21 documents found, page 1 of 3
Predicting edge cracking in sheet metal forming: evaluating machine learning mo...
Contente, José; Prates, PedroThis work evaluates the performance of machine learning algorithms in predicting the strain values at which edge cracking occurs in sheet metal forming. Four regression models—Extreme Gradient Boosting, multilayer perceptron, support vector regression, and Gaussian processes—were tested, alongside two ensemble methods: majority voting and stacking. The models were trained and tested using a dataset of mechanica...
Application of recurrent neural networks in uncertainty analysis of sheet metal...
Cruz, Daniel; Parreira, Tomás; Marques, Armando; Prates, Pedro; Oliveira, Marta; Neto, Diogo; Santos, Abel; Amaral, Rui; Barbosa, Manuel; Pereira, AndréThe quality of deep-drawn sheet metal components can be strongly influenced by different sources of uncertainty, such as variations in process conditions, deviations in tool geometry, and variations in material properties between coils. Identifying the underlying causes of forming defects remains a challenging and time-consuming task due to the complexity of the forming process. This study presents a machine le...
Limitations of XGBoost in predicting material parameters for complex constituti...
Prates, Pedro; Mitreiro, Dário; Andrade-Campos, AntónioMachine learning models, particularly Extreme Gradient Boosting, have been explored for predicting material parameters in constitutive models that describe the plastic behaviour of metal sheets. While effective for simple constitutive models like Hill’48, their performance declines with more complex models such as the Cazacu-Plunckett-Barlat yield criterion. This study examines the influence of training dataset...
Sensitivity Analysis of the Square Cup Forming Process Using PAWN and Sobol Ind...
Parreira, Tomás G.; Rodrigues, Diogo C.; Oliveira, Marta C.; Sakharova, Nataliya A.; Prates, Pedro; Pereira, André F. G.This study investigates the sensitivity of the square cup forming process. It analyses how the uncertainties in the material properties, friction and process conditions affect the results of the square cup, such as equivalent plastic strain, geometry change, thickness reduction, punch force and springback. The cup flange and the die curvature region are identified as highly affected areas, while the cup bottom ...
Influence of data filtering and noise on the calibration of constitutive models...
Prates, Pedro; Pinto, José; Marques, João; Henriques, João; Pereira, André; Andrade-Campos, AntónioThis work focuses on predicting material parameters that describe the plastic behaviour of metallic sheets using the XGBoost machine learning algorithm, with a dual focus on the influence of data filtering and data noise. A dataset was populated with finite element simulation results of cruciform tensile tests, including strain field data during the test. Different noise levels were added to the strain-related ...
Influence of the sheet thickness variability on the deep drawing of a cylindric...
Pereira, André; Prates, Pedro; Parreira, Tomás; Oliveira, MartaSheet metal forming processes are widely used in industry. The quality of formed parts can be significantly affected by various sources of uncertainty inevitably associated with the forming process. The objective of this work is to quantify the influence of thickness variability on the forming process of a cylindrical cup. Using numerical simulation, the influence of the sheet thickness variance on the evolutio...
VForm-xSteels: virtual materials database
Andrade-Campos, António; Campos, Afonso; Henriques, João; Filho, Lucius; Túlio, Marcos; Conde, Mariana; Gonçalves, Mafalda; Prates, PedroNowadays, most of the product designs rely on the aid of simulation software, particularly Finite Element Analysis (FEA) programs. However, an accurate simulation requires a proper virtual/numerical material behavior reproduction, meaning a precise material characterization through constitutive models and their parameters. To numerically characterize a material, particularly a metal, (i) experimental tests, (ii...
SecFL – Secure Federated Learning Framework for predicting defects in sheet met...
Dib, Mario Alberto da Silveira; Prates, Pedro; Ribeiro, BernardeteWith the ongoing digitization of the manufacturing industry and the ability to bring together data from specific manufacturing processes, there is enormous potential to use machine learning (ML) techniques to improve such processes. In this context, the competitive automotive industry can take advantage of the ML power by predicting defects before they occur, aiming to reduce the scrap rate and increase the rob...
Effect of L‐T and S‐T orientations on fatigue crack growth in an aluminum 7050‐...
Borges, Micael F.; Antunes, Fernando V.; Jesus, Joel; Branco, Ricardo; Prates, Pedro; Neto, Diogo M.This study is focused on the anisotropic fatigue crack growth (FCG) behavior of an aluminum AA7050-T7451 plate. L-T and S-T orientations were studied in M(T) samples with W = 50 mm, in mode I loading, with R-ratio of +0.05. A numerical approach was used, assuming that crack tip plastic strain is the crack driving force. A purely kinematic elastic–plastic model was calibrated using experimental data from low cyc...
Recent advances and applications of machine learning in metal forming processes
Prates, Pedro; Pereira, AndréSem resumo disponível.