Performance Comparison of Parametric and Non-Parametric Regression Models for Uncertainty Analysis of Sheet Metal Forming Processes

Abstract

This work aims to compare the performance of various parametric and non-parametric metamodeling techniques when applied to sheet metal forming processes. For this, the U-Channel and the Square Cup forming processes were studied. In both cases, three steel grades were considered, and numerical simulations were performed, in order to establish a database for each combination of forming process and material. Each database was used to train and test the various metamodels, and their predictive performances were evaluated. The best performing metamodeling techniques were Gaussian processes, multi-layer perceptron, support vector machines, kernel ridge regression and polynomial chaos expansion.

Poly(vinylidene fluoride) electrospun nonwovens morphology: Prediction and optimization of the size and number of beads on fibers through response surface methodology and machine learning regressions

“…These regressors have been used in several applications with great performance, 40 and they have outperformed RSM in some studies. 41 Electrospinning is a good candidate for these tools because of the large number of experimental parameters and the difficulty to theoretically predict their effect on the response variables or targets. Also, to reduce the number of tests necessary to optimize the output.…”

“…These regressors have been used in several applications with great performance, 40 and they have outperformed RSM in some studies. 41…”

Numerical study of the square cup stamping process: a stochastic analysis

“…For these reasons, the stochastic modelling and uncertainties quantification of sheet metal forming processes are of current industrial interest. In recent years, several researchers have modelled the influence of the uncertainty sources on the final product variability, by resorting to Monte Carlo method [3,4], design of experiences techniques [5,6] and metamodels [7,8].…”

“…With this knowledge it is expected to identify the uncertainty factors that most affect the results in different regions of the cup, and that are essential to control in order to guarantee product conformity with the intended requirements. Additionally, this work intends to fill the lack of research studies associated with the variability of the square cup benchmark, which is one of the most used test cases [7,[14][15][16][17].…”

Machine Learning-Based Models for the Estimation of the Energy Consumption in Metal Forming Processes

“…In the literature, machine learning algorithms have been already applied to various manufacturing topics, such as for the prediction of joint strength of ultrasonic welding processes [22], to estimate the tool wear in milling operations [23], to diagnose the dimensional variation of additive manufactured parts [24], to classify the cutting phase of the natural fiber reinforced plastic composites [25] and to predict the tool life in the micro-milling process [26]. More recently, Wang et al [27] developed a deep learning-based algorithm for the recognition of the defects in the strip rolling process, Marques et al [28] investigated the performances of parametric and non-parametric models for the correlation of process and material variables to springback and wall thinning, Palmieri et al [29] defined a metamodel to correlate the process parameters and key-quality indicators for the optimization of the blank-holding forces in the stamping process, and Winiczenko [30] utilized a hybrid response surface methodology combined with a genetic algorithm to simulate and optimize the friction welding parameters in AISI 1020-ASTM A536 joints.…”