{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T09:14:30Z","timestamp":1768295670628,"version":"3.49.0"},"reference-count":35,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T00:00:00Z","timestamp":1736380800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>This study investigates the effectiveness of Artificial Neural Networks (ANNs) in predicting the outcomes of Double Cantilever Beam (DCB) tests, focusing on time and force as input variables and displacement as the predicted output. Three ANN training algorithms\u2014Scaled Conjugate Gradient (SCG), Broyden Fletcher Goldfarb Shanno (BFGS) Quasi-Newton, and Levenberg-Marquardt (LM)\u2014were evaluated based on prediction accuracy and computational efficiency. A parametric study was performed by varying the number of neurons (from 10 to 100) in a single hidden layer to optimize network structure. Among the evaluated algorithms, LM demonstrated superior performance, achieving prediction accuracies of 99.6% for force and 99.3% for displacement. In contrast, SCG exhibited the fastest convergence but had a significantly higher error rate of 8.6%. The BFGS algorithm provided a compromise between accuracy and speed but was ultimately outperformed by LM in terms of overall precision. In addition, configurations with up to 100 neurons were tested, indicating that although slightly lower error rates could be achieved, the increase in computation time was substantial. Consequently, the LM algorithm with 50 neurons delivered the best balance between accuracy and computational cost. These findings underscore the potential of ANNs, particularly LM-based models, to enhance material design processes by providing reliable predictions from limited experimental data, thereby reducing both resource utilization and the time required for testing.<\/jats:p>","DOI":"10.3390\/sym17010091","type":"journal-article","created":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T07:59:42Z","timestamp":1736409582000},"page":"91","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Delamination Prediction in Layered Composites Using Optimized ANN Algorithms: A Comparative Analysis"],"prefix":"10.3390","volume":"17","author":[{"given":"Demet","family":"Balkan","sequence":"first","affiliation":[{"name":"Faculty of Aeronautics and Astronautics, Istanbul Technical University, Istanbul 34467, Turkey"}]}],"member":"1968","published-online":{"date-parts":[[2025,1,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1900143","DOI":"10.1002\/aisy.201900143","article-title":"Artificial Intelligence to Power the Future of Materials Science and Engineering","volume":"2","author":"Sha","year":"2020","journal-title":"Adv. Intell. Syst."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1631\/FITEE.1601885","article-title":"Applications of artificial intelligence in intelligent manufacturing: A review","volume":"18","author":"Li","year":"2017","journal-title":"Front. Inf. Technol. Electron. Eng."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.jmat.2017.08.002","article-title":"Materials discovery and design using machine learning","volume":"3","author":"Liu","year":"2017","journal-title":"J. Materiomics"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"821","DOI":"10.1557\/mrc.2019.95","article-title":"Materials science in the artificial intelligence age: High-throughput library generation, machine learning, and a pathway from correlations to the underpinning physics","volume":"9","author":"Vasudevan","year":"2019","journal-title":"MRS Commun."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1111\/j.1460-2695.2006.00994.x","article-title":"Application of artificial neural network for predicting plain strain fracture toughness using tensile test results","volume":"29","author":"Kang","year":"2006","journal-title":"Fatigue Fract. Eng. Mater. Struct."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.msea.2014.03.043","article-title":"Improvement of fracture toughness of directionally solidified Nb-silicide in situ composites using artificial neural network","volume":"605","author":"Guan","year":"2014","journal-title":"Mater. Sci. Eng. A"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1268","DOI":"10.1016\/j.matpr.2021.06.365","article-title":"Prediction of mechanical properties for polyetheretherketone composite reinforced with graphene and titanium powder using artificial neural network","volume":"49","author":"Zakaulla","year":"2022","journal-title":"Mater. Today Proc."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1027","DOI":"10.1016\/j.ijfatigue.2004.03.009","article-title":"Application of artificial neural network for predicting strain-life fatigue properties of steels on the basis of tensile tests","volume":"26","author":"Genel","year":"2004","journal-title":"Int. J. Fatigue"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"112885","DOI":"10.1016\/j.compstruct.2020.112885","article-title":"Predictive ANN models for varying filler content for cotton fiber\/PVC composites based on experimental load-displacement curves","volume":"254","author":"Kazi","year":"2020","journal-title":"Compos. Struct."},{"key":"ref_10","unstructured":"Gavin, H.P. (2023, April 20). The Levenberg-Marquardt Algorithm for Nonlinear Least Squares. Available online: https:\/\/people.duke.edu\/~hpgavin."},{"key":"ref_11","first-page":"297","article-title":"Improvements to the Levenberg-Marquardt algorithm for nonlinear least-squares minimization","volume":"231","author":"Transtrum","year":"2012","journal-title":"J. Comput. Phys."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Kayri, M. (2016). Predictive Abilities of Bayesian Regularization and Levenberg\u2013Marquardt Algorithms in Artificial Neural Networks: A Comparative Empirical Study on Social Data. Math. Comput. Appl., 21.","DOI":"10.3390\/mca21020020"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.matpr.2022.11.341","article-title":"Modeling of mode 1 delamination behavior in laminated composite structures for aerospace applications","volume":"82","author":"Jadhav","year":"2023","journal-title":"Mater. Today Proc."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.matdes.2004.04.008","article-title":"Artificial neural network based delamination prediction in laminated composites","volume":"26","author":"Chakraborty","year":"2005","journal-title":"Mater. Des."