Reduction of calibration effort in FEM-based optimization via numerical and experimental data fusion

Colosimo, Bianca Maria; Pagani, Luca; Strano, Matteo

doi:10.1007/s00158-014-1149-0

Cited by 6 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this context, recent work focused on the combination (fusion) (e.g. [20]) or automatic deduction (e.g. [21]) of high and low-fidelity models to achieve higher computational speeds while maintaining the required precision.…”

Section: Process Planning and Configuration In Micro Manufacturingmentioning

confidence: 99%

Application of Cause-Effect-Networks for the process planning in laser rod end melting

et al. 2018

View full text Add to dashboard Cite

In micro manufacturing, a precise configuration of manufacturing processes constitutes an essential factor for success. The continuing miniaturization of work pieces results in ever decreasing tolerances, whereas machines and processes become more and more specialized. As a result, a precise determination of each process result is important to guarantee the final product quality. Unfortunately, so called size effects often prevent the direct transfer of knowledge from the area of macro manufacturing. To cope with these effects, finite element simulations provide a suitable tool to simulate forming processes and their results in advance and to perform parameter studies in order to analyze the process and effect interdependencies. Unfortunately, these simulations usually require a rather long computing time, so that only simulations for a small subset of the available parameter range can be performed in a reasonable planning interval. In this context, this article presents an application of the method “Micro – Process Planning and Analysis” (μ-ProPlAn) for the configuration of laser rod end melting, which is used to create preforms for further forming processes. This method uses cause-effect networks, to combine expert knowledge with methods from artificial intelligence to estimate the result of laser melting processes quickly. For this purpose, the cause-effect networks are trained using a finite element simulation of the laser process using different process parameters and varying rod diameters. Results show a high accuracy for the prediction of the finite element simulation results. This article focusses on the validation of these cause-effect networks in comparison to the real laser rod end melting process and demonstrates how these models can be used to predict the resulting volume, eccentricity and the largest diameter of the solidified preform for different process configurations.

show abstract

Section: Process Planning and Configuration In Micro Manufacturingmentioning

confidence: 99%

Application of Cause-Effect-Networks for the process planning in laser rod end melting

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Hierarchical metamodels, based on the fusion of experimental and numerical results, have been recently applied to sheet metal forming problems [20]. These metamodels are called hierarchical, because there is a hierarchy between different data sets: the results of physical experimental tests, though affected by measurement errors and scatter, are a direct representation of the process and are, therefore, high fidelity data (hi-fi).…”

Section: Introductionmentioning

confidence: 99%

Hierarchical Metamodeling of the Air Bending Process

Strano

Semeraro

Iorio³

et al. 2018

Journal of Manufacturing Science and Engineering

Self Cite

View full text Add to dashboard Cite

Despite the tremendous effort of researchers and manufacturing engineers in improving the predictability of the air bending process, there is still a strong need for comprehensive and dependable prediction models. Currently, available modeling approaches all present some relevant limitations in practical applications. In this paper, we propose a new method, which represents an improvement over all existing modeling and prediction techniques. The proposed method can be used for accurate prediction of the main response variables of the air bending process: the angle α after springback and the bend deduction BD. The metamodeling method is based on the hierarchical fusion of different kinds of data: the deterministic low-fidelity response of numerical finite element method (FEM) simulations and the stochastic high fidelity response of experimental tests. The metamodel has been built over a very large database, unprecedented in the scientific literature on air bending, made of more than 500 numerical simulations and nearly 300 experimental tests. The fusion is achieved first by interpolating the FEM simulations with a kriging predictor; then, the hierarchical metamodel is built as a linear regression model of the experimental data, using the kriging predictor among the regressors. The accuracy of the method has been proved using a variant of the leave-one-out cross validation technique. The quality of the prediction yielded by the proposed method significantly over-performs the current prediction of the press brake on-line numerical control.

show abstract