MétaCan
Menu
Back to cohort
Record W4414143555 · doi:10.1007/s00521-025-11619-2

Multi-head attention transformer and Bayesian inference recommendation engine-based blade icing detection framework for wind turbines

2025· article· en· W4414143555 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

VenueNeural Computing and Applications · 2025
Typearticle
Languageen
FieldEngineering
TopicIcing and De-icing Technologies
Canadian institutionsArtificial Intelligence in Medicine (Canada)
FundersMonash University
KeywordsIcingTurbineWind powerConvolutional neural networkTransformerArtificial neural networkBayesian probabilityBayesian inferenceOverfitting

Abstract

fetched live from OpenAlex

Abstract Icing accumulation on wind turbine blades significantly diminishes power output and revenue generation. Traditional icing detection methods, including sensor-based and model-based approaches, heavily rely on domain knowledge, contrasting with data-centric methods. However, a balanced distribution of normal and abnormal instances in wind turbine data is imperative. In this research, we propose a framework for blade icing detection utilizing a multi-head attention mechanism-based transformer. Supervisory control and data acquisition (SCADA) data is collected from wind turbines on Hitra Island, Norway, with a 10-min average interval over 12 months. To address dimensionality challenges, an autoencoder-based data compression technique is employed, followed by the application of a multi-head attention transformer for icing detection. We investigate and compare the performance of two baseline deep learning methods: convolutional neural network (CNN) and Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM), against our proposed transformer framework. The results demonstrate superior accuracy and F1-score by the proposed model compared to CNN and CNN-LSTM. Additionally, we delve into a recommendation engine grounded in Bayesian inference. This engine assesses the risk associated with specific control actions, estimating conditional risk for icing and non-icing events on wind turbine blades. This Bayesian recommendation engine holds promise for real-time deployment scenarios.

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: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.960
Threshold uncertainty score0.481

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 head0.017
GPT teacher head0.297
Teacher spread0.280 · 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