Deep reinforcement learning‐based active mass driver decoupled control framework considering control–structure interaction effects

H Yao, P Tan, TY Yang, F Zhou - Computer‐Aided Civil and …, 2024 - Wiley Online Library
Control–structure interaction (CSI) plays a significant role in active control systems. Popular
methods incorporate actuator dynamics into an integrated control system to account for CSI …

RL-Controller: a reinforcement learning framework for active structural control

SS Eshkevari, SS Eshkevari, D Sen… - arXiv preprint arXiv …, 2021 - arxiv.org
To maintain structural integrity and functionality during the designed life cycle of a structure,
engineers are expected to accommodate for natural hazards as well as operational load …

A composite control scheme for electromagnetic active mass damper against control-structure-interaction effects

H Yao, P Tan, H Zhou, F Zhou - Engineering Structures, 2023 - Elsevier
Existing methods account for control-structure-interaction (CSI) in structural control design.
However, their implementations may be challenging since the dynamic characteristics of …

Continuous control of structural vibrations using hybrid deep reinforcement learning policy

J Panda, M Chopra, V Matsagar… - Expert Systems with …, 2024 - Elsevier
An efficient active structural control scheme by utilizing the collective concepts of data-driven
and physics-inspired reinforcement learning (RL) approaches is being introduced here. The …

A deep reinforcement learning framework to modify LQR for an active vibration control applied to 2D building models

EZ Gheni, HMH Al-Khafaji, HM Alwan - Open Engineering, 2024 - degruyter.com
Deep reinforcement learning (DRL) has emerged as a promising approach for optimizing
control policies in various fields. In this article, we explore the use of DRL for controlling …

Vibration control based on reinforcement learning for a flexible building-like structure system with active mass damper against disturbance effects

H Gao, W He, Y Zhang, C Sun - 2020 59th IEEE Conference on …, 2020 - ieeexplore.ieee.org
Vibration and displacement control are of critical importance for both high-rise and ultra high-
rise building systems. A single-floor building-like structure equipped with an active mass …

Active structural control framework using policy-gradient reinforcement learning

SS Eshkevari, SS Eshkevari, D Sen, SN Pakzad - Engineering Structures, 2023 - Elsevier
This paper presents a novel data-driven approach for active structural control through the
use of deep reinforcement learning, wherein, the control system learns to react in an optimal …

Machine-learning based optimal seismic control of structure with active mass damper

PC Chen, KY Chien - Applied Sciences, 2020 - mdpi.com
In recent years, optimal control which minimizes a cost function formulated by weighted
states and control inputs has been applied to the seismic control of structures. Optimal …

Deep Reinforcement Learning for Active Structure Stabilization

W Compton, M Curtin, W Vogt, A Scheinker… - Data Science in …, 2022 - Springer
Structures are continuously exposed to external forcing, which can have dramatic variation
both in loading magnitude and frequency content. A structure must implement control …

Rapid Controller Generation for Vibration Suppression of Structures Using Direct Excitation with Machine Learning

PC Chen, CW Chou, WJ Wang - Journal of Structural Engineering, 2024 - ascelibrary.org
Active mass dampers (AMDs) have been used to suppress vibration of structures subjected
to dynamic loading. Generally, controller design of AMD requires an identified numerical …