Identifying damage mechanisms of composites by acoustic emission and supervised machine learning
Acoustic emission (AE) is a well-established technique for in-situ damage analysis of composite materials. The main challenge, however, is to be able to correlate the measured AE signals with their respective damage mechanism sources. Hence, an innovative approach to classify AE signals based on sup...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-03-01
|
| Series: | Materials & Design |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0264127523001600 |
| _version_ | 1827974699966005248 |
|---|---|
| author | Renato S.M. Almeida Marcelo D. Magalhães Md Nurul Karim Kamen Tushtev Kurosch Rezwan |
| author_facet | Renato S.M. Almeida Marcelo D. Magalhães Md Nurul Karim Kamen Tushtev Kurosch Rezwan |
| author_sort | Renato S.M. Almeida |
| collection | DOAJ |
| description | Acoustic emission (AE) is a well-established technique for in-situ damage analysis of composite materials. The main challenge, however, is to be able to correlate the measured AE signals with their respective damage mechanism sources. Hence, an innovative approach to classify AE signals based on supervised machine learning is presented in this work. At first, the constituents of a composite (fiber, matrix and interface) are characterized separately and fingerprint information regarding the characteristic AE features of each damage mechanism is gathered. This dataset is then used to train a model based on the k-nearest neighbors algorithm. Model accuracy is calculated to be 88%. Subsequently, AE signals measured during tensile tests of commercial composites are classified by the trained model. The analysis provides important information regarding location, time, frequency and intensity of each damage mechanism. Matrix cracking and fiber debonding are the most frequent damage mechanisms representing around 40% and 20% of the measured AE hits. Nevertheless, fiber breakage is the mechanism that dissipates the most AE energy (40%) for the studied composite. Furthermore, the presented method can also be applied together with other techniques like computer tomography, delivering a powerful approach to understand different multi-phase materials. |
| first_indexed | 2024-04-09T19:58:34Z |
| format | Article |
| id | doaj.art-5f998a5d77244a7d9b7bc8fcc8b1f084 |
| institution | Directory Open Access Journal |
| issn | 0264-1275 |
| language | English |
| last_indexed | 2024-04-09T19:58:34Z |
| publishDate | 2023-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Materials & Design |
| spelling | doaj.art-5f998a5d77244a7d9b7bc8fcc8b1f0842023-04-03T05:20:54ZengElsevierMaterials & Design0264-12752023-03-01227111745Identifying damage mechanisms of composites by acoustic emission and supervised machine learningRenato S.M. Almeida0Marcelo D. Magalhães1Md Nurul Karim2Kamen Tushtev3Kurosch Rezwan4Advanced Ceramics, University of Bremen, Bremen 28359, Germany; Corresponding authors.Advanced Ceramics, University of Bremen, Bremen 28359, Germany; Department of Mechanical Engineering, Federal University of Santa Catarina, Florianópolis, BrazilAdvanced Ceramics, University of Bremen, Bremen 28359, GermanyAdvanced Ceramics, University of Bremen, Bremen 28359, Germany; Corresponding authors.Advanced Ceramics, University of Bremen, Bremen 28359, Germany; MAPEX - Center for Materials and Processes, University of Bremen, Bremen 28359, GermanyAcoustic emission (AE) is a well-established technique for in-situ damage analysis of composite materials. The main challenge, however, is to be able to correlate the measured AE signals with their respective damage mechanism sources. Hence, an innovative approach to classify AE signals based on supervised machine learning is presented in this work. At first, the constituents of a composite (fiber, matrix and interface) are characterized separately and fingerprint information regarding the characteristic AE features of each damage mechanism is gathered. This dataset is then used to train a model based on the k-nearest neighbors algorithm. Model accuracy is calculated to be 88%. Subsequently, AE signals measured during tensile tests of commercial composites are classified by the trained model. The analysis provides important information regarding location, time, frequency and intensity of each damage mechanism. Matrix cracking and fiber debonding are the most frequent damage mechanisms representing around 40% and 20% of the measured AE hits. Nevertheless, fiber breakage is the mechanism that dissipates the most AE energy (40%) for the studied composite. Furthermore, the presented method can also be applied together with other techniques like computer tomography, delivering a powerful approach to understand different multi-phase materials.http://www.sciencedirect.com/science/article/pii/S0264127523001600Acoustic emissionDamage mechanismsSupervised classificationStructural health monitoringCeramic matrix composites |
| spellingShingle | Renato S.M. Almeida Marcelo D. Magalhães Md Nurul Karim Kamen Tushtev Kurosch Rezwan Identifying damage mechanisms of composites by acoustic emission and supervised machine learning Materials & Design Acoustic emission Damage mechanisms Supervised classification Structural health monitoring Ceramic matrix composites |
| title | Identifying damage mechanisms of composites by acoustic emission and supervised machine learning |
| title_full | Identifying damage mechanisms of composites by acoustic emission and supervised machine learning |
| title_fullStr | Identifying damage mechanisms of composites by acoustic emission and supervised machine learning |
| title_full_unstemmed | Identifying damage mechanisms of composites by acoustic emission and supervised machine learning |
| title_short | Identifying damage mechanisms of composites by acoustic emission and supervised machine learning |
| title_sort | identifying damage mechanisms of composites by acoustic emission and supervised machine learning |
| topic | Acoustic emission Damage mechanisms Supervised classification Structural health monitoring Ceramic matrix composites |
| url | http://www.sciencedirect.com/science/article/pii/S0264127523001600 |
| work_keys_str_mv | AT renatosmalmeida identifyingdamagemechanismsofcompositesbyacousticemissionandsupervisedmachinelearning AT marcelodmagalhaes identifyingdamagemechanismsofcompositesbyacousticemissionandsupervisedmachinelearning AT mdnurulkarim identifyingdamagemechanismsofcompositesbyacousticemissionandsupervisedmachinelearning AT kamentushtev identifyingdamagemechanismsofcompositesbyacousticemissionandsupervisedmachinelearning AT kuroschrezwan identifyingdamagemechanismsofcompositesbyacousticemissionandsupervisedmachinelearning |