On the investigation of Statistical Alignement for enhancing damage identification across a population of heterogeneous shear structures
Práctica Supervisada (I.C.)--FCEFN-UNC, 2024
Guardado en:
| Autor principal: | |
|---|---|
| Otros Autores: | |
| Formato: | bachelorThesis |
| Lenguaje: | Español |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | http://webthesis.biblio.polito.it/id/eprint/30747 http://hdl.handle.net/11086/554544 |
| Aporte de: |
| id |
I10-R141-11086-554544 |
|---|---|
| record_format |
dspace |
| institution |
Universidad Nacional de Córdoba |
| institution_str |
I-10 |
| repository_str |
R-141 |
| collection |
Repositorio Digital Universitario (UNC) |
| language |
Español |
| topic |
Práctica Supervisada IC Ingeniería civil Ingenieria de estructuras Modelos matemáticos Programa de Maestría en Ingeniería Civil - Politécnico de Torino, Italia Politécnico de Turín Corso di laurea magistrale in Ingegneria Civile |
| spellingShingle |
Práctica Supervisada IC Ingeniería civil Ingenieria de estructuras Modelos matemáticos Programa de Maestría en Ingeniería Civil - Politécnico de Torino, Italia Politécnico de Turín Corso di laurea magistrale in Ingegneria Civile Badariotti, Sebastian On the investigation of Statistical Alignement for enhancing damage identification across a population of heterogeneous shear structures |
| topic_facet |
Práctica Supervisada IC Ingeniería civil Ingenieria de estructuras Modelos matemáticos Programa de Maestría en Ingeniería Civil - Politécnico de Torino, Italia Politécnico de Turín Corso di laurea magistrale in Ingegneria Civile |
| description |
Práctica Supervisada (I.C.)--FCEFN-UNC, 2024 |
| author2 |
Surace, Cecilia |
| author_facet |
Surace, Cecilia Badariotti, Sebastian |
| format |
bachelorThesis |
| author |
Badariotti, Sebastian |
| author_sort |
Badariotti, Sebastian |
| title |
On the investigation of Statistical Alignement for enhancing damage identification across a population of heterogeneous shear structures |
| title_short |
On the investigation of Statistical Alignement for enhancing damage identification across a population of heterogeneous shear structures |
| title_full |
On the investigation of Statistical Alignement for enhancing damage identification across a population of heterogeneous shear structures |
| title_fullStr |
On the investigation of Statistical Alignement for enhancing damage identification across a population of heterogeneous shear structures |
| title_full_unstemmed |
On the investigation of Statistical Alignement for enhancing damage identification across a population of heterogeneous shear structures |
| title_sort |
on the investigation of statistical alignement for enhancing damage identification across a population of heterogeneous shear structures |
| publishDate |
2024 |
| url |
http://webthesis.biblio.polito.it/id/eprint/30747 http://hdl.handle.net/11086/554544 |
| work_keys_str_mv |
AT badariottisebastian ontheinvestigationofstatisticalalignementforenhancingdamageidentificationacrossapopulationofheterogeneousshearstructures AT badariottisebastian investigacionsobreelrendimientodelalineamientoestadisticoparamejorarlaidentificaciondedanosenunapoblaciondeestructurasdecorteheterogeneas |
| _version_ |
1824552203507990528 |
| spelling |
I10-R141-11086-5545442024-12-18T13:49:16Z On the investigation of Statistical Alignement for enhancing damage identification across a population of heterogeneous shear structures Investigación sobre el rendimiento del alineamiento estadístico para mejorar la identificación de daños en una población de estructuras de corte heterogéneas Badariotti, Sebastian Surace, Cecilia Delo, Giulia Práctica Supervisada IC Ingeniería civil Ingenieria de estructuras Modelos matemáticos Programa de Maestría en Ingeniería Civil - Politécnico de Torino, Italia Politécnico de Turín Corso di laurea magistrale in Ingegneria Civile Práctica Supervisada (I.C.)--FCEFN-UNC, 2024 Tesis de Maestría (I.C.)--Politécnico de Torino, 2024 Fil: Badariotti, Sebastian. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Física y Naturales; Argentina. Fil: Badariotti, Sebastián. Politécnico de Turín. Programa de Maestría en Ingeniería Civil; Italia. Fil: Badariotti, Sebastián. Politecnico di Torino. Corso di laurea magistrale in Ingegneria Civile; Italia. The development of machine learning algorithms for Structural Health Monitoring (SHM) is rapidly advancing. However, their application for real-world structures finds a high number of complications. One is the need for comprehensive data for training the proper algorithms. Thus, Population-Based Health Monitoring (PBSHM) overcomes these challenges by sharing information between different structures. In this framework, it is necessary to understand to what extent knowledge can be shared, especially for heterogeneous datasets. Therefore, this study implements a simple domain adaptation technique based on Statistical Alignment (SA) on a population of heterogeneous shear structures to investigate how the performance changes due to the variations within the population. The scenarios proposed are solved with normal-condition alignment (NCA) and normal-correlation alignment (NCORAL). Two case studies are analysed. The first is related to numerical structures. It is created by simulating multiple source and target datasets, containing the features and labels of each data point. The features consist of the natural frequencies of each structure, and the label is a binary vector indicating if the data point corresponds to a damage condition or not. To calculate the natural frequencies, the structure is modelled as a shear-type with chain-like models, and the mass and stiffness matrices are calculated considering the equation of motion. The damage is then introduced with a reduction of the stiffness of a column, leading to reduced values of the related frequencies. It is important to highlight that, in each sample, a variation of the material properties is introduced, trying to simulate the actual variability on measured data. The second case study extends the implementation to an experimental case study of a three-story frame structure to test this methodology for sharing knowledge between real and simulated data. El desarrollo de algoritmos de aprendizaje automático para el Monitoreo de Salud Estructural (SHM) avanza rápidamente, pero su aplicación en estructuras reales enfrenta complicaciones debido a la falta de datos completos para entrenar los algoritmos. El Monitoreo de Salud Basado en Población (PBSHM) resuelve estos problemas al compartir información entre estructuras. Este estudio implementa una técnica de adaptación de dominio basada en Alineamiento Estadístico (SA) en estructuras de corte heterogéneas, para analizar cómo varía el rendimiento con las diferencias dentro de la población. Se resuelven los escenarios con alineamiento en condiciones normales (NCA) y alineamiento de correlación normal (NCORAL). El primer estudio de caso simula estructuras numéricas, usando frecuencias naturales y etiquetas para identificar daños. El segundo caso extiende la técnica a una estructura experimental de tres pisos, para probar el intercambio de conocimiento entre datos reales y simulados. (resumen provisto por el ctalogador) Fil: Badariotti, Sebastian. Universidad Nacional de Córdoba. Facultad de Ciencias Exactas, Física y Naturales; Argentina. Fil: Badariotti, Sebastián. Politécnico de Turín. Programa de Maestría en Ingeniería Civil; Italia. Fil: Badariotti, Sebastián. Politecnico di Torino. Corso di laurea magistrale in Ingegneria Civile; Italia. 2024-12-12T13:26:58Z 2024-12-12T13:26:58Z 2024 bachelorThesis http://webthesis.biblio.polito.it/id/eprint/30747 http://hdl.handle.net/11086/554544 spa Attribution-NonCommercial-ShareAlike 4.0 International http://creativecommons.org/licenses/by-nc-sa/4.0/ |