Papers by Keyword: Property Prediction

Abstract: Metal additive manufacturing encompasses multiple techniques, among which Selective Laser Melting (SLM) is extensively employed for fabricating highly complex, precise, and uniquely shaped metal parts. However, obtaining accurate product characteristics often requires complex experimentation, which can potentially damage the products. Thus, there is a need to develop an automated method for predicting product characteristics. To forecast these attributes, details related to metal additive manufacturing products were documented, including process parameters and textural features. These features were extracted from product’s longitudinal sectional images and layer-by-layer images, using the gray-level co-occurrence matrix (GLCM). Subsequently, machine learning (ML) models such as Support Vector Regression (SVR), XGBoost, and LightGBM were employed to predict product properties and compare their performance. The experimental results indicated stronger correlations between process parameters and textural features in longitudinal section images compared to layer-by-layer ones. Moreover, the models demonstrated high predictive accuracy, particularly XGBoost and LightGBM, with R² score approaching 0.9 for all properties. These findings highlight the superiority and feasibility of the proposed approach. Furthermore, this method shows potential for accurately predicting a variety of product properties, fulfilling the needs of multiple application scenarios.

Abstract: The control of furnaces for heat treatment is a result of the permanent efforts to help work by amplifying of this capacity in solving problems of productions. The advanced system for conducting the furnaces of heat treatments has the main importance in different activities developed in hard conditions. The electric furnaces heat treatment is aimed primarily at obtaining specific temperature profile characteristic type of heat treatment imposed by technology, the heat treatments applied to heat-sensitive parts with complex configuration of alloy or operating in demanding work environments or arrangements often require temperature the furnace is kept constant with maximum deviations of 2 ÷ 3 °C above the prescribed manufacturing technology. Resolving these conditions requires accurate tracking of the desired temperature profile, goal difficult to achieve with conventional control algorithms. In this scientific work will be shown how to solve complex problems of driving an electric furnace heat treatment using the thermo regulators with algorithms type PID (proportional-integral-derivative controller ) and PID-predictive (proportional-integral-derivative - predictive controller)

Abstract: Traditionally, the discovery of new materials has been the result of a trial and error process. This has resulted in an extremely time-consuming and expensive process. Models for guiding the discovery of new materials have been developed within the European Accelerated Metallurgy project. The application of statistical techniques to large materials datasets has lead to the discovery of unexpected regularities among their properties. This work focuses on mechanical properties. In particular, the interplay between yield strength, ultimate tensile strength and elongation. A methodology based on principal component analysis, and Kocks-Mecking modelling has led to a tool for finding optimal compositional and heat treatment scenarios. The model is first presented for wide ranges of alloys, and the application to the discovery of new magnesium and ferrous alloys is outlined.

Abstract: Based on the full process 3D elastic-plastic thermal mechanical coupled simulation of large size H-Beam, the relevant issues about the residual stress distribution of H-Beam has been systematically analyzed, which include the formation and control of residual stress. In addition, based on the conclusion of the large size H-Beam residual stress analysis, the method of cooling for the control of residual stress has been provided and experiments about the outside cooling of the flange has been implemented. The result of the experiments proved that the coercive water cooling for the outside surface of flange largely reduced the residual stress of the web, which can avoid the web wave after cooling and crack phenomenon during utility. At the same time, on the basis of the whole rolling process finite element simulations, with the help of model of austenite evolution, phase transition and microstructure and property prediction, the simulation of 3D microstructure evolution and property prediction has been fulfilled. By means of microstructure research, it has been proved that the simulation result meet the genuine microstructure very well, which has revealed the feasibility of this method.

Abstract: Powder Metallurgy (PM) component properties are influenced by the pore morphology, size, size-distribution and pore content [1]. Structural alloy Astaloy LH mechanical properties are characterized for density range 6.3 to 7.1 g/cm3. Porosity characterization of the material is also done using ASTM standard. In the first phase, an attempt is made to predict the tensile property using Gurson-Tvergaard-Needleman (GTN) model and FEM. The prediction is verified with tensile test results. It is observed that after fine tuning the parameters in the model, the prediction is found to be close to experimental values.

Abstract: The microstructures of materials determine their properties. Micromechanics is one of the effective methods by which the quantitative relationship between the microstructure of the material and macroscopical mechanical properties can be established. In this paper, the mechanical properties of matrix phase from two different MgO-C refractories were predicted by using micromechanics model. Then, the predicted results were explained based on their different microstructures and compositions. It was proved that the method provides a new approach for researching the mechanical properties of refractories.

Abstract: A novel numerical approach for testing and evaluation of quenching media and quenching systems is outlined. The technique proposed is based on determination of heat transfer coefficient from temperature signals recorded and applying it as input for simulation of quenching process. The evaluation method is based on the calculated microstructural and mechanical properties of cylindrical samples.