Supervisión de la integridad estructural mediante inteligencia artificial
retos, avances y aplicaciones
DOI:
https://doi.org/10.35699/2965-6931.2023.47533Palabras clave:
detección de daños estructurales, inteligencia computacional, aprendizaje automático, aprendizaje profundoResumen
Este artículo presenta una revisión sistemática y aporta reflexiones críticas sobre el uso de técnicas de inteligencia artificial para identificar el deterioro estructural a través de señales de vibración (es decir, aceleraciones, desplazamientos, etc.). Los enfoques basados en el aprendizaje automático y el aprendizaje profundo se consideran prometedores para aumentar la seguridad y optimizar los programas de mantenimiento preventivo. Sin embargo, algunos autores reconocen las preocupaciones que surgen de los métodos estrictamente supervisados, la naturaleza de "caja negra" de los modelos y su interpretación por parte de los operadores humanos. La aportación de este trabajo es, por tanto, aportar información relevante sobre el paradigma actual de detección de daños, posibilitando predicciones en tiempo real, no destructivas y fiables sobre la seguridad en la construcción en el ámbito de la Industria 4.0. Además, los desafíos relacionados con el uso de inteligencia computacional para el reconocimiento de patrones y la toma de decisiones en el monitoreo de anomalías estructurales se informan y examinan en estudios de casos recientes.Descargas
Citas
ABDELJABER, O.; AVCI, O.; KIRANYAZ, S.; GABBOUJ, M.; INMAN, D. J. Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks. Journal of Sound and Vibration, v. 388, p. 154-170, 2017. DOI:10.1016/j.jsv.2016.10.043
ALAZZAWI, Osama; WANG, Dansheng. A novel structural damage identification method based on the acceleration responses under ambient vibration and an optimized deep residual algorithm. Structural Health Monitoring, v. 21, n. 6, p. 2587-2617, 2022. DOI:10.1177/14759217211065009
ALVES, Victor; CURY, Alexandre. A fast and efficient feature extraction methodology for structural damage localization based on raw acceleration measurements. Structural Control and Health Monitoring, v. 28, n. 7, p. e2748, 2021. DOI:10.1002/stc.2748
ALVES, Victor; CURY, Alexandre. An automated vibration-based structural damage localization strategy using filter-type feature selection. Mechanical Systems and Signal Processing, v. 190, p. 110145, 2023. DOI:10.1016/j.ymssp.2023.110145
AMIN, A.; BIBO, A.; PANYAM, M.; TALLAPRAGADA, P. Wind Turbine Gearbox Fault Diagnosis Using Cyclostationary Analysis and Interpretable CNN. Journal of Vibration Engineering & Technologies, p. 1-11, 2023. DOI: 10.1007/s42417-023-00937-1
ARRIETA, Alejandro Barredo et al. Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information fusion, v. 58, p. 82-115, 2020. DOI: 10.1016/j.inffus.2019.12.012
AVCI, O.; ABDELJABER, O.; KIRANYAZ, S.; HUSSEIN, M.; GABBOUJ, M.; INMAN, D. J. A review of vibration-based damage detection in civil structures: From traditional methods to Machine Learning and Deep Learning applications. Mechanical systems and signal processing, v. 147, p. 107077, 2021. DOI:10.1016/j.ymssp.2020.107077
AZIMI, Mohsen; ESLAMLOU, Armin Dadras; PEKCAN, Gokhan. Data-driven structural health monitoring and damage detection through deep learning: State-of-the-art review. Sensors, v. 20, n. 10, p. 2778, 2020. DOI: 10.3390/s20102778
