Distribution & Access For Publication Downloads News About Us Contact Us
Paper Titles
Identification of Swift Law Parameters Using FEMU by a Synthetic Image DIC-Based Approach
p.2211
Integrated Thermomechanical Characterization of Metals Using the Virtual Fields Method
p.2222
On the Design of a Heterogeneous Mechanical Test Using a Nonlinear Topology Optimization Approach
p.2228
Parameter Identification of Swift Law Using a FEMU-Based Approach and an Innovative Heterogeneous Mechanical Test
p.2238
Formability Assessment of Variable Geometries Using Machine Learning - Analysis of the Influence of the Database
p.2247
Parameter Identification and Modeling of Hardening to Preserve Identical Predictions under Monotonic Loading
p.2258
In-Process Monitoring of Springback in Industrial Bending Using a Laser Sensor-Based Method
p.2266
Towards a Hybrid Twin Model to Obtain the Formability of a Car Body Part in Real Time
p.2277
Reduced FFT-Based Simulation of a Mechanically Loaded Clustered Microstructure Using an Adaptive Set of Fourier Modes
p.2285

Formability Assessment of Variable Geometries Using Machine Learning - Analysis of the Influence of the Database

Article Preview

Abstract:

Surrogate modelling has proven to be an effective strategy for time-efficient analysis and optimisation of expensive functions such as manufacturing process simulations. However, most surrogate approaches generate problem-specific “one-off” models, which cannot be reused in other, even similar scenarios. Hence, variations of the problem, e.g. minor geometry changes, instantly invalidate the surrogate. Image-based machine learning (ML) techniques have been proposed as an option to train a surrogate for variable geometries. However, it is currently unclear how to construct a sufficiently diverse set of generic training geometries and what effect different databases have. This work investigates the effect of different databases on the prediction accuracy of an ML-assessment of component manufacturability. The considered use-case is textile forming (draping) of a woven fabric. Sampling plans generate different numbers of training geometries, which are in turn evaluated in draping simulations. An image-based ML-algorithm is trained on these process samples and evaluated on a set of validation geometries. Results show that the diversity of the training geometries has a greater impact on the prediction accuracy than the number of samples. The results also hint that a comparably low number of geometry samples suffices to give meaningful results. With these findings, ML-techniques are considered a promising and time-efficient tool for manufacturability assessment at early stages of part and process design.

By email Full Text Pdf
You might also be interested in these eBooks
Achievements and Trends in Material Forming View Preview

Info:

Periodical:

Key Engineering Materials (Volume 926)

Pages:

2247-2257

DOI:

https://doi.org/10.4028/p-1o0007

Citation:

Cite this paper

Online since:

July 2022

Authors:

Clemens Zimmerling*, Benedikt Fengler, Luise Kärger

Keywords:

Composite Manufacturing, Machine Learning, Surrogate Modelling, Textile Forming

Export:

RIS, BibTeX

Permissions:

Creative Commons CC BY 4.0

* - Corresponding Author

References

[1] D.M. Anderson, Design for Manufacturability: How to Use Concurrent Engineering to Rapidly Develop Low-Cost, High-Quality Products for Lean Production, Taylor & Francis, United Kingdom, (2014).

DOI: 10.1201/b16501

Google Scholar

[2] H.S. Jagdev, J. Browne, J. Keogh, Manufacturing Process Optimisation – A Survey of Techniques, in: B.J. Davies (Eds), Proc. 28th Intl. Matador Conf., Palgrave, London. 1990, pp.205-215.

DOI: 10.1007/978-1-349-10890-9_29

Google Scholar

[3] I. Dostaler, Avoiding rework in product design: evidence from the aerospace industry, Int. J. Qual. Reliab. Manage. 27 (2010) 5–26.

DOI: 10.1108/02656711011009281

Google Scholar

[4] Y. Koren, The Global Manufacturing Revolution: Product-Process-Business Integration and Reconfigurable Systems. Wiley, USA, (2010).

DOI: 10.1002/9780470618813

Google Scholar

[5] L. Kärger, A. Bernath, F. Fritz, S. Galkin, D. Magagnato, A. Oeckerath, K.Wolf, Development and validation of a CAE chain for unidirectional fibre reinforced composite components, Compos. Struct. 132 (2015) 350–358.

DOI: 10.1016/j.compstruct.2015.05.047

Google Scholar

[6] L. Kärger, S. Galkin, C. Zimmerling, D. Dörr, J. Linden, A. Oeckerath, et al., Forming optimisation embedded in a cae chain to assess and enhance the structural performance of composite components, Compos Struct 192 (2018) 143–152.