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"586","DOI":"10.1016\/j.compositesb.2018.12.118","article-title":"Structural vibration-based classification and prediction of delamination in smart composite laminates using deep learning neural network","volume":"161","author":"Khan","year":"2019","journal-title":"Compos. Part B Eng."},{"key":"ref_16","first-page":"37","article-title":"Artificial neural network based delamination prediction in composite plates using vibration signals","volume":"63","author":"Sreekanth","year":"2022","journal-title":"Frat. Integrit\u00e0 Strutt."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"116509","DOI":"10.1016\/j.compstruct.2022.116509","article-title":"On the influence of rectangular Z-pins parameters on mode II delamination resistance of through-the-thickness reinforced composites","volume":"305","author":"Bortoluzzi","year":"2023","journal-title":"Compos. Struct."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.matdes.2018.05.049","article-title":"Modelling fatigue delamination growth in fiber-reinforced composites: Power-law equations or artificial neural networks","volume":"155","author":"Allegri","year":"2018","journal-title":"Mater. Des."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"106907","DOI":"10.1016\/j.engfracmech.2020.106907","article-title":"Effect of aspect ratio on dynamic fracture toughness of particulate polymer composite using artificial neural network","volume":"228","author":"Sharma","year":"2020","journal-title":"Eng. Fract. Mech."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"3183","DOI":"10.1007\/s00521-020-05180-3","article-title":"Neural network-based damage identification in composite laminated plates using frequency shifts","volume":"33","author":"Oliver","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Rautela, M., Senthilnath, J., Monaco, E., and Gopalakrishnan, S. (2022). Delamination prediction in composite panels using unsupervised-feature learning methods with wavelet-enhanced guided wave representations. arXiv.","DOI":"10.1016\/j.compstruct.2022.115579"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2397","DOI":"10.1016\/j.eswa.2011.08.087","article-title":"Comparing the performance of neural networks developed by using Levenberg\u2013Marquardt and Quasi-Newton with the gradient descent algorithm for modeling a multiple response grinding process","volume":"39","author":"Mukherjee","year":"2012","journal-title":"Expert Syst. Appl."},{"key":"ref_23","unstructured":"(2015). Standard Test Methods for Constituent Content of Composite Materials (Standard No. ASTM D3171)."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"104103","DOI":"10.1016\/j.tafmec.2023.104103","article-title":"Experimental and numerical investigation on the mode I and mode II interlaminar fracture toughness of nitrogen-doped reduced graphene oxide reinforced composites","volume":"128","year":"2023","journal-title":"Theor. Appl. Fract. Mech."},{"key":"ref_25","unstructured":"(2013). Mode I Interlaminar Fracture Toughness of Unidirectional Fiber-Reinforced Polymer Matrix Composites (Standard No. ASTM D5528)."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Arora, I., and Saha, A. (2016, January 14\u201317). Comparison of back propagation training algorithms for software defect prediction. Proceedings of the 2nd International Conference on Contemporary Computing and Informatics (IC3I), Greater Noida, India.","DOI":"10.1109\/IC3I.2016.7917934"},{"key":"ref_27","first-page":"384","article-title":"Scaled Conjugate Gradient Based Adaptive ANN Control for SVM-DTC Induction Motor Drive","volume":"112","author":"Babani","year":"2016","journal-title":"Neurocomputing"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1016\/S0893-6080(05)80056-5","article-title":"A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning","volume":"6","year":"1993","journal-title":"Neural Netw."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"3000","DOI":"10.1016\/j.neucom.2009.04.006","article-title":"Self-scaled conjugate gradient training algorithms","volume":"72","author":"Kostopoulos","year":"2009","journal-title":"Neurocomputing"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"012020","DOI":"10.1088\/1742-6596\/1188\/1\/012020","article-title":"Parameter estimation of Gumbel distribution using Quasi-Newton Broyden Fletcher Goldfarb Shanno (BFGS) method","volume":"1188","author":"Saputro","year":"2019","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"e2730","DOI":"10.1002\/env.2730","article-title":"Normalization methods for spatio-temporal analysis of environmental performance: Revisiting the Min\u2013Max method","volume":"33","author":"Mazziotta","year":"2022","journal-title":"Environmetrics"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.compstruct.2017.08.079","article-title":"Effect of particle size on mixed-mode fracture of nanographene reinforced epoxy and mode I delamination of its carbon fiber composite","volume":"181","author":"Roy","year":"2017","journal-title":"Compos. Struct."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Karalar, A.B., Soyug\u00fczel, T., and Balkan, D. (2023, January 7\u20139). An Artificial Neural Network Approach to Predict Strain Gauge Results of Unidirectional Laminated Composites\u2019 Tensile Test. Proceedings of the 2023 10th International Conference on Recent Advances in Air and Space Technologies (RAST), Istanbul, Turkey.","DOI":"10.1109\/RAST57548.2023.10197913"},{"key":"ref_34","first-page":"700","article-title":"Multi-response optimization of carbon fiber reinforced polymer (CFRP) drilling using back propagation neural network-particle swarm optimization (BPNN-PSO)","volume":"23","author":"Soepangkat","year":"2020","journal-title":"Eng. Sci. Technol. Int. J."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Rosales, M.A., Palconit, M.G.B., Bandala, A.A., Vicerra, R.R.P., Dadios, E.P., and Calinao, H. (2020, January 16\u201319). Prediction of Total Body Water using Scaled Conjugate Gradient Artificial Neural Network. Proceedings of the 2020 IEEE Region 10 Conference (TENCON), Osaka, Japan.","DOI":"10.1109\/TENCON50793.2020.9293804"}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/1\/91\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T10:25:39Z","timestamp":1759919139000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/1\/91"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,9]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,1]]}},"alternative-id":["sym17010091"],"URL":"https:\/\/doi.org\/10.3390\/sym17010091","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,9]]}}}