Intelligent Control of Building Vibrations: A Transformer-Based Deep Reinforcement Learning Framework
Bibliographic record
Abstract
Deep reinforcement learning (DRL) has emerged as a promising methodology for optimizing control policies across diverse domains, despite its well-acknowledged high training costs.This paper delves into the application of transformer model-based DRL for vibration control in building structures.Specifically, we tackle the challenge of diminishing vibrations induced by external factors like wind or earthquakes.Our innovative method eliminates the necessity for online interaction with the simulation environment during training, offering a more resource-efficient approach.In our proposed framework, the DRL agent learns to dynamically adjust the control signal of a classical linear-quadratic regulator (LQR)-based model in real-time to alleviate building structure vibrations.Combining the proximal policy optimization (PPO) method with a deep neural network trained on experimental environment data using the transformer model, our approach utilizes input sensor data obtained from the structure.The DRL model then generates corrective signals that augment the LQR model's output.Through an experimental study on a small-scale 3-story building structure, we demonstrate the efficacy of our transformer-based DRL control.Our results highlight the superiority of our approach over the classical LQR model in terms of both training computational cost and vibration reduction.This underscores the potential of DRL in enhancing the functionality of construction frameworks when facing external disturbances.Moreover, our adaptable framework is simple to include in the building control systems now in use.with the potential for extension to various control challenges within the realm of structural engineering.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".