BRUSA, E.; CIBRARIO, L.; DELPRETE, C.; DI MAGGIO, L. G. Explainable AI for machine fault diagnosis: understanding features’ contribution in machine learning models for industrial condition monitoring. Applied Sciences, v. 13, n. 4, p. 2038, 2023. DOI: 10.3390/app13042038
CHAMANGARD, M.; GHODRATI AMIRI, G.; DARVISHAN, E.; RASTIN, Z. Transfer Learning for CNN-Based Damage Detection in Civil Structures with Insufficient Data. Shock and Vibration, v. 2022, 2022. DOI: 10.1155/2022/3635116
CIREŞAN, D. C.; MEIER, U.; GAMBARDELLA, L. M.; SCHMIDHUBER, J. Deep, big, simple neural nets for handwritten digit recognition. Neural computation, v. 22, n. 12, p. 3207-3220, 2010. DOI: 10.1162/NECO_a_00052
CURY, Alexandre; CRÉMONA, Christian; DIDAY, Edwin. Application of symbolic data analysis for structural modification assessment. Engineering Structures, v. 32, n. 3, p. 762-775, 2010. DOI:10.1016/j.engstruct.2009.12.004
CURY, Alexandre; RIBEIRO, Diogo; UBERTINI, Filippo; TODD, Michael D. Structural health monitoring based on data science techniques. Springer, 2022. DOI:10.1007/978-3-030-81716-9
DANESHJOO, Z.; SHOKRIEH, M. M.; FAKOOR, M. A micromechanical model for prediction of mixed mode I/II delamination of laminated composites considering fiber bridging effects. Theoretical and Applied Fracture Mechanics, v. 94, p. 46-56, 2018. DOI: 10.1016/j.tafmec.2017.12.002
DONG, Chuan-Zhi; CATBAS, F. Necati. A review of computer vision–based structural health monitoring at local and global levels. Structural Health Monitoring, v. 20, n. 2, p. 692-743, 2021. DOI: 10.1177/1475921720935585
FINOTTI, R. P.; DE SOUZA BARBOSA, F.; CURY, A. A.; GENTILE, C. A novel natural frequency-based technique to detect structural changes using computational intelligence. Procedia engineering, v. 199, p. 3314-3319, 2017. DOI:10.1016/j.proeng.2017.09.438
FINOTTI, R. P.; BARBOSA, F. D. S.; CURY, A. A.; PIMENTEL, R. L. Numerical and Experimental Evaluation of Structural Changes Using Sparse Auto-Encoders and SVM Applied to Dynamic Responses. Applied Sciences, v. 11, n. 24, p. 11965, 2021. DOI:10.3390/app112411965
FIGUEIREDO, E.; PARK, G.; FIGUEIRAS, J.; FARRAR, C.; WORDEN, K. Structural health monitoring algorithm comparisons using standard data sets. Los Alamos National Lab.(LANL), Los Alamos, NM (United States), 2009. DOI: 10.2172/961604
GHIASI, Ramin; GHASEMI, Mohammad Reza; CHAN, Tommy HT. Optimum feature selection for SHM of benchmark structures using efficient AI mechanism. Smart Struct. Syst, v. 27, p. 623-640, 2021. DOI: 10.12989/sss.2021.27.4.623
GUI, G.; PAN, H.; LIN, Z.; LI, Y.; YUAN, Z. Data-driven support vector machine with optimization techniques for structural health monitoring and damage detection. KSCE Journal of Civil Engineering, v. 21, p. 523-534, 2017. DOI: 10.1007/s12205-017-1518-5
JOHNSON, E. A.; LAM, H. F.; KATAFYGIOTIS, L. S.; BECK, J. L. Phase I IASC-ASCE structural health monitoring benchmark problem using simulated data. Journal of engineering mechanics, v. 130, n. 1, p. 3-15, 2004. DOI: 10.1061/(ASCE)0733-9399(2004)130:1(3)
Li, H.; Li, S.; Ou, J.; Li, H. Reliability assessment of cable-stayed bridges based on structural health monitoring techniques. Structure and Infrastructure Engineering, v. 8, n. 9, p. 829-845, 2012. DOI: 10.1080/15732479.2010.496856
LULECI, Furkan; CATBAS, F. Necati; AVCI, Onur. Generative adversarial networks for labeled acceleration data augmentation for structural damage detection. Journal of Civil Structural Health Monitoring, v. 13, n. 1, p. 181-198, 2023a.
