{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T01:22:30Z","timestamp":1772068950037,"version":"3.50.1"},"reference-count":41,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2020,7,17]],"date-time":"2020-07-17T00:00:00Z","timestamp":1594944000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The present article addresses a generation of predictive models that assesses the thickness and length of internal defects in additive manufacturing materials. These modes use data from the application of active transient thermography numerical simulation. In this manner, the raised procedure is an ad-hoc hybrid method that integrates finite element simulation and machine learning models using different predictive feature sets and characteristics (i.e., regression, Gaussian regression, support vector machines, multilayer perceptron, and random forest). The performance results for each model were statistically analyzed, evaluated, and compared in terms of predictive performance, processing time, and outlier sensibility to facilitate the choice of a predictive method to obtain the thickness and length of an internal defect from thermographic monitoring. The best model to predictdefect thickness with six thermal features was interaction linear regression. To make predictive models for defect length and thickness, the best model was Gaussian process regression. However, models such as support vector machines also had significative advantages in terms of processing time and adequate performance for certain feature sets. In this way, the results showed that the predictive capability of some types of algorithms could allow for the detection and measurement of internal defects in materials produced by additive manufacturing using active thermography as a non-destructive test.<\/jats:p>","DOI":"10.3390\/s20143982","type":"journal-article","created":{"date-parts":[[2020,7,17]],"date-time":"2020-07-17T10:22:02Z","timestamp":1594981322000},"page":"3982","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["Predictive Models for the Characterization of Internal Defects in Additive Materials from Active Thermography Sequences Supported by Machine Learning Methods"],"prefix":"10.3390","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9285-7834","authenticated-orcid":false,"given":"Manuel","family":"Rodr\u00edguez-Mart\u00edn","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, Universidad de Salamanca, 37008 Salamanca, Spain"},{"name":"Department of Technology, Universidad Cat\u00f3lica de \u00c1vila, 05005 \u00c1vila, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8680-7010","authenticated-orcid":false,"given":"Jos\u00e9 G.","family":"Fueyo","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Universidad de Salamanca, 37008 Salamanca, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8949-4216","authenticated-orcid":false,"given":"Diego","family":"Gonzalez-Aguilera","sequence":"additional","affiliation":[{"name":"Department of Cartographic and Land Engineering, Universidad de Salamanca, 05003 \u00c1vila, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2853-5977","authenticated-orcid":false,"given":"Francisco J.","family":"Madruga","sequence":"additional","affiliation":[{"name":"Photonics Engineering Group, CIBER-BBN and IDIVAL, Universidad de Cantabria, 39005 Santander, Cantabria, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6345-4825","authenticated-orcid":false,"given":"Roberto","family":"Garc\u00eda-Mart\u00edn","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Universidad de Salamanca, 37008 Salamanca, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0814-1639","authenticated-orcid":false,"given":"\u00c1ngel Luis","family":"Mu\u00f1\u00f3z","sequence":"additional","affiliation":[{"name":"Department of Cartographic and Land Engineering, Universidad de Salamanca, 05003 \u00c1vila, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Javier","family":"Pisonero","sequence":"additional","affiliation":[{"name":"Department of Cartographic and Land Engineering, Universidad de Salamanca, 05003 \u00c1vila, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,7,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1108\/17410381011063996","article-title":"Rapid manufacturing in the spare parts supply chain: Alternative approaches to capacity deployment","volume":"21","author":"Partanen","year":"2010","journal-title":"J. Manuf. Technol. Manag."},{"key":"ref_2","unstructured":"Maldague, X.P. (2001). Theory and Practice of Infrared Technology for Nondestructive Testing, John Wiley & Sons Interscience."