Title | ||
---|---|---|
Efficient residuals pre-processing for diagnosing multi-class faults in a doubly fed induction generator, under missing data scenarios. |
Abstract | ||
---|---|---|
•Extended fault diagnosis system for a doubly fed induction generator.•Improved the ensemble based decision module to allow incremental learning of new fault classes.•The pre-processing module generates the latent residuals.•The Wold cross-validation algorithm estimates the number of latent residuals.•The scheme can diagnose the faults under missing data scenarios. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1016/j.eswa.2014.03.056 | Expert Systems with Applications |
Keywords | Field | DocType |
Fault diagnosis,NIPALS,Wold cross-validation,Latent residuals,New class faults,Wind turbine | Residual,Data mining,Feature vector,Weighting,Operating point,Control theory,Computer science,Partial least squares regression,Algorithm,Turbine,Missing data,Principal component analysis | Journal |
Volume | Issue | ISSN |
41 | 14 | 0957-4174 |
Citations | PageRank | References |
11 | 0.75 | 10 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Roozbeh Razavi-Far | 1 | 95 | 19.93 |
Enrico Zio | 2 | 742 | 57.86 |
Vasile Palade | 3 | 20 | 2.16 |