Virtual Sensing of Wind Turbine Loads With Multi‐Hidden Markov Models for Above‐Rated Wind Speeds
Bibliographic record
Abstract
ABSTRACT The growing demand for wind energy necessitates efficient health monitoring strategies to ensure the long‐term reliability of wind turbines. Monitoring critical loads, such as flapwise blade root moments and tower base fore‐aft moments, is crucial for preventing turbine fatigue and failure. However, direct measurements through physical sensors are costly, time‐consuming, and limited to specific locations. This study introduces a probabilistic data‐driven virtual sensing framework that uses multi‐hidden Gauss‐Markov model (Multi‐HGMM) to estimate these loads by capturing the relationship between measurable quantities and key structural metrics, without requiring extensive physical sensors. An expectation–maximization algorithm is used to determine the HGMM parameters from a comprehensive dataset. This dataset includes routinely recorded SCADA data, such as wind speed, rotor speed, and pitch angles, along with additional key features that were carefully selected for their relevance to load estimation. In a subsequent stage that includes operational measurement data, the probabilistic HGMM can be used to estimate loads. We validate our approach on a 5‐MW wind turbine model developed by the National Renewable Energy Laboratory (NREL), for above‐rated wind speeds where turbines face heightened loads due to increased aerodynamic forces, critical for structural integrity. The results demonstrated that the multi‐HGMM approach achieved a mean absolute error of approximately 6% for estimating both the tower base moment and flapwise moment when incorporating tower top accelerations and shaft bending moments alongside baseline features. By reducing reliance on physical sensors, this virtual sensing methodology offers a scalable, cost‐effective solution for wind turbine monitoring.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".