Abstract
Composite structures in transportation industries have gained significant attention due to their unique characteristics, including high energy absorption. Non-destructive testing methods coupled with machine learning techniques offer valuable insights into failure mechanisms by analyzing basic parameters. In this study, damage monitoring technologies for composite tubes experiencing progressive damage were investigated. The challenges associated with quantitative failure monitoring were addressed, and the Genetic K-means algorithm, hierarchical clustering, and artificial neural network (ANN) methods were employed along with other three alternative methods. The impact characteristics and damage mechanisms of composite tubes under axial compressive load were assessed using Acoustic Emission (AE) monitoring and machine learning.Various failure modes such as matrix cracking, delamination, debonding, and fiber breakage were induced by layer bending. An increase in fibers/matrix separation and fiber breakage was observed with altered failure modes, while matrix cracking decreased Signal classification was achieved using hierarchical and K-means genetic clustering methods, providing insights into failure mode frequency ranges and corresponding amplitude ranges. The ANN model, trained with labeled data, demonstrated high accuracy in classifying data and identifying specific failure mechanisms. Comparative analysis revealed that the Random Forest model consistently outperformed the ANN and Support Vector Machine (SVM) models, exhibiting superior predictive accuracy and classification using ACC, MCC and F1-Score metrics. Moreover, our evaluation emphasized the Random Forest model's higher true positive rates and lower false positive rates. Overall, this study contributes to the understanding of model selection, performance assessment in machine learning, and failure detection in composite structures.
Similar content being viewed by others
Data Availability Statements
The authors can confirm that all data generated or analyzed during this study are included in the article and/or its supplementary information files.
References
Thirumavalavan, K., Sarukasan, D.: Experimental investigation on multi-layered filament wound basalt/E-glass hybrid fiber composite tubes. Mater. Res. Express. 9(4), (2022)
Bani Mohammad Ali, A., Alimirzaei, S., Ahmadi Najafabadi, M.: Evaluation of damage of filament wound composite tubes under lateral loading by acoustic emission method and finite element simulation. Modares. Mech. Eng. 22(11), 647–655 (2022)
Mohamad, F., Hossein, H., Farzad, P., Ahmadi Najaf Abadi, M.: Composite materials damage characterization under quasi-static 3-point bending test using fuzzy C-means clustering. Appl. Mech. Mater. Trans. Tech. Publ. 1221–1228 (2012)
Ameur, M.B., El Mahi, A., Rebiere, J.-L., Gimenez, I., Beyaoui, M., Abdennadher, M., Haddar, M.: Investigation and identification of damage mechanisms of unidirectional carbon/flax hybrid composites using acoustic emission. Eng. Fract. Mech. 216, 106511 (2019)
Beheshtizadeh, N., Mostafapour, A., Davoodi, S.: Three point bending test of glass/epoxy composite health monitoring by acoustic emission. Alex. Eng. J. 58(2), 567–578 (2019)
Jung, K.-C., Chang, S.-H.: Advanced deep learning model-based impact characterization method for composite laminates. Compos. Sci. Technol. 207, 108713 (2021)
Azizian, M., Almeida, J.H.S., Jr.: Stochastic, probabilistic and reliability analyses of internally-pressurised filament wound composite tubes using artificial neural network metamodels. Mater. Today Commun. 31, 103627 (2022)
Šofer, M., Cienciala, J., Fusek, M., Pavlíček, P., Moravec, R.: Damage analysis of composite CFRP tubes using acoustic emission monitoring and pattern recognition approach. Materials 14(4), 786 (2021)
Park, D., Jung, J., Gu, G.X., Ryu, S.: A Generalizable and Interpretable Deep Learning Model to Improve the Prediction Accuracy of Strain Fields in Grid Composites. Mater. Des. 111192 (2022)
Cui, R., Azuara, G., Lanza di Scalea, F., Barrera, E.: Damage imaging in skin-stringer composite aircraft panel by ultrasonic-guided waves using deep learning with convolutional neural network. Struct. Health Monit. 21(3), 1123–1138 (2022)
Kinga, D., Baadam, J.: A method for stochastic optimization, vol. 5, p. 6. International conference on learning representations (ICLR) (2015)
Seventekidis, P., Giagopoulos, D.: A combined finite element and hierarchical Deep learning approach for structural health monitoring: Test on a pin-joint composite truss structure. Mech. Syst. Signal Process. 157, 107735 (2021)
Lyu, J., Akhavan, J., Manoochehri, S.: Image-based dataset of artifact surfaces fabricated by additive manufacturing with applications in machine learning. Data Brief 41, 107852 (2022)
Lyu, J., Akhavan Taheri Boroujeni, J., Manoochehri, S.: In-situ laser-based process monitoring and in-plane surface anomaly identification for additive manufacturing using point cloud and machine learning, International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. Ame. Soc. Mech. Eng. V002T02A030 (2021)
Azimirad, V., Sotubadi, S.V., Nasirlou, A.: Vision-based Learning: a novel machine learning method based on convolutional neural networks and spiking neural networks, 2021 9th RSI International Conference on Robotics and Mechatronics (ICRoM). IEEE. 192–197 (2021)
Zhao, Y., Noori, M., Altabey, W.A., Ghiasi, R., Wu, Z.: Deep learning-based damage, load and support identification for a composite pipeline by extracting modal macro strains from dynamic excitations. Appl. Sci. 8(12), 2564 (2018)
Alimirzaei, S., Najafabadi, M.A., Nikbakht, A., Pahlavan, L.: Damage mechanism characterization of ±35° and ±55° FW composite tubes using acoustic emission method. 10567895221095603 (2022)
Alimirzaei, S., Ahmadi Najafabadi, M., Nikbakht, A., Pahlavan, L.: Investigation of energy absorption capacity of 3D filament wound composite tubes: experimental evaluation, numerical simulation, and acoustic emission monitoring. Mech. Adv. Mater. Struct. 1–16 (2023)
Saeedifar, M., Zarouchas, D.: Damage characterization of laminated composites using acoustic emission: A review. Compos. B Eng. 195, 108039 (2020)
Yousefi, J., Najfabadi, M.A., Toudeshky, H.H., Akhlaghi, M.: Damage evaluation of laminated composite material using a new acoustic emission Lamb-based and finite element techniques. Appl. Compos. Mater. 25, 1021–1040 (2018)
Fotouhi, M., Suwarta, P., Jalalvand, M., Czel, G., Wisnom, M.R.: Detection of fibre fracture and ply fragmentation in thin-ply UD carbon/glass hybrid laminates using acoustic emission. Compos. A Appl. Sci. Manuf. 86, 66–76 (2016)
Kumar, C.S., Arumugam, V., Sajith, S., Dhakal, H.N., John, R.: Acoustic emission characterisation of failure modes in hemp/epoxy and glass/epoxy composite laminates. J. Nondestr. Eval. 34, 1–11 (2015)
Woo, S.-C., Kim, T.-W.: High-strain-rate impact in Kevlar-woven composites and fracture analysis using acoustic emission. Compos. B Eng. 60, 125–136 (2014)
Nimdum, P., Renard, J.: Use of acoustic emission to discriminate damage modes in carbon fibre reinforced epoxy laminate during tensile and buckling loading, ECCM 15–15th European Conference on Composite Mater. 8 (2012)
Ni, Q.-Q., Iwamoto, M.: Wavelet transform of acoustic emission signals in failure of model composites. Eng. Fract. Mech. 69(6), 717–728 (2002)
Saeedifar, M., Najafabadi, M.A., Zarouchas, D., Toudeshky, H.H., Jalalvand, M.: Clustering of interlaminar and intralaminar damages in laminated composites under indentation loading using Acoustic Emission. Compos. B Eng. 144, 206–219 (2018)
