Use of Artificial Intelligence in Design, Development, Additive Manufacturing, and Certification of Multifunctional Composites for Aircraft, Drones, and Spacecraft
Source abstract
Abstract
Multifunctional composites provide more than one function from the same part. The anisotropy, material, and process characterization challenges and the lack of standardization on the 3D-printed multifunctional carbon composites make it difficult for application into aerospace. The current solutions for additive manufacturing (AM) technologies and additively manufactured monofunctional and multifunctional composites are not mature enough for safety-critical applications. A new approach is proposed to explore the use of machine learning (ML) in the design, development, AM, testing, and certification of multifunctional composites for aircraft, unmanned aircraft systems (UAS), and spacecraft. In this work, an artificial neural network (ANN) architecture is proposed. An AM-embedded building block approach integrates the complete lifecycle of aircraft, UAS, and spacecraft using ANN to support the continued operational safety (COS) of aircraft, spacecraft, and UAS. The proposed method exploits the power of ANN on the metadata for the characterization of multifunctional material properties and processes and the mapping of the failure modes compared with the predicted models and history. This paper provides an in-depth analysis and explanation of the new methods needed to overcome the existing barriers, problems, and situations.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Additive Manufacturing and 3D Printing Technologies · Manufacturing Process and Optimization · Innovations in Concrete and Construction Materials
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Aerospace Engineering, Hindustan Institute of Technology and Science, Chennai 603103, India
References (47)
Show source-provided references
1. Winston, P.H. (1993). Artificial Intelligence, Addison-Wesley Publishing Company. [3rd ed.].
2. Sheikh, H., Prins, C., and Schrijvers, E. (2023). Artificial Intelligence: Definition and Background, Springer.10.1007/978-3-031-21448-6_2 ↗
3. Dietterich, T. (2010). Introduction to Machine Learning, The MIT Press. [2nd ed.].
4. U.S. DOT FAA (2010). Advisory Circular, AC 20-107B: Composite Aircraft Structure.
5. Roy, M., Tran, P., Dickens, T., and Schrand, A. (2019). Composite Reinforcement Architectures: A Review of Field-Assisted Additive Manufacturing for Polymers. J. Compos. Sci., 4.10.3390/jcs4010001 ↗
6. Stepwise Regression for Increasing the Predictive Accuracy of Artificial Neural Networks: Applications in Benchmark and Advanced Problems10.3390/modelling5010009 ↗
7. Sacco, C., Radwan, A.B., Harik, R., and Van Tooren, M. (2018, January 21–24). Automated fiber placement defects: Automated inspection and characterization. Proceedings of the International SAMPE Technical Conference, Long Beach, CA, USA.
8. Brüning, J., Denkena, B., Dittrich, M.A., and Hocke, T. (2017, January 3–5). Machine Learning Approach for Optimization of Automated Fiber Placement Processes. Proceedings of the Procedia CIRP, Taichung City, Taiwan.10.1016/j.procir.2017.03.295 ↗
9. Narayanan, R.M., Wood, N.S., and Lewis, B.P. (2023). Assessment of Various Multimodal Fusion Approaches Using Synthetic Aperture Radar (SAR) and Electro-Optical (EO) Imagery for Vehicle Classification via Neural Networks. Sensors, 23.10.3390/s23042207 ↗
10. Chauhan, R., Ghanshala, K.K., and Joshi, R.C. (2018, January 15–17). Convolutional Neural Network (CNN) for Image Detection and Recognition. Proceedings of the ICSCCC 2018—1st International Conference on Secure Cyber Computing and Communications, Jalandhar, India.10.1109/ICSCCC.2018.8703316 ↗
11. (2023, April 24). Shervine Amidi Recurrent Neural Networks Cheatsheet (ref. CS 230—Deep Learning). Available online: https://stanford.edu/~shervine/teaching/cs-230/cheatsheet-recurrent-neural-networks.
12. (2023, April 24). MathWorks Recurrent Neural Network (RNN)—Why RNNs Matter. Available online: https://www.mathworks.com/discovery/rnn.html.