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Madruga, F.J., Sfarra, S., Perilli, S., Pivar\u010diov\u00e1, E., and L\u00f3pez-Higuera, J.M. (2020). Measuring the Water Content in Wood Using Step-Heating Thermography and Speckle Patterns-Preliminary Results. Sensors, 20.","DOI":"10.3390\/s20010316"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/j.infrared.2015.03.003","article-title":"Two-stage neural algorithm for defect detection and characterization uses an active thermography","volume":"71","author":"Dudzik","year":"2015","journal-title":"Infrared Phys. Technol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1016\/j.infrared.2015.06.013","article-title":"Prediction of depth model for cracks in steel using infrared thermography","volume":"71","year":"2015","journal-title":"Infrared Phys. Technol."},{"key":"ref_6","first-page":"1","article-title":"Crack-Depth Prediction in Steel Based on Cooling Rate","volume":"2016","year":"2016","journal-title":"Adv. Mater. Sci. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"113872","DOI":"10.1016\/j.applthermaleng.2019.113872","article-title":"Simulation and validation of thermography inspection for components produced by additive manufacturing","volume":"159","author":"Carvalho","year":"2019","journal-title":"Appl. Therm. Eng."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Balageas, D. (2010, January 27\u201330). Thickness or diffusivity measurements from front-face flash experiments using the TSR (thermographic signal reconstruction) approach. Proceedings of the 2010 International Conference on Quantitative InfraRed Thermography, Quebec, QC, Canada.","DOI":"10.21611\/qirt.2010.011"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.infrared.2013.11.011","article-title":"Size determination of subsurface defect by active thermography\u2014Simulation research","volume":"62","author":"Grys","year":"2014","journal-title":"Infrared Phys. Technol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1016\/j.proeng.2016.08.373","article-title":"Characterization of Defects in Curved Composite Structures Using Active Infrared Thermography","volume":"157","author":"Pastuszak","year":"2016","journal-title":"Procedia Eng."},{"key":"ref_11","unstructured":"Abaqus (2019). Analysis User\u2019s Manual Version 2019, Simulia."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1016\/j.infrared.2015.08.006","article-title":"Delamination detection in glass\u2013epoxy composites using step-phase thermography (SPT)","volume":"72","author":"Ghadermazi","year":"2015","journal-title":"Infrared Phys. Technol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1016\/j.ndteint.2009.02.010","article-title":"Numerical modeling for thermographic inspection of fiber metal laminates","volume":"42","author":"Mabrouki","year":"2009","journal-title":"NDT E Int."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.compositesb.2016.09.011","article-title":"Pulsed thermography inspection of adhesive composite joints: Computational simulation model and experimental validation","volume":"106","author":"Grosso","year":"2016","journal-title":"Compos. Part B Eng."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Hardle, W. (1990). Applied Nonparametric Regression, Cambridge University Press (CUP).","DOI":"10.1017\/CCOL0521382483"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.infrared.2012.08.006","article-title":"Analysis of the accuracy of a neural algorithm for defect depth estimation using PCA processing from active thermography data","volume":"56","author":"Dudzik","year":"2013","journal-title":"Infrared Phys. Technol."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Cruz-Vega, I., Hernandez-Contreras, D., Peregrina-Barreto, H., Rangel-Magdaleno, J.D.J., and Ramirez-Cortes, J.M. (2020). Deep Learning Classification for Diabetic Foot Thermograms. Sensors, 20.","DOI":"10.3390\/s20061762"},{"key":"ref_18","unstructured":"Pardo, A., Guti\u00e9rrez-Guti\u00e9rrez, J.A., L\u00f3pez-Higuera, J., Pogue, B.W., and Conde, O.M. (2019). Coloring the Black Box: Visualizing neural network behavior with a self-introspective model (preprint). arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1016\/j.infrared.2016.06.015","article-title":"Non-metallic coating thickness prediction using artificial neural network and support vector machine with time resolved thermography","volume":"77","author":"Wang","year":"2016","journal-title":"Infrared Phys. Technol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"108497","DOI":"10.1016\/j.ijheatfluidflow.2019.108497","article-title":"Using a Gaussian process regression inspired method to measure agreement between the experiment and CFD simulations","volume":"80","author":"Duan","year":"2019","journal-title":"Int. J. Heat Fluid Flow"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"182060","DOI":"10.1109\/ACCESS.2019.2958264","article-title":"Infrared Thermal Imaging-Based Crack Detection Using Deep Learning","volume":"7","author":"Yang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.jmatprotec.2012.08.006","article-title":"Challenges in drop-on-drop deposition of reactive molten nylon materials for additive manufacturing","volume":"213","author":"Fathi","year":"2013","journal-title":"J. Mater. Process. Technol."},{"key":"ref_23","first-page":"64","article-title":"Making sense of 3-D printing: Creating a map of additive manufacturing products and services","volume":"1","author":"Conner","year":"2014","journal-title":"Addit. Manuf."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Farina, I., Singh, N., Colangelo, F., Luciano, R., Bonazzi, G., and Fraternali, F. (2019). High-Performance Nylon-6 Sustainable Filaments for Additive Manufacturing. Materials, 12.","DOI":"10.3390\/ma12233955"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"811","DOI":"10.1007\/s11837-015-1792-y","article-title":"Analysis of Glass-Filled Nylon in Laser Powder Bed Fusion Additive Manufacturing","volume":"68","author":"Slotwinski","year":"2016","journal-title":"JOM"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1108\/13552541111184143","article-title":"The effect of process conditions on mechanical properties of laser-sintered nylon","volume":"17","author":"Starr","year":"2011","journal-title":"Rapid Prototyp. J."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1007\/s12206-016-1212-4","article-title":"Influence of building orientation on the flexural strength of laminated object manufacturing specimens","volume":"31","author":"Olivier","year":"2017","journal-title":"J. Mech. Sci. Technol."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Domingo-Espin, M., Travieso-Rodriguez, J.A., Jerez-Mesa, R., Lluma-Fuentes, J., and Jerez-Mesa, R. (2018). Fatigue Performance of ABS Specimens Obtained by Fused Filament Fabrication. Materials, 11.","DOI":"10.20944\/preprints201811.0225.v1"},{"key":"ref_29","unstructured":"(2020, January 10). Mathworks. MATLAB. Available online: https:\/\/es.mathworks.com\/?s_tid=gn_logo."},{"key":"ref_30","unstructured":"Weka 3 (2012, June 30). Data Mining Software in Java. Available online: http:\/\/www.cs.waikato.ac.nz\/ml\/weka\/."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Berk, R.A. (2016). Statistical Learning from a Regression Perspective, Springer International Publishing.","DOI":"10.1007\/978-3-319-44048-4"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"112665","DOI":"10.1016\/j.cam.2019.112665","article-title":"Gaussian process regression with skewed errors","volume":"370","author":"Alodat","year":"2020","journal-title":"J. Comput. Appl. Math."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"23012","DOI":"10.1088\/0029-5515\/55\/2\/023012","article-title":"Improved profile fitting and quantification of uncertainty in experimental measurements of impurity transport coefficients using Gaussian process regression","volume":"55","author":"Chilenski","year":"2015","journal-title":"Nucl. Fusion"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Rasmussen, C.E., and Williams, C. (2006). Gaussian Processes for Machine Learning, MIT Press.","DOI":"10.7551\/mitpress\/3206.001.0001"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"92","DOI":"10.5539\/mas.v11n8p92","article-title":"Robust Support Vector Regression Model in the Presence of Outliers and Leverage Points","volume":"11","author":"Dhhan","year":"2017","journal-title":"Mod. Appl. Sci."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1016\/j.infrared.2014.12.006","article-title":"Prediction of the solar radiation on the Earth using support vector regression technique","volume":"68","author":"Piri","year":"2015","journal-title":"Infrared Phys. Technol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"14714","DOI":"10.1109\/ACCESS.2019.2891367","article-title":"Weld Bead Detection Based on 3D Geometric Features and Machine Learning Approaches","volume":"7","year":"2019","journal-title":"IEEE Access"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1080","DOI":"10.1016\/j.enconman.2007.09.021","article-title":"Solar radiation modelling using ANNs for different climates in China","volume":"49","author":"Lam","year":"2008","journal-title":"Energy Convers. Manag."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"826","DOI":"10.1016\/j.enconman.2016.08.020","article-title":"Assessment of ANN and SVM models for estimating normal direct irradiation (Hb)","volume":"126","author":"Escobedo","year":"2016","journal-title":"Energy Convers. Manag."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"104320","DOI":"10.1016\/j.cageo.2019.104320","article-title":"Modelling of soil moisture retention curve using machine learning techniques: Artificial and deep neural networks vs support vector regression models","volume":"133","author":"Achieng","year":"2019","journal-title":"Comput. Geosci."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/14\/3982\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:49:25Z","timestamp":1760176165000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/14\/3982"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,17]]},"references-count":41,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2020,7]]}},"alternative-id":["s20143982"],"URL":"https:\/\/doi.org\/10.3390\/s20143982","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,17]]}}}