Gutkin, R., Green, C., Vangrattanachai, S., Pinho, S., Robinson, P., Curtis, P.: On acoustic emission for failure investigation in CFRP: Pattern recognition and peak frequency analyses. Mech. Syst. Signal Process. 25(4), 1393–1407 (2011)
Chou, H.-Y., Mouritz, A., Bannister, M., Bunsell, A.R.: Acoustic emission analysis of composite pressure vessels under constant and cyclic pressure. Compos. A Appl. Sci. Manuf. 70, 111–120 (2015)
De Groot, P.J., Wijnen, P.A., Janssen, R.B.: Real-time frequency determination of acoustic emission for different fracture mechanisms in carbon/epoxy composites. Compos. Sci. Technol. 55(4), 405–412 (1995)
Liu, P., Chu, J., Liu, Y., Zheng, J.: A study on the failure mechanisms of carbon fiber/epoxy composite laminates using acoustic emission. Mater. Des. 37, 228–235 (2012)
Ceysson, O., Salvia, M., Vincent, L.: Damage mechanisms characterization of carbon fiber/epoxy composite laminates by both electrical resistance measurements and acoustic emission analysis. Scripta. Materialia. 34(8), (1996)
Bourchak, M., Farrow, I., Bond, I., Rowland, C., Menan, F.: Acoustic emission energy as a fatigue damage parameter for CFRP composites. Int. J. Fatigue 29(3), 457–470 (2007)
Morissette, L., Chartier, S.: The k-means clustering technique: General considerations and implementation in Mathematica. Tutorials in Quantitative Methods for Psychology 9(1), 15–24 (2013)
Hartigan, J.A., Wong, M.A.: Algorithm AS 136: A k-means clustering algorithm. J. R. Stat. Soc. Ser. C Appl. Stat. 28(1), 100–108 (1979)
Murtagh, F.: A survey of recent advances in hierarchical clustering algorithms. Comput. J. 26(4), 354–359 (1983)
Alimirzaei, S., Najafabadi, M.A., Ali, A.B.M.: Investigation of Failure Mechanism of the Composite Tubes Made by Filament Winding Process by Acoustic Emission Method. Amirkabir J. Mech. Eng. 54(6), 1357–1372 (2022)
Boominathan, R., Arumugam, V., Santulli, C., Sidharth, A.A.P., Sankar, R.A., Sridhar, B.: Acoustic emission characterization of the temperature effect on falling weight impact damage in carbon/epoxy laminates. Compos. B Eng. 56, 591–598 (2014)
Mohammadi, M., Saidi, A.R., Jomehzadeh, E.: A novel analytical approach for the buckling analysis of moderately thick functionally graded rectangular plates with two simply-supported opposite edges. Proc. Inst. Mech. Eng. C J. Mech. Eng. Sci. 224(9), 1831–1841 (2010)
Lee, K., Booth, D., Alam, P.: A comparison of supervised and unsupervised neural networks in predicting bankruptcy of Korean firms. Expert Syst. Appl. 29(1), 1–16 (2005)
Funding
This research was not supported by any specific grants from public, commercial, or not-for-profit funding agencies.
Author information
Authors and Affiliations
Contributions
All authors have made significant contributions to the research presented in this manuscript. They have reviewed and approved the contents of the manuscript and have agreed to adhere to ethical standards.
Corresponding author
Ethics declarations
Ethical Approval
This manuscript is an original work and has not been previously submitted, either partially or in full, for publication elsewhere. Furthermore, it has not been simultaneously submitted to multiple publications for consideration.
Conflict of Interest
The authors declared that they have no conflicts of interest in this work.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Bani Mohammad Ali, A., Valizadeh Sotubadi, S., Alimirzaei, S. et al. Quantitative Damage Monitoring of Filament Wound Composites by Using Machine Learning-Based Techniques. Appl Compos Mater 31, 223–247 (2024). https://doi.org/10.1007/s10443-023-10174-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10443-023-10174-0