A Two-Stage Classification Method for Improved Fault Detection in Wind Turbines Based on SCADA Data
Jiazhi Dai, Mario Rotea, Nasser Kehtarnavaz · 2026
Read A Two-Stage Classification Method for Improved Fault Detection in Wind Turbines Based on SCADA Data by Jiazhi Dai, Mario Rotea, Nasser Kehtarnavaz (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13306862.txt.
Description
Jiazhi Dai split wind turbine fault hunting into two stages to handle skewed operating data in a 2026 study. Normal running records swamp fault records in SCADA logs, so single supervised models miss many real faults.
Stage one uses a one-class support vector method with two anomaly scores to pull odd records aside. Stage two runs a convolutional classifier only on those flagged records to name true faults among them. Trials on real turbine data beat plain supervised methods on accuracy and missed-fault rate in reported results, supporting the staged design.
Catalog record
| CREATOR | Jiazhi Dai, Mario Rotea, Nasser Kehtarnavaz |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 38612 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |