journal article·2020-09Open access

Knowledge based data boosting exposition on CNT-engineered carbon composites for machine learning

Sunil Chandrakant Joshi

Abstract

Machine learning (ML) is useful in predictive analytic or prognostic modeling for materials and engineering. It is, however, challenging to gather sufficient and representative data. Experiments are possible only in small numbers due to specialty materials, manufacturing, infrastructure, and testing involved. Simulation and numerical models need skills and appropriate validation. If the dataset at hand is too small in size to train ML, professionals tend to create synthetic data, which may not necessarily meet the quality required of the new data. A Knowledge-based Data Boosting (KDB) process, named COMPOSITES, that rationally addresses data sparsity without losing data quality is systematically discussed in this paper. A study on inter-ply fracture toughness of carbon nanotube (CNT)-engineered carbon fiber reinforced polymer (CFRP) composite laminates is used to demonstrate the KDB process. This involved strengthening of inter-ply interfaces using CNT advocated for improving delamination resistance of the CFRP composites. It is demonstrated that the KDB process helped augment the dataset reliably and improved the best fit regression lines. The process also made it possible to define boundaries and limitations of the augmented dataset. Such sanitized dataset is certainly valuable for prognostic modeling.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Ultrasonics and Acoustic Wave Propagation · Smart Materials for Construction · Thermography and Photoacoustic Techniques

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (22)

Show source-provided references
1. Chen CT, Gu G (2019) Machine learning for composite materials. MRS Communications 9(2):556–566. https://doi.org/10.1557/mrc.2019.3210.1557/mrc.2019.32 ↗
2. Sherman S, Simmons J, Przybyla C (2019) Mesoscale characterization of continuous fiber reinforced composites through machine learning: fiber chirality. Acta Mater 181:447–459. https://doi.org/10.1016/j.actamat.2019.10.00110.1016/j.actamat.2019.10.001 ↗
3. Sharp M, Ak R, Hedberg T (2018) A survey of the advancing use and development of machine learning in smart manufacturing. J Manuf Syst 48(C):170–179. https://doi.org/10.1016/j.jmsy.2018.02.00410.1016/j.jmsy.2018.02.004 ↗
4. Escobar CA, Morales-Menendez R, (2018) Machine learning techniques for quality control in high conformance manufacturing environment, Adv Mech Eng 10 (2). https://doi.org/10.1177/168781401875551910.1177/1687814018755519 ↗
5. Fernandes H, Zhang H, Figueiredo A, Malheiros FIL, Sfarra S, Ibarra-Castanedo C et al (2018) Machine learning and infrared thermography for fiber orientation assessment on randomly-oriented strands parts. Sensors 18(1):288. https://doi.org/10.3390/s1801028810.3390/s18010288 ↗
6. Pathan MV, Ponnusami SA, Pathan J, Pitisongsawat R, Erice B, Petrinic N et al (Sep 2019) Predictions of the mechanical properties of unidirectional fibre composites by supervised machine learning. Sci Rep 9:13964. https://doi.org/10.1038/s41598-019-50144-w10.1038/s41598-019-50144-w ↗
7. Bunker RP, Fadi T (2019) A machine learning framework for sport result prediction. Appl Comp Inform 15(1):27–33. https://doi.org/10.1016/j.aci.2017.09.00510.1016/j.aci.2017.09.005 ↗
8. Abueidda DW, Almasri M, Ammourah R, Ravaioli U, Jasiuk IM, Sobh NA (2019) Prediction and optimization of mechanical properties of composites using convolutional neural networks. Compos Struct 227:111264. https://doi.org/10.1016/j.compstruct.2019.11126410.1016/j.compstruct.2019.111264 ↗
9. Chen L, Tran H, Batra R, Kim C, Ramprasad R (2019) Machine learning models for the lattice thermal conductivity prediction of inorganic materials. Comput Mater Sci 170:109155. https://doi.org/10.1016/j.commatsci.2019.10915510.1016/j.commatsci.2019.109155 ↗
10. (2019) Machine learning algorithms in 7 days, Video by Sengupta S, 1st edition, Safari, an O’Reilly Media Company. https://subscription.packtpub.com/video/big_data_and_business_intelligence/9781789800289. Accessed 13 Jul 2020
11. Bisong EO, (2019) Building machine learning and deep learning models on google cloud platform: a comprehensive guide for beginners, Chapter 14, Principles of learning, Apress, Berkeley, 176. https://doi.org/10.1007/978-1-4842-4470-8_1410.1007/978-1-4842-4470-8_14 ↗
12. Surendra H, Mohan HS (2017) A review of synthetic data generation methods for privacy preserving data publishing. Int J Sci Technol Res 6(3):95–101. https://www.ijstr.org/final-print/mar2017/A-Review-Of-Synthetic-Data-Generation-Methods-For-Privacy-Preserving-Data-Publishing.pdf. Accessed 13 Jul 2020
13. Mikołajczyk A, Grochowski M, (2018) Data augmentation for improving deep learning in image classification problem, 2018. International Interdisciplinary PhD Workshop, Swinoujście, pp 117–122. https://ieeexplore.ieee.org/document/8388338. Accessed 13 Jul 202010.1109/IIPHDW.2018.8388338 ↗
14. Joshi SC, COMPOSITES, (2020) A pragmatic knowledge-based engineering data boosting process, Open Access Journal of Engineering Sciences. https://springfieldpublishers.com/journal-of-engineering-sciences/pdf/OAES.MS.ID.000101.pdf. Accessed 13 Jul 2020
15. Boon YD, Joshi SC (2020) A review of methods for improving interlaminar interfaces and fracture toughness of laminated composites. Mater Today Commun 22:100830. https://doi.org/10.1016/j.mtcomm.2019.10083010.1016/j.mtcomm.2019.100830 ↗
16. Dikshit V, Bhudolia S, Joshi SC (2017) Multiscale polymer composites: a review of the interlaminar fracture toughness improvement. Fibers 5(4):38. https://doi.org/10.3390/fib504003810.3390/fib5040038 ↗
17. Dikshit V, (2014) Manufacturing and performance studies of laminated composites with nano-reinforced inter-ply interfaces, PhD Thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/63276
18. Joshi SC, Dikshit V (2011) Enhancing interlaminar fracture characteristics of woven CFRP prepreg composites through CNT dispersion. J Compos Mater. https://doi.org/10.1177/002199831141047210.1177/0021998311410472 ↗
19. Dikshit V, Joshi SC, (2020) Manufacturing of multiscale interlaminar interface composites and quantitative analysis of interlaminar fracture toughness, Chapter 12, Fiber-reinforced nanocomposites: fundamentals and applications, 261-278. https://doi.org/10.1016/B978-0-12-819904-6.00012-810.1016/B978-0-12-819904-6.00012-8 ↗
20. Bustero I, Gaztelumendi I, Obieta I, Mendizabal MA, Zurutuza A, Ortega A, Alonso B (2020) Free-standing graphene films embedded in epoxy resin with enhanced thermal properties. Adv Composit Hybrid Mater 3:31–40. https://doi.org/10.1007/s42114-020-00136-610.1007/s42114-020-00136-6 ↗
21. ASTM (2013) D5528–13, standard test method for mode I interlaminar fracture toughness of unidirectional fiber-reinforced polymer matrix composites. ASTM International, West Conshohocken https://www.astm.org/Standards/D5528
22. Numerical methods, by Babu Ram, Pearson India, 2010, ISBN: 9788131732212. https://www.worldcat.org/title/numerical-methods/oclc/1024277468. Accessed 13 Jul 2020