13. Ghimire, R., and Liou, F. (2022). Quasi-Static Multifunctional Characterization of 3D-Printed Carbon Fiber Composites for Compressive-Electrical Properties. Polymers, 14.10.3390/polym14020328 ↗
14. Aird, J.A., Barthelmie, R.J., and Pryor, S.C. (2023). Automated Quantification of Wind Turbine Blade Leading Edge Erosion from Field Images. Energies, 16.10.3390/en16062820 ↗
15. Angulo-Saucedo, G.A., Leon-Medina, J.X., Pineda-Muñoz, W.A., Torres-Arredondo, M.A., and Tibaduiza, D.A. (2022). Damage Classification Using Supervised Self-Organizing Maps in Structural Health Monitoring. Sensors, 22.10.3390/s22041484 ↗
16. Ghimire, R., and Liou, F. (2021). Experimental Investigation of Additive Manufacturing of Continuous Carbon Fiber Composites with Multifunctional Electro-Tensile Properties. Materials, 14.10.3390/ma14216574 ↗
17. Ghimire, R., and Liou, F. (2021). Coupled flexural-electrical evaluation of additively manufactured multifunctional composites at ambient temperature. Appl. Sci., 11.10.3390/app11209638 ↗
18. Alhammad, M., Avdelidis, N.P., Ibarra-Castanedo, C., Torbali, M.E., Genest, M., Zhang, H., Zolotas, A., and Maldgue, X.P.V. (2022). Automated Impact Damage Detection Technique for Composites Based on Thermographic Image Processing and Machine Learning Classification. Sensors, 22.10.3390/s22239031 ↗
19. Dabetwar, S., Ekwaro-Osire, S., and Dias, J.P. (2020, January 22–26). Damage detection of composite materials using data fusion with deep neural networks. Proceedings of the ASME Turbo Expo, London, UK.10.1115/1.0003274V ↗
20. Ai, L., Flowers, S., Mesaric, T., Henderson, B., Houck, S., and Ziehl, P. (2023). Acoustic Emission-Based Detection of Impacts on Thermoplastic Aircraft Control Surfaces: A Preliminary Study. Appl. Sci., 13.10.3390/app13116573 ↗
21. Classification and Discrimination of Birds and Small Drones Using Radar Micro-Doppler Spectrogram Images10.3390/signals4020018 ↗
22. Sofos, F., Papakonstantinou, C.G., Valasaki, M., and Karakasidis, T.E. (2023). Fiber-Reinforced Polymer Confined Concrete: Data-Driven Predictions of Compressive Strength Utilizing Machine Learning Techniques. Appl. Sci., 13.10.3390/app13010567 ↗
23. Hrehova, S., and Knapcikova, L. (2022). The Study of Machine Learning Assisted the Design of Selected Composites Properties. Appl. Sci., 12.10.3390/app122110863 ↗
24. Rodríguez-Martín, M., Fueyo, J.G., Gonzalez-Aguilera, D., Madruga, F.J., García-Martín, R., Muñóz, Á.L., and Pisonero, J. (2020). Predictive models for the characterization of internal defects in additive materials from active thermography sequences supported by machine learning methods. Sensors, 20.10.3390/s20143982 ↗
25. Gor, M., Dobriyal, A., Wankhede, V., Sahlot, P., Grzelak, K., Kluczyński, J., and Łuszczek, J. (2022). Density Prediction in Powder Bed Fusion Additive Manufacturing: Machine Learning-Based Techniques. Appl. Sci., 12.10.3390/app12147271 ↗
26. Eltouny, K., Gomaa, M., and Liang, X. (2023). Unsupervised Learning Methods for Data-Driven Vibration-Based Structural Health Monitoring: A Review. Sensors, 23.10.3390/s23063290 ↗
27. Fei, C.-W., Han, Y.-J., Wen, J.-R., Li, C., Han, L., and Choy, Y.-S. (Propuls. Power Res., 2023). Deep learning-based modeling method for probabilistic LCF life prediction of turbine blisk, Propuls. Power Res., in press.10.1016/j.jppr.2023.08.005 ↗
28. ICRA: An Intelligent Clustering Routing Approach for UAV Ad Hoc Networks10.1109/TITS.2022.3145857 ↗
29. TROVE: A Context-Awareness Trust Model for VANETs Using Reinforcement Learning10.1109/JIOT.2020.2975084 ↗
30. Lightweight Trustworthy Message Exchange in Unmanned Aerial Vehicle Networks10.1109/TITS.2021.3136304 ↗
31. Kabashkin, I., Misnevs, B., and Zervina, O. (2023). Artificial Intelligence in Aviation: New Professionals for New Technologies. Appl. Sci., 13.10.3390/app132111660 ↗
32. Shah, C., Bosse, S., and von Hehl, A. (2022). Taxonomy of Damage Patterns in Composite Materials, Measuring Signals, and Methods for Automated Damage Diagnostics. Materials, 15.10.3390/ma15134645 ↗
33. (2023, May 29). Wikipedia Metadata. Available online: https://en.wikipedia.org/wiki/Metadata.
34. Tomblin, J.S., Raju, K.S., Acosta, J.F., Smith, B.L., and Romine, N.A. (2002). DOT/FAA/AR-02/80, Impact Damage Characterization and Damage Tolerance of Composite Sandwich Airframe Structures—Phase II.
35. Ghimire, R. (2008). Local Bending Containment in Sandwich Panels with Subsurface Core Damage, Wichita State University.
36. (2000). Standard Test Method for Tensile Properties of Polymer Matrix Composite Materials (Standard No. ASTM D3039/D3039M—00).
37. Surface roughness prediction in fused deposition modelling by neural networks10.1007/s00170-012-4687-x ↗
38. Smithing, N. (1999). Supervised Learning in Feedforward Artificial Neural Networks, RD Reed RJ Marks, MIT Press.
39. Recent advances and applications of machine learning in solid-state materials science10.1038/s41524-019-0221-0 ↗
40. Sutton, R.S., and Barto, A.G. (2018). Reinforcement Learning: An Introduction, 2en ed., The MIT Press.
41. Artificial neural networks and empirical equations to estimate daily evaporation: Application to Lake Vegoritis, Greece10.1080/02626667.2016.1142667 ↗
42. Aneesh, T., Mohanty, C.P., Tripathy, A.K., Chauhan, A.S., Gupta, M., and Annamalai, A.R. (2023). A Thermo-Structural Analysis of Die-Sinking Electrical Discharge Machining (EDM) of a Haynes-25 Super Alloy Using Deep-Learning-Based Methodologies. Manuf. Mater. Process., 7.10.3390/jmmp7060225 ↗
43. (2023, April 24). Relevancy. Available online: https://en.wikipedia.org/wiki/Relevance.
44. (2023, April 24). False Positive (FP). Available online: https://en.wikipedia.org/wiki/False_positives_and_false_negatives#:~:text=A false positive error%2C or,conviction of an innocent person.
45. (2023, April 24). False Negative (FN). Available online: https://en.wikipedia.org/wiki/False_positives_and_false_negatives#:~:text=A false positive error%2C or,conviction of an innocent person.
46. (2023, April 24). True Positive (TP). Available online: https://en.wikipedia.org/wiki/Sensitivity_and_specificity.
47. (2023, April 24). True Negative (TN). Available online: https://en.wikipedia.org/wiki/Sensitivity_and_specificity.