Abstract
Carbon fiber reinforced polymers (CFRP) are light yet strong composite materials designed to reduce the weight of aerospace or automotive components – contributing to reduced emissions. Resin transfer molding (RTM) is a manufacturing process for CFRP that can be scaled up to industrial-sized production. It is prone to errors such as voids or dry spots, resulting in high rejection rates and costs. At runtime, only limited in-process information can be made available for diagnostic insight via a grid of pressure sensors. We propose FlowFrontNet, a deep learning approach to enhance the in-situ process perspective by learning a mapping from sensors to flow front “images” (using upscaling layers), to capture spatial irregularities in the flow front to predict dry spots (using convolutional layers). On simulated data of 6 million single time steps resulting from 36k injection processes, we achieve a time step accuracy of 91.7% when using a \(38 \times 30\) sensor grid 1 cm sensor distance in x- and y-direction. On a sensor grid of \(10 \times 8\), with a sensor distance of 4 cm, we achieve 83.7% accuracy. In both settings, FlowFrontNet provides a significant advantage over direct end-to-end learning models.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
- 2.
- 3.
Note that we did not use the “air entrapment” feature in PAM-RTM since that would prematurely end simulation runs, produces lagging information, and cause the experimental setup to diverge from the model setup in Leoben.
- 4.
References
Babb, D.A., et al.: Resin transfer molding process for composites (1998)
Darcy, H.P.G.: Les Fontaines publiques de la ville de Dijon. V. Dalamont (1856)
Grössing, H., Stadlmajer, N., Fauster, E., Fleischmann, M., Schledjewski, R.: Flow front advancement during composite processing: predictions from numerical filling simulation tools in comparison with real-world experiments. Polym. Compos. 37(9), 2782–2793 (2016). https://doi.org/10.1002/pc.23474
Heuer, H., et al.: Review on quality assurance along the CFRP value chain - non-destructive testing of fabrics, preforms and CFRP by HF radio wave techniques. Compos. Part B Eng. 77, 494–501 (2015). https://doi.org/10.1016/j.compositesb.2015.03.022
Heywood, J., et al.: On the road toward 2050: report Massachusetts Institute of Technology potential for substantial reductions in light-duty vehicle energy use and greenhouse gas emissions. Massachusetts Institute of Technology (2015). http://mitei.mit.edu/publications/
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Lee, D.H., Lee, W.I., Kang, M.K.: Analysis and minimization of void formation during resin transfer molding process. Compos. Sci. Technol. 66(16), 3281–3289 (2006)
Lee, J., Bagheri, B., Kao, H.A.: A cyber-physical systems architecture for industry 4.0-based manufacturing systems. Manuf. Lett. 3, 18–23 (2015)
Liu, B., Bickerton, S., Advani, S.G.: Modelling and simulation of resin transfer moulding (RTM) - gate control, venting and dry spot prediction. Compos. Part A Appl. Sci. Manuf. 27(2), 135–141 (1996). https://doi.org/10.1016/1359-835X(95)00012-Q
Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: 7th International Conference on Learning Representations, ICLR 2019, November 2019
Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, vol. 2015, pp. 1520–1528, May 2015. https://doi.org/10.1109/ICCV.2015.178
Pantelesis, N., Bistekos, E.: Process monitoring and control for the production of CFRP components. In: SAMPE Conference, pp. 5–9 (2012)
Peng, X.B., Andrychowicz, M., Zaremba, W., Abbeel, P.: Sim-to-real transfer of robotic control with dynamics randomization. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 1–8. IEEE (2018)
Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39, 640–651 (2017). https://doi.org/10.1109/TPAMI.2016.2572683
Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. December 2016, pp. 1874–1883, September 2016. https://doi.org/10.1109/CVPR.2016.207
Shin, H.C., et al.: Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans. Med. Imaging 35(5), 1285–1298 (2016). https://doi.org/10.1109/TMI.2016.2528162
Sorg, C.: Data Mining als Methode zur Industrialisierung und Qualifizierung neuer Fertigungsprozesse für CFK-Bauteile in automobiler Großserienproduktion. Ph.D. thesis, Technische Universität München (2014)
Stieber, S.: Transfer learning for optimization of carbon fiber reinforced polymer production. Organic Computing: Doctoral Dissertation Colloquium 2018, pp. 1–12 (2018)
Stieber, S.: FlowFrontNet Checkpoints (2020). https://doi.org/10.6084/m9.figshare.12102714.v1. https://figshare.com/articles/FlowFrontNet_Checkpoints/12102714
Stieber, S.: FlowFrontNet Data: Sensor to Flowfront/Dryspot (2020). https://doi.org/10.6084/m9.figshare.12063480.v4. https://figshare.com/articles/FlowFrontNet_Data_Sensor_to_Flowfront_Dryspot/12063480
Xu, L., Ren, J.S., Liu, C., Jia, J.: Deep convolutional neural network for image deconvolution. Adv. Neural Inf. Process. Syst. 2(January), 1790–1798 (2014)
Zhang, J., Pantelelis, N.: Modelling and optimisation control of polymer composite moulding processes using bootstrap aggregated neural network models. In: Proceedings of 2011 International Conference on Electric Information and Control Engineering, ICEICE 2011, vol. 1, no. 2, p. 3 (2011). https://doi.org/10.1109/ICEICE.2011.5777841
Acknowledgments
This research is funded by the Bavarian Ministry of Economic Affairs, Regional Development and Energy in the project CosiMo. We thank Ewald Fauster from Montanuniversität Leoben for his expert advice on the RTM process and Frederic Masseria from ESI for supporting our RTM-simulations.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Stieber, S., Schröter, N., Schiendorfer, A., Hoffmann, A., Reif, W. (2021). FlowFrontNet: Improving Carbon Composite Manufacturing with CNNs. In: Dong, Y., Mladenić, D., Saunders, C. (eds) Machine Learning and Knowledge Discovery in Databases: Applied Data Science Track. ECML PKDD 2020. Lecture Notes in Computer Science(), vol 12460. Springer, Cham. https://doi.org/10.1007/978-3-030-67667-4_25
Download citation
DOI: https://doi.org/10.1007/978-3-030-67667-4_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-67666-7
Online ISBN: 978-3-030-67667-4
eBook Packages: Computer ScienceComputer Science (R0)
