MétaCan
Menu
Back to cohort

From augmentation to translation: Data generation by conditional hierarchical variational autoencoder, enhancing monitoring mooring systems in floating offshore wind turbines

2025· article· en· W4415700466 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueEngineering Applications of Artificial Intelligence · 2025
Typearticle
Languageen
FieldPhysics and Astronomy
TopicModel Reduction and Neural Networks
Canadian institutionsNational Research Council Canada
FundersEusko JaurlaritzaFundación Iberdrola España
KeywordsBenchmark (surveying)Offshore wind powerWind powerMooringUnderwaterCode (set theory)Noise (video)Data modelingRandomness

Abstract

fetched live from OpenAlex

The integrity of mooring systems in floating offshore wind turbines (FOWTs) is crucial, as their degradation alters the platform’s dynamic behavior. A robust machine learning-based health monitoring system that continuously monitors different mooring systems for FOWTs requires data under diverse health, operational, and metocean conditions. To this end, we propose a Conditional Hierarchical Variational Autoencoder (CHVAE) generative model designed for simultaneous data augmentation and domain translation to generate the required data. We train the model to learn the nonlinear relationships between healthy and minority-damaged fairlead tension records from the source mooring system across various sea states. CHVAE generates realistic damaged responses under diverse conditions by leveraging healthy data from the target mooring system. We first assess CHVAE’s ability to augment minority data based on majority distribution, validated on the Modified National Institute of Standards and Technology (MNIST) benchmark dataset. This experiment compares the performance of CHVAE variants with conventional and recent oversampling methods. Second, the open-source software OpenFast simulates the testing and training datasets for simultaneously data augmentation and domain translation on the Offshore Code Comparison Collaboration Continuation (OC4) semi-submersible platform (DeepCwind) FOWT benchmark. OpenFast and CHVAE records are compared through visual, statistical, and behavioral methodologies. Simulations utilize diverse wave seeds to represent excitation randomness and undetected damage severities, assessing CHVAE’s one-to-all capability. Generated records for unobserved sea states and damage severities closely mimic real behavior in downstream binary classification, illustrating the versatility of CHVAE for zero-shot, real-time damage identification. • Novel generator for real-scale time-series synthesis (CHVAE) • One-to-all CHVAE maps healthy data to a specified damage severity • Second CHVAE decoder estimates de-normalization parameters from minority distribution • Compared with oversampling baselines on the MNIST benchmark • CHVAE conducts domain translation to generate unseen damaged tension for OC4 FOWT

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.919
Threshold uncertainty score0.604

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.046
GPT teacher head0.317
Teacher spread0.271 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it