DOI: 10.1016/j.compstruct.2018.02.041

Google Scholar

[7] S. Chen, L.T. Harper, A. Endruweit, N.A. Warrior, Formability optimisation of fabric preforms by controlling material draw-in through in-plane constraints, Composites Part A 76 (2015) 10–19.

DOI: 10.1016/j.compositesa.2015.05.006

Google Scholar

[8] B. Fengler, M. Schäferling, B. Schäfer, L. Bretz, G. Lanza, B. Hafner, A. Hrymak, L. Kärger, Manufacturing uncertainties and resulting robustness of optimized patch positions on continuous-discontinuous fiber reinforced polymer structures, Compos. Struc. 213, 47-57, (2019).

DOI: 10.1016/j.compstruct.2019.01.063

Google Scholar

[9] S. Koziel, L. Leifsson, Surrogate-based Modeling and Optimization, first ed., Springer, New York, (2013).

Google Scholar

[10] J. Jakumeit, M. Herdy, M. Nitsche, Parameter optimization of the sheet metal forming process using an iterative parallel Kriging algorithm, Structural and Multidisciplinary Optimization (29) (2005), 498-507.

DOI: 10.1007/s00158-004-0455-3

Google Scholar

[11] M.H.A. Bonte, A.H. van den Boogaard, J. Huétink, A Metamodel Based Optimisation Algorithm for Metal Forming Processes, in: Adv. Methods in Material Forming, Springer Berlin/Heidelberg, (2007), 55-72.

DOI: 10.1007/3-540-69845-0_4

Google Scholar

[12] H.Wang, F. Ye, L. Chen, E. Li, Sheet metal forming optimization by using surrogate modeling techniques. Chinese Journal of Mechanical Engineering 30, 22–36, (2017).

DOI: 10.3901/cjme.2016.1020.123

Google Scholar

[13] J. Pfrommer, C. Zimmerling, J. Liu, L. Kärger, F. Henning, J. Beyerer, Optimisation of manufacturing process parameters using deep neural networks as surrogate models, Proc. CIRP 72, 2018, 426–431.

DOI: 10.1016/j.procir.2018.03.046

Google Scholar

[14] C. Zimmerling , P. Schindler, J. Seuffert, L. Kärger, Deep neural networks as surrogate models for time-efficient manufacturing process optimization, Proceedings of ESAFORM 2021, Liège/Belgium, (2021).

DOI: 10.25518/esaform21.3882

Google Scholar

[15] P.M. Horton, J.M. Allwood, C. Cleaver, A. Nagy-Sochacki, An experimental analysis of the relationship between the corner, die and punch radii in forming isolated flanged shrink corners from Al 5251, Journal of Materials Processing Technology 278 (2020) 116486.

DOI: 10.1016/j.jmatprotec.2019.116486

Google Scholar

[16] H.R. Attar, N. Li, A. Foster, A new design guideline development strategy for aluminium alloy corners formed through cold and hot stamping processes, Materials & Design 207, 2021,109856.

DOI: 10.1016/j.matdes.2021.109856

Google Scholar

[17] C. Zimmerling, D. Dörr, F. Henning, L. Kärger, A Machine learning assisted approach for textile formability assessment and design improvement of composite components, Composites Part A 124, (2019).

DOI: 10.1016/j.compositesa.2019.05.027

Google Scholar

[18] G. Misiun, C. Wang, H. Geijselaers, A. van den Boogaard, Interpolation of final geometry and result fields in process parameter space, Numiform 80, 2016, 16010-1 – 16010-6.

DOI: 10.1051/matecconf/20168013006

Google Scholar

[19] X. Guo, W. Li, F. Iorio, Convolutional Neural Networks for Steady Flow Approximation. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data, 2016, 481-490.

DOI: 10.1145/2939672.2939738

Google Scholar

[20] C. Zimmerling, D. Trippe, B. Fengler, L. Kärger, An approach for rapid prediction of textile draping results for variable composite component geometries using deep neural networks, AIP Conf. Proc. 2113, AIP Publishing, (2019).

DOI: 10.1063/1.5112512

Google Scholar

[21] A.I.J. Forrester, A. Sóbester, A.J. Keane, Engineering design via surrogate modelling: A practical guide, Wiley, USA, (2008).

DOI: 10.1002/9780470770801

Google Scholar

[22] K. Hornik, Approximation capabilities of multilayer feedforward networks, Neural Networks 4, 1991, 251–257.

DOI: 10.1016/0893-6080(91)90009-t

Google Scholar

[23] P.S. Mann, Mann's Introductory Statistics, ninth ed., Wiley, Hoboken, (2017).

Google Scholar

Scientific.Net is a registered brand of Trans Tech Publications Ltd
© 2024 by Trans Tech Publications Ltd. All Rights Reserved