Communication Dans Un Congrès Année : 2024

Damage detection in a semi-active structural control system based on reinforcement learning

Résumé

This contribution applies the machine learning technique of reinforcement learning for simultaneous damage detection and control of structures. The proposed system consists of two components. The control component is responsible for semi-active mitigation of vibrations. The control law is determined experimentally in a trial-and-error interaction with a simulated environment. The process is data-driven: the control agent iteratively improves its control law based on the observed results of past control actions. The robustness relies on the accuracy of the structural model used for training. The control efficiency can decrease if the physical structure is damaged and diverges from the model, that is, when effective control may be most required. Thus, the second component of the proposed system monitors the structure to detect damages and inform the control component. The approach is tested in a numerical experiment of a shear building under random seismic-type excitation. A semi-active tuned mass damper (TMD) is used as an actuator, and a classical TMD serves as a reference.

Fichier principal
Vignette du fichier
ISMA_2024.pdf (409.25 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04702122 , version 1 (19-09-2024)

Licence

Identifiants

  • HAL Id : hal-04702122 , version 1

Citer

Aleksandra Jedlińska, Dominik Pisarski, Grzegorz Mikułowski, Bartłomiej Błachowski, Łukasz Jankowski. Damage detection in a semi-active structural control system based on reinforcement learning. International Conference on Noise and Vibration Engineering (ISMA 2024), KU Leuven, Sep 2024, Leuven, Belgium. ⟨hal-04702122⟩
74 Consultations
161 Téléchargements

Partager

  • More