Simulation-Based Classification; a Model-Order-Reduction Approach for Structural Health Monitoring
We present a model-order-reduction approach to simulation-based classification, with particular application to structural health monitoring. The approach exploits (1) synthetic results obtained by repeated solution of a parametrized mathematical model for different values of the parameters, (2) mach...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Springer Netherlands
2018
|
| Online Access: | http://hdl.handle.net/1721.1/115173 https://orcid.org/0000-0002-3134-3730 https://orcid.org/0000-0001-7882-2483 https://orcid.org/0000-0002-2631-6463 |
| _version_ | 1826196908951994368 |
|---|---|
| author | Yano, M. Taddei, Tommaso Penn, James Douglass Patera, Anthony T |
| author2 | Massachusetts Institute of Technology. Department of Mechanical Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Mechanical Engineering Yano, M. Taddei, Tommaso Penn, James Douglass Patera, Anthony T |
| author_sort | Yano, M. |
| collection | MIT |
| description | We present a model-order-reduction approach to simulation-based classification, with particular application to structural health monitoring. The approach exploits (1) synthetic results obtained by repeated solution of a parametrized mathematical model for different values of the parameters, (2) machine-learning algorithms to generate a classifier that monitors the damage state of the system, and (3) a reduced basis method to reduce the computational burden associated with the model evaluations. Furthermore, we propose a mathematical formulation which integrates the partial differential equation model within the classification framework and clarifies the influence of model error on classification performance. We illustrate our approach and we demonstrate its effectiveness through the vehicle of a particular physical companion experiment, a harmonically excited microtruss. |
| first_indexed | 2024-09-23T10:39:52Z |
| format | Article |
| id | mit-1721.1/115173 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T10:39:52Z |
| publishDate | 2018 |
| publisher | Springer Netherlands |
| record_format | dspace |
| spelling | mit-1721.1/1151732022-09-30T22:08:04Z Simulation-Based Classification; a Model-Order-Reduction Approach for Structural Health Monitoring Yano, M. Taddei, Tommaso Penn, James Douglass Patera, Anthony T Massachusetts Institute of Technology. Department of Mechanical Engineering Taddei, Tommaso Penn, James Douglass Patera, Anthony T We present a model-order-reduction approach to simulation-based classification, with particular application to structural health monitoring. The approach exploits (1) synthetic results obtained by repeated solution of a parametrized mathematical model for different values of the parameters, (2) machine-learning algorithms to generate a classifier that monitors the damage state of the system, and (3) a reduced basis method to reduce the computational burden associated with the model evaluations. Furthermore, we propose a mathematical formulation which integrates the partial differential equation model within the classification framework and clarifies the influence of model error on classification performance. We illustrate our approach and we demonstrate its effectiveness through the vehicle of a particular physical companion experiment, a harmonically excited microtruss. United States. Air Force. Office of Scientific Research. Multidisciplinary University Research Initiative (Grant FA9550-09-1-0613) United States. Office of Naval Research (Grant N00014-11-1-0713) MIT-Singapore International Design Center 2018-05-02T17:13:22Z 2018-05-02T17:13:22Z 2016-08 2017-12-02T05:42:52Z Article http://purl.org/eprint/type/JournalArticle 1134-3060 1886-1784 http://hdl.handle.net/1721.1/115173 Taddei, T., et al. “Simulation-Based Classification; a Model-Order-Reduction Approach for Structural Health Monitoring.” Archives of Computational Methods in Engineering, vol. 25, no. 1, Jan. 2018, pp. 23–45. https://orcid.org/0000-0002-3134-3730 https://orcid.org/0000-0001-7882-2483 https://orcid.org/0000-0002-2631-6463 en http://dx.doi.org/10.1007/s11831-016-9185-0 Archives of Computational Methods in Engineering Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ CIMNE, Barcelona, Spain application/pdf Springer Netherlands Springer Netherlands |
| spellingShingle | Yano, M. Taddei, Tommaso Penn, James Douglass Patera, Anthony T Simulation-Based Classification; a Model-Order-Reduction Approach for Structural Health Monitoring |
| title | Simulation-Based Classification; a Model-Order-Reduction Approach for Structural Health Monitoring |
| title_full | Simulation-Based Classification; a Model-Order-Reduction Approach for Structural Health Monitoring |
| title_fullStr | Simulation-Based Classification; a Model-Order-Reduction Approach for Structural Health Monitoring |
| title_full_unstemmed | Simulation-Based Classification; a Model-Order-Reduction Approach for Structural Health Monitoring |
| title_short | Simulation-Based Classification; a Model-Order-Reduction Approach for Structural Health Monitoring |
| title_sort | simulation based classification a model order reduction approach for structural health monitoring |
| url | http://hdl.handle.net/1721.1/115173 https://orcid.org/0000-0002-3134-3730 https://orcid.org/0000-0001-7882-2483 https://orcid.org/0000-0002-2631-6463 |
| work_keys_str_mv | AT yanom simulationbasedclassificationamodelorderreductionapproachforstructuralhealthmonitoring AT taddeitommaso simulationbasedclassificationamodelorderreductionapproachforstructuralhealthmonitoring AT pennjamesdouglass simulationbasedclassificationamodelorderreductionapproachforstructuralhealthmonitoring AT pateraanthonyt simulationbasedclassificationamodelorderreductionapproachforstructuralhealthmonitoring |