Numerical and Experimental Evaluation of Structural Changes Using Sparse Auto-Encoders and SVM Applied to Dynamic Responses
The present work evaluates the deep learning algorithm called Sparse Auto-Encoder (SAE) when applied to the characterization of structural anomalies. This study explores the SAE’s performance in a supervised damage detection approach to consolidate its application in the Structural Health Monitoring...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/24/11965 |
| _version_ | 1797506740433977344 |
|---|---|
| author | Rafaelle Piazzaroli Finotti Flávio de Souza Barbosa Alexandre Abrahão Cury Roberto Leal Pimentel |
| author_facet | Rafaelle Piazzaroli Finotti Flávio de Souza Barbosa Alexandre Abrahão Cury Roberto Leal Pimentel |
| author_sort | Rafaelle Piazzaroli Finotti |
| collection | DOAJ |
| description | The present work evaluates the deep learning algorithm called Sparse Auto-Encoder (SAE) when applied to the characterization of structural anomalies. This study explores the SAE’s performance in a supervised damage detection approach to consolidate its application in the Structural Health Monitoring (SHM) field, especially when dealing with real-case structures. The main idea is to use the SAE to extract relevant features from the monitored signals and the well-known Support Vector Machine (SVM) to classify such characteristics within the context of an SHM problem. Vibration data from a numerical beam model and a highway viaduct in Brazil are considered to assess the proposed approach. In both analyzed examples, the efficiency of the implemented methodology achieved more than 99% of correct damage structural classifications, supporting the conclusion that SAE can extract relevant characteristics from dynamic signals that are useful for SHM applications. |
| first_indexed | 2024-03-10T04:37:06Z |
| format | Article |
| id | doaj.art-dc6118523da2462d8707acb2fb49b007 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T04:37:06Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-dc6118523da2462d8707acb2fb49b0072023-11-23T03:41:07ZengMDPI AGApplied Sciences2076-34172021-12-0111241196510.3390/app112411965Numerical and Experimental Evaluation of Structural Changes Using Sparse Auto-Encoders and SVM Applied to Dynamic ResponsesRafaelle Piazzaroli Finotti0Flávio de Souza Barbosa1Alexandre Abrahão Cury2Roberto Leal Pimentel3Graduate Program in Computational Modeling, Federal University of Juiz de Fora, Juiz de Fora 36036090, BrazilGraduate Program in Computational Modeling, Federal University of Juiz de Fora, Juiz de Fora 36036090, BrazilGraduate Program in Civil Engineering, Federal University of Juiz de Fora, Juiz de Fora 36036090, BrazilGraduate Program in Civil and Environment Engineering, Federal University of Paraíba, João Pessoa 58051900, BrazilThe present work evaluates the deep learning algorithm called Sparse Auto-Encoder (SAE) when applied to the characterization of structural anomalies. This study explores the SAE’s performance in a supervised damage detection approach to consolidate its application in the Structural Health Monitoring (SHM) field, especially when dealing with real-case structures. The main idea is to use the SAE to extract relevant features from the monitored signals and the well-known Support Vector Machine (SVM) to classify such characteristics within the context of an SHM problem. Vibration data from a numerical beam model and a highway viaduct in Brazil are considered to assess the proposed approach. In both analyzed examples, the efficiency of the implemented methodology achieved more than 99% of correct damage structural classifications, supporting the conclusion that SAE can extract relevant characteristics from dynamic signals that are useful for SHM applications.https://www.mdpi.com/2076-3417/11/24/11965novelty detectionvibration signalsSparse Auto-Encoderdamage detectionstructural health monitoring |
| spellingShingle | Rafaelle Piazzaroli Finotti Flávio de Souza Barbosa Alexandre Abrahão Cury Roberto Leal Pimentel Numerical and Experimental Evaluation of Structural Changes Using Sparse Auto-Encoders and SVM Applied to Dynamic Responses Applied Sciences novelty detection vibration signals Sparse Auto-Encoder damage detection structural health monitoring |
| title | Numerical and Experimental Evaluation of Structural Changes Using Sparse Auto-Encoders and SVM Applied to Dynamic Responses |
| title_full | Numerical and Experimental Evaluation of Structural Changes Using Sparse Auto-Encoders and SVM Applied to Dynamic Responses |
| title_fullStr | Numerical and Experimental Evaluation of Structural Changes Using Sparse Auto-Encoders and SVM Applied to Dynamic Responses |
| title_full_unstemmed | Numerical and Experimental Evaluation of Structural Changes Using Sparse Auto-Encoders and SVM Applied to Dynamic Responses |
| title_short | Numerical and Experimental Evaluation of Structural Changes Using Sparse Auto-Encoders and SVM Applied to Dynamic Responses |
| title_sort | numerical and experimental evaluation of structural changes using sparse auto encoders and svm applied to dynamic responses |
| topic | novelty detection vibration signals Sparse Auto-Encoder damage detection structural health monitoring |
| url | https://www.mdpi.com/2076-3417/11/24/11965 |
| work_keys_str_mv | AT rafaellepiazzarolifinotti numericalandexperimentalevaluationofstructuralchangesusingsparseautoencodersandsvmappliedtodynamicresponses AT flaviodesouzabarbosa numericalandexperimentalevaluationofstructuralchangesusingsparseautoencodersandsvmappliedtodynamicresponses AT alexandreabrahaocury numericalandexperimentalevaluationofstructuralchangesusingsparseautoencodersandsvmappliedtodynamicresponses AT robertolealpimentel numericalandexperimentalevaluationofstructuralchangesusingsparseautoencodersandsvmappliedtodynamicresponses |