Research data for: "Damage-aware structural control based on reinforcement learning"

This dataset contains the research data used for preparation of the publication:Jedlińska A., Pisarski D., Mikułowski G., Błachowski B., Jankowski Ł., Damage-aware structural control based on reinforcement learning, EWSHM 2024, 11th Euopean Workshop on Structural Health Monitoring, 2024-06-10/06-13, Potsdam (DE), 8 pages, 2024. e-Journal of Nondestructive Testing (eJNDT), issue 2024-07. https://doi.org/10.58286/29606This research has been supported by the National Science Centre, Poland, under grant agreement 2020/39/B/ST8/02615. The title of the project is "Reinforcement learning for semi-active structural control and decentralized mitigation of vibrations: development of new algorithms and assessment of of their efficiency". The aim of the project is the development and application of the machine learning techniques of reinforcement learning (RL) in tasks of semi-active structural control. The ultimate goal is the design of a framework that learns quasi-optimal control by itself in a repeated trial-and-error interactions with simulated structures.The data files are in the txt/CSV format, and they have been exported using the Wolfram Mathematica environment. They define the investigated structure (an 11-DOF shear-type building with a semi-active TMD) and contain the control results defined as the mean total energy of the structure subjected to a seismic-type excitation. An additional problem in this manuscript was the damage-awarness, that is, the design of a specific RL control agent that estimates the current structural damage and uses this knowledge to improve its contorl decisions. One of the files contains thus the indices used to asses the effetiveness of damage identification.