LULECI, Furkan; AVCI, Onur; CATBAS, F. Necati. Improved undamaged-to-damaged acceleration response translation for Structural Health Monitoring. Engineering Applications of Artificial Intelligence, v. 122, p. 106146, 2023c. DOI: 10.1016/j.engappai.2023.106146
LULECI, Furkan; CATBAS, F. Necati; AVCI, Onur. CycleGAN for undamaged-to-damaged domain translation for structural health monitoring and damage detection. Mechanical Systems and Signal Processing, v. 197, p. 110370, 2023b. DOI:10.1016/j.ymssp.2023.110370
LUO, B; WANG, H.; LIU, H.; LI, B.; PENG, F. Early fault detection of machine tools based on deep learning and dynamic identification. IEEE Transactions on Industrial Electronics, v. 66, n. 1, p. 509-518, 2018. DOI: 10.1109/TIE.2018.2807414
MARINIELLO, G.; PASTORE, T.; MENNA, C.; FESTA, P.; ASPRONE, D. Structural damage detection and localization using decision tree ensemble and vibration data. Computer‐Aided Civil and Infrastructure Engineering, v. 36, n. 9, p. 1129-1149, 2021. DOI:10.1111/mice.12633
MEIXEDO, A.; SANTOS, J.; RIBEIRO, D.; CALÇADA, R.; TODD, M. Damage detection in railway bridges using traffic-induced dynamic responses. Engineering Structures, v. 238, p. 112189, 2021. DOI:10.1016/j.engstruct.2021.112189
MORALES, Fabricio A. O.; CURY, Alexandre A. Analysis of thermal and damage effects over structural modal parameters. Structural engineering and mechanics: An international journal, v. 65, n. 1, p. 43-51, 2018. DOI:10.12989/sem.2018.65.1.043
MAECK, Johan; DE ROECK, Guido. Damage assessment using vibration analysis on the Z24-bridge. Mechanical Systems and Signal Processing, v. 17, n. 1, p. 133-142, 2003. DOI: 10.1006/mssp.2002.1550
MOUGHTY, John J.; CASAS, Joan R. A state of the art review of modal-based damage detection in bridges: Development, challenges, and solutions. Applied Sciences, v. 7, n. 5, p. 510, 2017. DOI: 10.3390/app7050510
RYTTER, A. Vibrational based inspection of civil engineering structures. 1993. Tese de doutorado – Denmark: Department of Building Technology and Structural, Aalborg University, Aalborg, 1993.
SONY, S.; GAMAGE, S.; SADHU, A.; SAMARABANDU, J. Vibration-based multiclass damage detection and localization using long short-term memory networks. Structures, v. 35, p. 436-451, 2022. DOI: 10.1016/j.istruc.2021.10.088
TAN, Yi; ZHANG, Limao. Computational methodologies for optimal sensor placement in structural health monitoring: A review. Structural Health Monitoring, v. 19, n. 4, p. 1287-1308, 2020. DOI: 10.1177/1475921719877579
TIAN, W.; CHENG, X.; LIU, Q.; YU, C.; GAO, F.; CHI, Y. Meso-structure segmentation of concrete CT image based on mask and regional convolution neural network. Materials & Design, v. 208, p. 109919, 2021. DOI:10.1016/j.matdes.2021.109919
WANG, Teng; LU, Guoliang; YAN, Peng. A novel statistical time-frequency analysis for rotating machine condition monitoring. IEEE
Transactions on Industrial Electronics, v. 67, n. 1, p. 531-541, 2019. DOI: 10.1109/TIE.2019.2896109
YUAN, Fuh-Gwo (Ed.). Structural health monitoring (SHM) in aerospace structures. Woodhead Publishing, 2016. DOI: 10.1016/C2014-0-00994-X
ZACHARAKIS, Ilias; GIAGOPOULOS, Dimitrios. Vibration-Based Damage Detection Using Finite Element Modeling and the Metaheuristic Particle Swarm Optimization Algorithm. Sensors, v. 22, n. 14, p. 5079, 2022. DOI: 10.3390/s22145079
ZHANG, Yixiao; LEI, Ying. Data anomaly detection of bridge structures using convolutional neural network based on structural vibration signals. Symmetry, v. 13, n. 7, p. 1186, 2021. DOI: 10.3390/sym13071186
