of precision and speed unattainable through manual methods. [ABSTRACT FROM AUTHOR]

This article is focused on the experimental characterization and validation of a novel elastomeric material fabricated from the grinded end-of-life tires blended with polyurethane resin. This material will be used as a vibration and noise attenuator in railway slab track systems with embedded rail, commonly used in urban areas. Cylinders with different combinations of grain sizes (coarse, medium, and fine) of end-of-life tires and contents of resin were mechanically tested to obtain the Young's modulus. The most versatile combination consisting in 50 % coarse + 50 % medium size grains was selected. Two real-scale prototypes consisting of a rail surrounded by the rubber mixture and the concrete slab were designed and fabricated to be applied under normal conditions (low attenuation system) and under situations where vibrations could be fatal (high attenuation system). These prototypes were subjected to static, dynamic, and fatigue loading conditions, applying vertical and angular loads, to validate their mechanical performance. In addition, a vibroacustical experimental study was carried out to obtain the frequency response and the receptance functions. A one-degree-of-freedom analytical model was developed to obtain a loss factor η = 0.287 and a vibration attenuation capacity of the system for the human ear peak sensitivity of ~40 dB. This study proves the validation of this new eco-friendly material to be used as a vibration attenuator for railway traffic. [ABSTRACT FROM AUTHOR]

The present research is aimed at obtaining and experimentally validating an artificial neural network to predict the hardness of TX304HB steel tubes subjected to shot peening. The experimental scope consisted of 228 tubes. Seven variables were considered as input parameters: rotation speed, line speed, material flow, air pressure, the size of the nozzle, and the internal diameter of the tubes; the experimental data demonstrated the need for considering the material bulk hardness as an input variable. One specimen from each tube was taken and subjected to Vickers microhardness tests at a depth of 40 µm from the interior circumference as well as a depth beyond the influence of the shot peening (bulk condition). The hardness was proven to follow Gaussian distribution. Therefore, a neural network was designed and tuned to provide the mean and standard deviation of the hardness for each of the combinations of input variables. The neural networks designed in this way were able to faithfully reproduce the experimental results. Several statistical parameters were determined to measure the goodness of the fitting. Thus, the correlation between experimental and predicted numerical values of mean hardness yields R² = 0.7651 and a mean absolute percentage error of 1.547% for the training data set and 0.7402 and 2.054% for the test data set. The corresponding values for the prediction of the standard deviation are R² = 0.4713 and 17.946% for the training set and R² = 0.6847 and 17.071% for the test set. [ABSTRACT FROM AUTHOR]

The assessment of the structural integrity of nuclear vessels is based on a series of procedures developed in the 1970s and 1980s. On one hand, curves that, according to the American Society of Mechanical Engineers code, describe the relationship between steel toughness and temperature in the ductile-to-brittle transition region, based on the reference temperature concept RTNDT, were adopted in 1972. On the other hand, the material embrittlement derived from the exposure of steel to neutron irradiation is determined through the model included in "Regulatory Guide 1.99 Rev. 2," published in 1988. Since then, there have been enormous advances in this field. For example, the Master Curve, based on the reference temperature T0, describes the relationship between toughness and temperature in the transition zone more realistically and with much more robust microstructural and mechanical foundations and uses the elastic-plastic fracture toughness KJc. Moreover, improved models have been developed to estimate the embrittlement of steel subjected to neutron irradiation, such as ASTM E900, Standard Guide for Predicting Radiation-Induced Transition Temperature Shift in Reactor Vessel Materials. This study is aimed at comparing the results obtained using traditional procedures to the improved alternatives developed later. For this purpose, the behavior of the steel of a nuclear vessel that is currently under construction has been experimentally characterized through RTNDT and T0 parameters. In addition, the material embrittlement has been quantified using "Regulatory Guide 1.99 Rev. 2" and ASTM E900. These experimental results have been transferred to the assessment of the structural integrity of the vessel to determine the pressure-temperature limit curves and size of the maximum admissible defect as a function of the operation time of the plant. The results have allowed the implicit overconservatism present in the traditional procedures to be quantified. [ABSTRACT FROM AUTHOR]

The elastic cellular polyurethane elastomer is widely used to manufacture shock absorbers for elevators, due to its excellent conditions for absorption of energy and vibration damping. In this paper, a complete mechanical characterization of this material was performed including the uniaxial compressive test, the planar test, and the volumetric and the simple shear test. From the experimental results, several models behavior for hyperelastic and elastomeric foam materials have been analyzed by fitting their corresponding material parameters. The scope of work includes the Ogden model, the Van der Waals model, and polynomial and elastomeric foam forms. [ABSTRACT FROM AUTHOR]