Deep Reinforcement Learning for Structural Model Updating Using Transfer Learning Mechanism
Bibliographic record
Abstract
Structural simulation models using pre-defined assumptions and values of material properties usually produce results that differ from the real structures with varying degree of accuracy. This is commonly attributed to two broad types of uncertainties, namely aleatory (related to inherent randomness) and epistemic (related to lack of knowledge). Sources of such uncertainties include material properties, construction techniques, aging, and natural or man-made hazard-induced damage. Accurate computational models with on-time model updating capabilities are important goals in engineering research and practice for monitoring the structural health during the operation stage and for making rapid and well-informed decisions following extreme events, for example, major earthquakes. Moreover, the advances and recent adoption of artificial intelligence technologies bring effective and innovative solutions for the structural model updating endeavors. In this paper, a novel model updating method is proposed using two deep reinforcement learning algorithms, namely, Advantage Actor-Critic and Asynchronous Advantage Actor-Critic. In addition, transfer learning is adopted, which generalizes the trained model to various scenarios and enhances the computational efficiency. Through several computer experiments, the results demonstrate the high accuracy and computational efficiency of the proposed approach, which brings about its promising potential for practical engineering applications.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| 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".