Data mining for diagnosis, monitoring, and prediction in wind power plants
Bibliographic record
Abstract
Nowadays, renewable energy sources play the key role in power system engineering. Among multiplicity of energy sources, wind energy is more popular due to its substantial advantages such as lower prices of produced electricity, their established technology, and being more accessible. However, these technologies have considerable costs that can mitigate profit for the investors and consumers. Among the different costs, the operation and maintenance (O&M) costs have the key role since many installed wind turbines are getting older. To mitigate the O&M costs it is crucial to update the defined strategies for condition monitoring (CM) in wind farms. The proper CM tool should be developed after exerting complete survey of existing CM techniques. To shift from a manual CM toward an automatic and smart approach, the machine learning and data mining concepts will be utilized in this application. The need for a modern condition monitoring strategy coincides with the emergence of Deep Learning (DL) in the recent decade. In this thesis, a novel condition monitoring is proposed to monitor the temperature of generator windings in a wind farm using Long Short-Term Memory (LSTM) model which is a Recurrent Neural Network (RNN) method. This DL model is a practical and unique choice for prediction due to its ability for considering long-term dependencies among input sequential features, which in this case are the provided time-series datasets by SCADA system. The time series SCADA datasets are provided by Power Factors which has a vast database of information about performance of different power plants which is gathered by SCADA system at 1Hz frequency. The novel proposed model in this thesis is evaluated in healthy and abnormal operation modes of a wind farm in Quebec Province, Canada as case scenarios. Moreover, the error signal is calculated between real and predicted signals to evaluate the proper performance of the model. Finally, this model is compared with Multiple Linear Regression model to show the effectiveness and high precision of the proposed model.
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 distilled prediction
Teacher imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".