Learning to Simulate Structural Failures: A CVAE Framework for Engineering Risk
Bibliographic record
Abstract
In engineering risk analysis, accurately estimating the structural failure probability of complex nonlinear systems remains a formidable challenge due to the high cost of repeated simulator evaluations. This paper proposes a conditional variational autoencoder (CVAE)-based simulation-based inference (SBI) framework to address this issue. By learning a generative model of the conditional limit-state function \(g( x )\mid x\), the proposed method enables efficient reliability estimation through conditional sampling and Bayesian inference. We demonstrate our method on a two-dimensional benchmark problem involving a four-branch limit-state surface, where each branch represents a distinct failure mechanism such as cracking, sliding, overload, or dynamic instability—typical of dam components under seismic or hydraulic loading. The CVAE surrogate successfully captures the structure of the failure boundary and provides credible intervals for the predicted failure probability. Experimental results show that the estimation achieves high accuracy, with relative error less than 3%, using only a small number of simulator calls. This confirms the potential of CVAE-based SBI as a general-purpose surrogate for structural reliability analysis. Looking ahead, our method will be extended to high-dimensional, physics-informed models and applied to real-world reliability assessments in hydropower infrastructure systems, where accurate uncertainty-aware risk quantification is critical for structural safety and decision-making.
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 | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| 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".